USE CASE · ATEX WORKER SAFETY AIANWENDUNGSFALL · PERSONENERKENNUNG ATEXUSE CASE · ATEX WORKER SAFETY AIUSE CASE · ATEX WORKER SAFETY AIUSE CASE · ATEX WORKER SAFETY AIUSE CASE · ATEX WORKER SAFETY AIUSE CASE · IA DE SEGURANÇA ATEX

ATEX worker safety AI
for hazard-zone monitoring.
Personenerkennung KI
für ATEX-Zonen und Schutzbereiche.
ATEX worker safety AI
for hazard-zone monitoring.
ATEX worker safety AI
for hazard-zone monitoring.
ATEX worker safety AI
for hazard-zone monitoring.
ATEX worker safety AI
for hazard-zone monitoring.
IA de segurança ATEX
para monitoramento de zonas de risco.

A LiDAR + camera pair detects when a worker enters a hazardous area — ATEX zone, crane swing radius, conveyor pull-cord zone, automated cell — and feeds slow-down or hard-stop signals into the safety PLC before the worker is at risk. Works in dust, fog and low light. Every event is logged for the safety officer's audit trail. Custom-built for your zone topology and your plant safety logic.

LiDAR und Kamera erkennen, wenn jemand eine Gefahrenzone betritt — ATEX-Zone, Kran-Schwenkbereich, Reißleinen-Zone eines Förderbands, automatisierte Zelle — und speisen Verlangsamung oder Notabschaltung in die Sicherheits-SPS, bevor der Mitarbeiter in Gefahr ist. Arbeitet in Staub, Nebel und schlechtem Licht. Jedes Ereignis wird auditfähig für die Sicherheits-Beauftragten protokolliert. Nach Maß gebaut für Ihre Zonen-Topologie und Ihre Anlagen-Sicherheitslogik.

A LiDAR + camera pair detects when a worker enters a hazardous area — ATEX zone, crane swing radius, conveyor pull-cord zone, automated cell — and feeds slow-down or hard-stop signals into the safety PLC before the worker is at risk. Works in dust, fog and low light. Every event is logged for the safety officer's audit trail. Custom-built for your zone topology and your plant safety logic.

A LiDAR + camera pair detects when a worker enters a hazardous area — ATEX zone, crane swing radius, conveyor pull-cord zone, automated cell — and feeds slow-down or hard-stop signals into the safety PLC before the worker is at risk. Works in dust, fog and low light. Every event is logged for the safety officer's audit trail. Custom-built for your zone topology and your plant safety logic.

A LiDAR + camera pair detects when a worker enters a hazardous area — ATEX zone, crane swing radius, conveyor pull-cord zone, automated cell — and feeds slow-down or hard-stop signals into the safety PLC before the worker is at risk. Works in dust, fog and low light. Every event is logged for the safety officer's audit trail. Custom-built for your zone topology and your plant safety logic.

A LiDAR + camera pair detects when a worker enters a hazardous area — ATEX zone, crane swing radius, conveyor pull-cord zone, automated cell — and feeds slow-down or hard-stop signals into the safety PLC before the worker is at risk. Works in dust, fog and low light. Every event is logged for the safety officer's audit trail. Custom-built for your zone topology and your plant safety logic.

Um par LiDAR + câmera detecta quando um trabalhador entra numa área perigosa — zona ATEX, raio de giro de ponte rolante, zona de cabo de emergência de correia, célula automatizada — e envia sinais de desaceleração ou parada total ao PLC de segurança antes que o trabalhador esteja em risco. Funciona em poeira, névoa e pouca luz. Todo evento é registrado para a trilha de auditoria do técnico de segurança. Construído sob medida para a topologia das suas zonas e para a lógica de segurança da sua planta.

5–25 m typical detection rangetypische Erfassungsreichweitetypical detection rangetypical detection rangetypical detection rangetypical detection rangealcance típico de detecção
< 200 ms typical reaction timetypische Reaktionszeittypical reaction timetypical reaction timetypical reaction timetypical reaction timetempo típico de reação
Compatível ATEX sensor housings per zoneSensor-Gehäuse je Zonesensor housings per zonesensor housings per zonesensor housings per zonesensor housings per zoneinvólucros de sensor por zona
Auditável event log for the safety officerEreignis-Log für Sicherheits-Beauftragteevent log for the safety officerevent log for the safety officerevent log for the safety officerevent log for the safety officerlog de eventos para o técnico de segurança
USE CASEANWENDUNGSFALLUSE CASEUSE CASEUSE CASEUSE CASEUSE CASE  ·  ATEX worker safety AI · LiDAR + camera fusionPersonenerkennung ATEX · Fusion aus LiDAR und KameraATEX worker safety AI · LiDAR + camera fusionATEX worker safety AI · LiDAR + camera fusionATEX worker safety AI · LiDAR + camera fusionATEX worker safety AI · LiDAR + camera fusionIA de segurança ATEX · fusão LiDAR + câmera

Person detection in hazard zones, before the worker is at risk. Personen in Gefahrenzonen erkennen, bevor der Mitarbeiter in Gefahr ist. Person detection in hazard zones, before the worker is at risk. Person detection in hazard zones, before the worker is at risk. Person detection in hazard zones, before the worker is at risk. Person detection in hazard zones, before the worker is at risk. Detecção de pessoas em zonas de risco, antes que o trabalhador esteja em risco.

ATEX worker safety AI is a perception pipeline that detects people entering hazardous zones — ATEX areas, crane swing radius, conveyor pull-cord zones, automated-cell perimeters — and triggers PLC slow-down or hard-stop signals before the worker is at risk, with an auditable event log for the safety officer.Personenerkennung KI für ATEX-Zonen ist eine Wahrnehmungs-Pipeline, die Personen beim Betreten von Gefahrenbereichen — ATEX-Zonen, Kran-Schwenkbereich, Reißleinen-Zonen am Förderband, Perimeter automatisierter Zellen — detektiert und Verlangsamungs- oder Notabschalt-Signale in die Sicherheits-SPS speist, bevor der Mitarbeiter in Gefahr ist. Mit auditfähigem Ereignis-Log für die Sicherheits-Beauftragten.ATEX worker safety AI is a perception pipeline that detects people entering hazardous zones — ATEX areas, crane swing radius, conveyor pull-cord zones, automated-cell perimeters — and triggers PLC slow-down or hard-stop signals before the worker is at risk, with an auditable event log for the safety officer.ATEX worker safety AI is a perception pipeline that detects people entering hazardous zones — ATEX areas, crane swing radius, conveyor pull-cord zones, automated-cell perimeters — and triggers PLC slow-down or hard-stop signals before the worker is at risk, with an auditable event log for the safety officer.ATEX worker safety AI is a perception pipeline that detects people entering hazardous zones — ATEX areas, crane swing radius, conveyor pull-cord zones, automated-cell perimeters — and triggers PLC slow-down or hard-stop signals before the worker is at risk, with an auditable event log for the safety officer.ATEX worker safety AI is a perception pipeline that detects people entering hazardous zones — ATEX areas, crane swing radius, conveyor pull-cord zones, automated-cell perimeters — and triggers PLC slow-down or hard-stop signals before the worker is at risk, with an auditable event log for the safety officer.A IA de segurança ATEX é um pipeline de percepção que detecta pessoas entrando em zonas perigosas — áreas ATEX, raio de giro de ponte rolante, zonas de cabo de emergência de correia, perímetros de células automatizadas — e aciona sinais de desaceleração ou parada total no PLC antes que o trabalhador esteja em risco, com log de eventos auditável para o técnico de segurança.

The pain is structural in every dust- or gas-prone plant: existing ATEX safety relies on light-curtains, RFID badges and procedural lockout-tagout. Light curtains miss anyone who walks around them; RFID badges only protect the worker who actually wore one; lockout-tagout is bypassed under schedule pressure more often than safety departments care to admit. And when an incident does happen — a near-miss, a swing-radius excursion, a pull-cord trip — there is rarely a clean record of who was where, when, and why the protection failed. Dust, smoke and low light defeat camera-only systems exactly when you need them most.Der Schmerz ist strukturell in jeder staub- oder gasführenden Anlage: bestehende ATEX-Sicherheit stützt sich auf Lichtvorhänge, RFID-Marken und Lockout-Tagout-Verfahren. Lichtvorhänge übersehen jeden, der sie umgeht; RFID-Marken schützen nur den Mitarbeiter, der sie tatsächlich getragen hat; Lockout-Tagout wird unter Termindruck häufiger umgangen, als es den Arbeitssicherheits-Abteilungen lieb ist. Und wenn doch etwas passiert — Beinahe-Unfall, Schwenkbereichs-Überschreitung, Reißleinen-Auslösung — fehlt meist die saubere Aufzeichnung, wer wann wo war und warum der Schutz versagt hat. Staub, Rauch und schlechtes Licht setzen reine Kamera-Systeme genau dann außer Kraft, wenn man sie am dringendsten braucht.The pain is structural in every dust- or gas-prone plant: existing ATEX safety relies on light-curtains, RFID badges and procedural lockout-tagout. Light curtains miss anyone who walks around them; RFID badges only protect the worker who actually wore one; lockout-tagout is bypassed under schedule pressure more often than safety departments care to admit. And when an incident does happen — a near-miss, a swing-radius excursion, a pull-cord trip — there is rarely a clean record of who was where, when, and why the protection failed. Dust, smoke and low light defeat camera-only systems exactly when you need them most.The pain is structural in every dust- or gas-prone plant: existing ATEX safety relies on light-curtains, RFID badges and procedural lockout-tagout. Light curtains miss anyone who walks around them; RFID badges only protect the worker who actually wore one; lockout-tagout is bypassed under schedule pressure more often than safety departments care to admit. And when an incident does happen — a near-miss, a swing-radius excursion, a pull-cord trip — there is rarely a clean record of who was where, when, and why the protection failed. Dust, smoke and low light defeat camera-only systems exactly when you need them most.The pain is structural in every dust- or gas-prone plant: existing ATEX safety relies on light-curtains, RFID badges and procedural lockout-tagout. Light curtains miss anyone who walks around them; RFID badges only protect the worker who actually wore one; lockout-tagout is bypassed under schedule pressure more often than safety departments care to admit. And when an incident does happen — a near-miss, a swing-radius excursion, a pull-cord trip — there is rarely a clean record of who was where, when, and why the protection failed. Dust, smoke and low light defeat camera-only systems exactly when you need them most.The pain is structural in every dust- or gas-prone plant: existing ATEX safety relies on light-curtains, RFID badges and procedural lockout-tagout. Light curtains miss anyone who walks around them; RFID badges only protect the worker who actually wore one; lockout-tagout is bypassed under schedule pressure more often than safety departments care to admit. And when an incident does happen — a near-miss, a swing-radius excursion, a pull-cord trip — there is rarely a clean record of who was where, when, and why the protection failed. Dust, smoke and low light defeat camera-only systems exactly when you need them most.A dor é estrutural em qualquer planta com poeira ou gás: a segurança ATEX existente depende de cortinas de luz, crachás RFID e procedimentos de bloqueio-etiquetagem. Cortinas de luz não pegam quem passa por fora; crachás RFID só protegem o trabalhador que efetivamente vestiu um; o bloqueio-etiquetagem é burlado sob pressão de cronograma com mais frequência do que os departamentos de segurança gostam de admitir. E quando um incidente acontece — um quase-acidente, uma invasão do raio de giro, um puxão do cabo de emergência — raramente há um registro limpo de quem estava onde, quando, e por que a proteção falhou. Poeira, fumaça e pouca luz derrubam sistemas só de câmera exatamente quando você mais precisa deles.

Our approach fuses two sensors per zone. A 3D-LiDAR scans the zone geometry — point clouds penetrate dust and smoke far better than RGB, so the system still sees a person when the camera does not. A high-resolution camera adds confirmation — rules out forklifts, animals and pallets that would otherwise trigger false stops. Per-zone safety distance is configured per area (a crane swing radius needs a larger margin than a robot-cell perimeter), and the redundant detection writes interlock signals into the safety PLC. Every event — detection, slow-down, stop, all-clear — goes into an audit log with timestamp, zone, person count, sensor confidence and evidence frames.Unser Ansatz fusioniert zwei Sensoren je Zone. Ein 3D-LiDAR scannt die Zonen-Geometrie — Punktwolken durchdringen Staub und Rauch deutlich besser als RGB, das System sieht die Person also auch dann, wenn die Kamera versagt. Eine hochauflösende Kamera bestätigt die Detektion — schließt Stapler, Tiere und Paletten aus, die sonst Fehlauslösungen wären. Der Sicherheitsabstand wird pro Schutzzone konfiguriert (ein Kran-Schwenkbereich braucht einen größeren Abstand als ein Roboter-Zell-Perimeter), und die redundante Detektion schreibt Verriegelungs-Signale in die Sicherheits-SPS. Jedes Ereignis — Detektion, Verlangsamung, Stopp, Freigabe — geht ins Audit-Log mit Zeitstempel, Zone, Personenanzahl, Sensor-Konfidenz und Beweis-Frames.Our approach fuses two sensors per zone. A 3D-LiDAR scans the zone geometry — point clouds penetrate dust and smoke far better than RGB, so the system still sees a person when the camera does not. A high-resolution camera adds confirmation — rules out forklifts, animals and pallets that would otherwise trigger false stops. Per-zone safety distance is configured per area (a crane swing radius needs a larger margin than a robot-cell perimeter), and the redundant detection writes interlock signals into the safety PLC. Every event — detection, slow-down, stop, all-clear — goes into an audit log with timestamp, zone, person count, sensor confidence and evidence frames.Our approach fuses two sensors per zone. A 3D-LiDAR scans the zone geometry — point clouds penetrate dust and smoke far better than RGB, so the system still sees a person when the camera does not. A high-resolution camera adds confirmation — rules out forklifts, animals and pallets that would otherwise trigger false stops. Per-zone safety distance is configured per area (a crane swing radius needs a larger margin than a robot-cell perimeter), and the redundant detection writes interlock signals into the safety PLC. Every event — detection, slow-down, stop, all-clear — goes into an audit log with timestamp, zone, person count, sensor confidence and evidence frames.Our approach fuses two sensors per zone. A 3D-LiDAR scans the zone geometry — point clouds penetrate dust and smoke far better than RGB, so the system still sees a person when the camera does not. A high-resolution camera adds confirmation — rules out forklifts, animals and pallets that would otherwise trigger false stops. Per-zone safety distance is configured per area (a crane swing radius needs a larger margin than a robot-cell perimeter), and the redundant detection writes interlock signals into the safety PLC. Every event — detection, slow-down, stop, all-clear — goes into an audit log with timestamp, zone, person count, sensor confidence and evidence frames.Our approach fuses two sensors per zone. A 3D-LiDAR scans the zone geometry — point clouds penetrate dust and smoke far better than RGB, so the system still sees a person when the camera does not. A high-resolution camera adds confirmation — rules out forklifts, animals and pallets that would otherwise trigger false stops. Per-zone safety distance is configured per area (a crane swing radius needs a larger margin than a robot-cell perimeter), and the redundant detection writes interlock signals into the safety PLC. Every event — detection, slow-down, stop, all-clear — goes into an audit log with timestamp, zone, person count, sensor confidence and evidence frames.Nossa abordagem combina dois sensores por zona. Um LiDAR 3D varre a geometria da zona — nuvens de pontos penetram poeira e fumaça muito melhor do que RGB, então o sistema ainda enxerga uma pessoa quando a câmera não consegue. Uma câmera de alta resolução adiciona confirmação — descarta empilhadeiras, animais e paletes que de outro modo disparariam paradas falsas. A distância de segurança por zona é configurada por área (o raio de giro de uma ponte rolante precisa de uma margem maior do que o perímetro de uma célula robotizada), e a detecção redundante grava sinais de intertravamento no PLC de segurança. Todo evento — detecção, desaceleração, parada, tudo-livre — vai para um log de auditoria com timestamp, zona, contagem de pessoas, confiança do sensor e frames de evidência.

This is not an off-the-shelf safety appliance. ATEX zones, crane envelopes and plant safety logic differ per site. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically four to twelve weeks from contract to live tool, with the code and the model handed over to you at the end.Das ist kein Sicherheits-Gerät von der Stange. ATEX-Zonen, Kran-Hüllen und Anlagen-Sicherheitslogik unterscheiden sich pro Standort. Wir behandeln jedes Projekt als Discovery + Festscope-Build, abgeleitet aus unserem Hub-Service Industrielle Objekterkennung. Typisch vier bis zwölf Wochen vom Vertrag bis zum produktiven Tool — Code und Modell gehören Ihnen.This is not an off-the-shelf safety appliance. ATEX zones, crane envelopes and plant safety logic differ per site. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically four to twelve weeks from contract to live tool, with the code and the model handed over to you at the end.This is not an off-the-shelf safety appliance. ATEX zones, crane envelopes and plant safety logic differ per site. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically four to twelve weeks from contract to live tool, with the code and the model handed over to you at the end.This is not an off-the-shelf safety appliance. ATEX zones, crane envelopes and plant safety logic differ per site. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically four to twelve weeks from contract to live tool, with the code and the model handed over to you at the end.This is not an off-the-shelf safety appliance. ATEX zones, crane envelopes and plant safety logic differ per site. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically four to twelve weeks from contract to live tool, with the code and the model handed over to you at the end.Isto não é um equipamento de segurança de prateleira. Zonas ATEX, envelopes de ponte rolante e a lógica de segurança da planta variam por site. Tratamos cada engajamento como um build de descoberta + escopo fechado, descendo do nosso serviço-hub Industrial Perception AI. Tipicamente de quatro a doze semanas do contrato à ferramenta em produção, com o código e o modelo entregues a você ao final.

„A near-miss that nobody recorded is a near-miss that will happen again." „Ein Beinahe-Unfall, den niemand protokolliert hat, ist ein Beinahe-Unfall, der wiederkommt." „A near-miss that nobody recorded is a near-miss that will happen again." „A near-miss that nobody recorded is a near-miss that will happen again." „A near-miss that nobody recorded is a near-miss that will happen again." „A near-miss that nobody recorded is a near-miss that will happen again." "Um quase-acidente que ninguém registrou é um quase-acidente que vai acontecer de novo."

Built by the same team that delivers our LiDAR wagon-detection pipeline — six lid centroids, sub-5 cm error, two-second response. Gebaut von dem Team, das auch unsere LiDAR-Waggon-Erkennung liefert — sechs Deckel-Mittelpunkte, Fehler unter 5 cm, Antwort in zwei Sekunden. Built by the same team that delivers our LiDAR wagon-detection pipeline — six lid centroids, sub-5 cm error, two-second response. Built by the same team that delivers our LiDAR wagon-detection pipeline — six lid centroids, sub-5 cm error, two-second response. Built by the same team that delivers our LiDAR wagon-detection pipeline — six lid centroids, sub-5 cm error, two-second response. Built by the same team that delivers our LiDAR wagon-detection pipeline — six lid centroids, sub-5 cm error, two-second response. Construído pela mesma equipe que entrega nosso pipeline de detecção de vagões por LiDAR — seis centroides de tampa, erro sub-5 cm, resposta em dois segundos.

Three stagesDrei StufenThree stagesThree stagesThree stagesThree stagesTrês estágios

From sensor to safety PLC — three stages of the pipeline. Vom Sensor zur Sicherheits-SPS — drei Stufen der Pipeline. From sensor to safety PLC — three stages of the pipeline. From sensor to safety PLC — three stages of the pipeline. From sensor to safety PLC — three stages of the pipeline. From sensor to safety PLC — three stages of the pipeline. Do sensor ao PLC de segurança — três estágios do pipeline.

1 · Sensor coverage of the zone1 · Sensor-Abdeckung der Zone1 · Sensor coverage of the zone1 · Sensor coverage of the zone1 · Sensor coverage of the zone1 · Sensor coverage of the zone1 · Cobertura de sensores da zona

One or more LiDAR + camera pairs cover the hazardous zone with redundant overlap, so no single sensor failure leaves a blind spot. ATEX-aware sensor housings where the zone classification requires it (dust zone 22, gas zone 2, fertiliser silos, refinery process areas). Dust-tolerant optics, runs in fog, smoke and night light — the geometry channel keeps working when the visual channel struggles. Ein oder mehrere LiDAR-Kamera-Paare decken die Gefahrenzone mit redundanter Überlappung ab, damit kein einzelner Sensor-Ausfall einen toten Winkel hinterlässt. ATEX-taugliche Sensor-Gehäuse, wo die Zonen-Einstufung es verlangt (Staubzone 22, Gaszone 2, Düngemittel-Silos, Prozessbereiche in Raffinerien). Staubtolerante Optik, läuft in Nebel, Rauch und Nachtlicht — der Geometrie-Kanal arbeitet weiter, wenn der visuelle Kanal schwächelt. One or more LiDAR + camera pairs cover the hazardous zone with redundant overlap, so no single sensor failure leaves a blind spot. ATEX-aware sensor housings where the zone classification requires it (dust zone 22, gas zone 2, fertiliser silos, refinery process areas). Dust-tolerant optics, runs in fog, smoke and night light — the geometry channel keeps working when the visual channel struggles. One or more LiDAR + camera pairs cover the hazardous zone with redundant overlap, so no single sensor failure leaves a blind spot. ATEX-aware sensor housings where the zone classification requires it (dust zone 22, gas zone 2, fertiliser silos, refinery process areas). Dust-tolerant optics, runs in fog, smoke and night light — the geometry channel keeps working when the visual channel struggles. One or more LiDAR + camera pairs cover the hazardous zone with redundant overlap, so no single sensor failure leaves a blind spot. ATEX-aware sensor housings where the zone classification requires it (dust zone 22, gas zone 2, fertiliser silos, refinery process areas). Dust-tolerant optics, runs in fog, smoke and night light — the geometry channel keeps working when the visual channel struggles. One or more LiDAR + camera pairs cover the hazardous zone with redundant overlap, so no single sensor failure leaves a blind spot. ATEX-aware sensor housings where the zone classification requires it (dust zone 22, gas zone 2, fertiliser silos, refinery process areas). Dust-tolerant optics, runs in fog, smoke and night light — the geometry channel keeps working when the visual channel struggles. Um ou mais pares LiDAR + câmera cobrem a zona perigosa com sobreposição redundante, de modo que a falha de um único sensor não deixe um ponto cego. Invólucros compatíveis com ATEX onde a classificação de zona exige (Zona de poeira 22, Zona de gás 2, silos de fertilizantes, áreas de processo de refinaria). Ópticas tolerantes à poeira, operação em névoa, fumaça e luz noturna — o canal de geometria segue funcionando quando o canal visual falha.

2 · Person detection + confirmation2 · Personen-Detektion + Bestätigung2 · Person detection + confirmation2 · Person detection + confirmation2 · Person detection + confirmation2 · Person detection + confirmation2 · Detecção de pessoas + confirmação

LiDAR clusters persons by geometry — height, gait, motion signature — so the system separates a worker from a forklift or a pile of pallets. The camera confirms the detection visually, ruling out animals, vegetation and yard equipment that would otherwise trigger false stops. Per-zone safety distance is configured: crane envelopes need larger margins than a robot-cell perimeter. Der LiDAR clustert Personen über die Geometrie — Höhe, Gangbild, Bewegungs-Signatur — und trennt so den Mitarbeiter von einem Stapler oder einem Paletten-Stapel. Die Kamera bestätigt die Detektion visuell und schließt Tiere, Pflanzen und Hofgerät aus, die sonst Fehlauslösungen wären. Der Sicherheitsabstand wird pro Schutzzone konfiguriert: Kran-Hüllen brauchen größere Margen als ein Roboter-Zell-Perimeter. LiDAR clusters persons by geometry — height, gait, motion signature — so the system separates a worker from a forklift or a pile of pallets. The camera confirms the detection visually, ruling out animals, vegetation and yard equipment that would otherwise trigger false stops. Per-zone safety distance is configured: crane envelopes need larger margins than a robot-cell perimeter. LiDAR clusters persons by geometry — height, gait, motion signature — so the system separates a worker from a forklift or a pile of pallets. The camera confirms the detection visually, ruling out animals, vegetation and yard equipment that would otherwise trigger false stops. Per-zone safety distance is configured: crane envelopes need larger margins than a robot-cell perimeter. LiDAR clusters persons by geometry — height, gait, motion signature — so the system separates a worker from a forklift or a pile of pallets. The camera confirms the detection visually, ruling out animals, vegetation and yard equipment that would otherwise trigger false stops. Per-zone safety distance is configured: crane envelopes need larger margins than a robot-cell perimeter. LiDAR clusters persons by geometry — height, gait, motion signature — so the system separates a worker from a forklift or a pile of pallets. The camera confirms the detection visually, ruling out animals, vegetation and yard equipment that would otherwise trigger false stops. Per-zone safety distance is configured: crane envelopes need larger margins than a robot-cell perimeter. O LiDAR agrupa pessoas pela geometria — altura, marcha, assinatura de movimento — de modo que o sistema separa um trabalhador de uma empilhadeira ou de uma pilha de paletes. A câmera confirma a detecção visualmente, descartando animais, vegetação e equipamentos de pátio que de outro modo disparariam paradas falsas. A distância de segurança é configurada por zona: envelopes de ponte rolante precisam de margens maiores do que o perímetro de uma célula robotizada.

3 · PLC interlock + audit log3 · SPS-Verriegelung + Audit-Log3 · PLC interlock + audit log3 · PLC interlock + audit log3 · PLC interlock + audit log3 · PLC interlock + audit log3 · Intertravamento no PLC + log de auditoria

Confirmed detections feed into the plant safety PLC as slow-down or hard-stop signals over the existing safety bus. Every event — detection, slow-down, stop, all-clear — writes into the historian or safety database with timestamp, zone, person count, sensor confidence and evidence frames. The safety officer gets an auditable trail without manual paperwork. Bestätigte Detektionen speisen die Sicherheits-SPS als Verlangsamungs- oder Notabschalt-Signale über den bestehenden Sicherheits-Bus. Jedes Ereignis — Detektion, Verlangsamung, Stopp, Freigabe — schreibt in den Historian oder die Sicherheits-Datenbank mit Zeitstempel, Zone, Personenanzahl, Sensor-Konfidenz und Beweis-Frames. Die Sicherheits-Beauftragten bekommen einen auditfähigen Trail ohne Papierkram. Confirmed detections feed into the plant safety PLC as slow-down or hard-stop signals over the existing safety bus. Every event — detection, slow-down, stop, all-clear — writes into the historian or safety database with timestamp, zone, person count, sensor confidence and evidence frames. The safety officer gets an auditable trail without manual paperwork. Confirmed detections feed into the plant safety PLC as slow-down or hard-stop signals over the existing safety bus. Every event — detection, slow-down, stop, all-clear — writes into the historian or safety database with timestamp, zone, person count, sensor confidence and evidence frames. The safety officer gets an auditable trail without manual paperwork. Confirmed detections feed into the plant safety PLC as slow-down or hard-stop signals over the existing safety bus. Every event — detection, slow-down, stop, all-clear — writes into the historian or safety database with timestamp, zone, person count, sensor confidence and evidence frames. The safety officer gets an auditable trail without manual paperwork. Confirmed detections feed into the plant safety PLC as slow-down or hard-stop signals over the existing safety bus. Every event — detection, slow-down, stop, all-clear — writes into the historian or safety database with timestamp, zone, person count, sensor confidence and evidence frames. The safety officer gets an auditable trail without manual paperwork. Detecções confirmadas alimentam o PLC de segurança da planta como sinais de desaceleração ou parada total pelo barramento de segurança existente. Todo evento — detecção, desaceleração, parada, tudo-livre — é gravado no historian ou no banco de segurança, com timestamp, zona, contagem de pessoas, confiança do sensor e frames de evidência. O técnico de segurança recebe uma trilha auditável sem papelada manual.

Pipeline architecture · #how-it-worksPipeline-Architektur · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-worksArquitetura do pipeline · #how-it-works

How the pipeline works — concretely. Wie die Pipeline arbeitet — konkret. How the pipeline works — concretely. How the pipeline works — concretely. How the pipeline works — concretely. How the pipeline works — concretely. Como o pipeline funciona — concretamente.

We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. Wir halten die Architektur absichtlich langweilig. Drei lose gekoppelte Stufen, jede einzeln testbar, jede einzeln tauschbar, wenn sich der Sensor-Stack ändert. Gebaut auf demselben Stack, den wir für unsere gesamte Wahrnehmungs-Arbeit nutzen: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. Mantemos a arquitetura chata de propósito. Três estágios pouco acoplados, cada um testável de forma independente, cada um substituível quando o stack de sensores muda. Construído sobre o mesmo stack que usamos em todo o nosso trabalho de percepção: PCL, Open3D, OpenCV, PyTorch.

01

Multi-sensor capture in dust + smokeMulti-Sensor-Aufnahme in Staub und RauchMulti-sensor capture in dust + smokeMulti-sensor capture in dust + smokeMulti-sensor capture in dust + smokeMulti-sensor capture in dust + smokeCaptura multi-sensor em poeira + fumaça

Each LiDAR delivers a 3D point cloud of the zone — typically several hundred thousand points per scan, multiple times per second. Cameras add synchronised colour frames, lens-calibrated and time-stamped. Raw data writes to local storage with a per-event UUID for audit trail and re-labelling. The LiDAR channel is the resilience layer: it keeps reporting geometry when dust, fog or low light blind the camera. Jeder LiDAR liefert eine 3D-Punktwolke der Zone — typisch mehrere hunderttausend Punkte pro Scan, mehrmals pro Sekunde. Kameras ergänzen synchronisierte Farb-Frames, objektiv-kalibriert und zeit-gestempelt. Rohdaten schreiben auf lokalen Speicher mit Ereignis-UUID für Audit-Trail und Re-Labelling. Der LiDAR-Kanal ist die Resilienz-Schicht: er meldet weiter Geometrie, wenn Staub, Nebel oder schlechtes Licht die Kamera blind machen. Each LiDAR delivers a 3D point cloud of the zone — typically several hundred thousand points per scan, multiple times per second. Cameras add synchronised colour frames, lens-calibrated and time-stamped. Raw data writes to local storage with a per-event UUID for audit trail and re-labelling. The LiDAR channel is the resilience layer: it keeps reporting geometry when dust, fog or low light blind the camera. Each LiDAR delivers a 3D point cloud of the zone — typically several hundred thousand points per scan, multiple times per second. Cameras add synchronised colour frames, lens-calibrated and time-stamped. Raw data writes to local storage with a per-event UUID for audit trail and re-labelling. The LiDAR channel is the resilience layer: it keeps reporting geometry when dust, fog or low light blind the camera. Each LiDAR delivers a 3D point cloud of the zone — typically several hundred thousand points per scan, multiple times per second. Cameras add synchronised colour frames, lens-calibrated and time-stamped. Raw data writes to local storage with a per-event UUID for audit trail and re-labelling. The LiDAR channel is the resilience layer: it keeps reporting geometry when dust, fog or low light blind the camera. Each LiDAR delivers a 3D point cloud of the zone — typically several hundred thousand points per scan, multiple times per second. Cameras add synchronised colour frames, lens-calibrated and time-stamped. Raw data writes to local storage with a per-event UUID for audit trail and re-labelling. The LiDAR channel is the resilience layer: it keeps reporting geometry when dust, fog or low light blind the camera. Cada LiDAR entrega uma nuvem de pontos 3D da zona — tipicamente várias centenas de milhares de pontos por varredura, várias vezes por segundo. Câmeras acrescentam frames coloridos sincronizados, calibrados por lente e com timestamp. Os dados brutos são gravados em armazenamento local com um UUID por evento para trilha de auditoria e rerrotulagem. O canal LiDAR é a camada de resiliência: continua reportando geometria quando poeira, névoa ou pouca luz cegam a câmera.

02

Person classification + safety-distance calculationPersonen-Klassifikation + SicherheitsabstandPerson classification + safety-distance calculationPerson classification + safety-distance calculationPerson classification + safety-distance calculationPerson classification + safety-distance calculationClassificação de pessoas + cálculo da distância de segurança

The point cloud goes through ground removal, voxel down-sampling and a person classifier trained on real plant data — workers in PPE, helmets, high-vis vests, not the office benchmark. The camera image goes through a second classifier on the same target. Both heads fuse into a confirmed person track with a measured distance to the configured zone boundary. False-positive rate is tuned per zone; the safety distance is configurable per area. Die Punktwolke läuft durch Boden-Entfernung, Voxel-Downsampling und einen Personen-Klassifikator, trainiert auf echten Anlagendaten — Mitarbeiter in PSA, Helm und Warnweste, nicht der Büro-Benchmark. Das Kamerabild läuft durch einen zweiten Klassifikator auf dasselbe Ziel. Beide Köpfe fusionieren zu einer bestätigten Personen-Spur mit gemessenem Abstand zur konfigurierten Zonen-Grenze. Die Fehlauslösungs-Rate wird pro Zone abgestimmt; der Sicherheitsabstand ist pro Bereich konfigurierbar. The point cloud goes through ground removal, voxel down-sampling and a person classifier trained on real plant data — workers in PPE, helmets, high-vis vests, not the office benchmark. The camera image goes through a second classifier on the same target. Both heads fuse into a confirmed person track with a measured distance to the configured zone boundary. False-positive rate is tuned per zone; the safety distance is configurable per area. The point cloud goes through ground removal, voxel down-sampling and a person classifier trained on real plant data — workers in PPE, helmets, high-vis vests, not the office benchmark. The camera image goes through a second classifier on the same target. Both heads fuse into a confirmed person track with a measured distance to the configured zone boundary. False-positive rate is tuned per zone; the safety distance is configurable per area. The point cloud goes through ground removal, voxel down-sampling and a person classifier trained on real plant data — workers in PPE, helmets, high-vis vests, not the office benchmark. The camera image goes through a second classifier on the same target. Both heads fuse into a confirmed person track with a measured distance to the configured zone boundary. False-positive rate is tuned per zone; the safety distance is configurable per area. The point cloud goes through ground removal, voxel down-sampling and a person classifier trained on real plant data — workers in PPE, helmets, high-vis vests, not the office benchmark. The camera image goes through a second classifier on the same target. Both heads fuse into a confirmed person track with a measured distance to the configured zone boundary. False-positive rate is tuned per zone; the safety distance is configurable per area. A nuvem de pontos passa por remoção de solo, subamostragem por voxel e um classificador de pessoas treinado em dados reais de planta — trabalhadores em EPI, capacetes, coletes refletivos, não o benchmark de escritório. A imagem da câmera passa por um segundo classificador no mesmo alvo. Os dois heads se fundem numa trilha de pessoa confirmada com distância medida até o limite da zona configurada. A taxa de falso-positivo é ajustada por zona; a distância de segurança é configurável por área.

03

PLC interlock + event-log write-backSPS-Verriegelung + Ereignis-Log-RückschreibungPLC interlock + event-log write-backPLC interlock + event-log write-backPLC interlock + event-log write-backPLC interlock + event-log write-backIntertravamento no PLC + gravação do log de eventos

Confirmed track crossing a zone boundary triggers a slow-down or hard-stop signal into the safety PLC over the existing safety bus — Profisafe, CIP Safety, or hard-wired safety outputs per project. Simultaneously the event writes into the historian or safety database: timestamp, zone, person count, confidence, evidence frames. The control-room operator sees the live overlay on the HUD; the safety officer queries the database for the audit trail. Eine bestätigte Spur, die eine Zonen-Grenze überschreitet, löst ein Verlangsamungs- oder Notabschalt-Signal in die Sicherheits-SPS aus — über den bestehenden Sicherheits-Bus, Profisafe, CIP Safety oder fest verdrahtete Sicherheits-Ausgänge je Projekt. Parallel schreibt das Ereignis in den Historian oder die Sicherheits-Datenbank: Zeitstempel, Zone, Personenanzahl, Konfidenz, Beweis-Frames. Der Leitstand-Operator sieht das Live-Overlay im HUD; die Sicherheits-Beauftragten fragen die Datenbank für den Audit-Trail ab. Confirmed track crossing a zone boundary triggers a slow-down or hard-stop signal into the safety PLC over the existing safety bus — Profisafe, CIP Safety, or hard-wired safety outputs per project. Simultaneously the event writes into the historian or safety database: timestamp, zone, person count, confidence, evidence frames. The control-room operator sees the live overlay on the HUD; the safety officer queries the database for the audit trail. Confirmed track crossing a zone boundary triggers a slow-down or hard-stop signal into the safety PLC over the existing safety bus — Profisafe, CIP Safety, or hard-wired safety outputs per project. Simultaneously the event writes into the historian or safety database: timestamp, zone, person count, confidence, evidence frames. The control-room operator sees the live overlay on the HUD; the safety officer queries the database for the audit trail. Confirmed track crossing a zone boundary triggers a slow-down or hard-stop signal into the safety PLC over the existing safety bus — Profisafe, CIP Safety, or hard-wired safety outputs per project. Simultaneously the event writes into the historian or safety database: timestamp, zone, person count, confidence, evidence frames. The control-room operator sees the live overlay on the HUD; the safety officer queries the database for the audit trail. Confirmed track crossing a zone boundary triggers a slow-down or hard-stop signal into the safety PLC over the existing safety bus — Profisafe, CIP Safety, or hard-wired safety outputs per project. Simultaneously the event writes into the historian or safety database: timestamp, zone, person count, confidence, evidence frames. The control-room operator sees the live overlay on the HUD; the safety officer queries the database for the audit trail. Uma trilha confirmada cruzando o limite de uma zona aciona um sinal de desaceleração ou parada total no PLC de segurança pelo barramento de segurança existente — Profisafe, CIP Safety ou saídas de segurança cabeadas, por projeto. Simultaneamente o evento é gravado no historian ou no banco de segurança: timestamp, zona, contagem de pessoas, confiança, frames de evidência. O operador da sala de controle vê a sobreposição ao vivo no HUD; o técnico de segurança consulta o banco para a trilha de auditoria.

All three stages run on an industrial PC at the zone cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. Alle drei Stufen laufen auf einem Industrie-PC im Zonen-Schaltschrank. Keine Cloud-Abhängigkeit, keine externe API, kein Lizenz-Heimruf. Der Code gehört Ihnen bei der Übergabe. All three stages run on an industrial PC at the zone cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC at the zone cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC at the zone cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC at the zone cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. Todos os três estágios rodam num PC industrial no armário da zona. Sem dependência de nuvem, sem API externa, sem licença que "telefona para casa". O código é seu na entrega.

What you getWas Sie bekommenWhat you getWhat you getWhat you getWhat you getO que você recebe

Three deliverables — from the same pipeline. Drei Liefer-Ergebnisse — aus derselben Pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline. Três entregáveis — a partir do mesmo pipeline.

Real-time safety interlockEchtzeit-Sicherheits-VerriegelungReal-time safety interlockReal-time safety interlockReal-time safety interlockReal-time safety interlockIntertravamento de segurança em tempo real

Slow-down and hard-stop signals into the plant safety PLC, over the safety bus or hard-wired safety outputs. The safety logic stays under your existing functional-safety regime — we feed the inputs; your safety PLC owns the decision and the certification scope. Verlangsamungs- und Notabschalt-Signale in die Sicherheits-SPS, über den Sicherheits-Bus oder fest verdrahtete Sicherheits-Ausgänge. Die Sicherheits-Logik bleibt in Ihrem bestehenden funktionalen Sicherheits-Regime — wir speisen die Eingänge; Ihre Sicherheits-SPS besitzt die Entscheidung und den Zertifizierungs-Scope. Slow-down and hard-stop signals into the plant safety PLC, over the safety bus or hard-wired safety outputs. The safety logic stays under your existing functional-safety regime — we feed the inputs; your safety PLC owns the decision and the certification scope. Slow-down and hard-stop signals into the plant safety PLC, over the safety bus or hard-wired safety outputs. The safety logic stays under your existing functional-safety regime — we feed the inputs; your safety PLC owns the decision and the certification scope. Slow-down and hard-stop signals into the plant safety PLC, over the safety bus or hard-wired safety outputs. The safety logic stays under your existing functional-safety regime — we feed the inputs; your safety PLC owns the decision and the certification scope. Slow-down and hard-stop signals into the plant safety PLC, over the safety bus or hard-wired safety outputs. The safety logic stays under your existing functional-safety regime — we feed the inputs; your safety PLC owns the decision and the certification scope. Sinais de desaceleração e parada total no PLC de segurança da planta, pelo barramento de segurança ou por saídas de segurança cabeadas. A lógica de segurança permanece sob o seu regime de segurança funcional já existente — nós alimentamos as entradas; o seu PLC de segurança detém a decisão e o escopo de certificação.

Audit-grade event logAuditfähiges Ereignis-LogAudit-grade event logAudit-grade event logAudit-grade event logAudit-grade event logLog de eventos com qualidade de auditoria

Every detection logged with timestamp, person count, zone, sensor confidence and evidence frames. Feeds your safety database, your historian, your incident-investigation workflow — the same temporal model we use on stockpile monitoring, applied to safety events instead of material piles. Jede Detektion protokolliert mit Zeitstempel, Personenanzahl, Zone, Sensor-Konfidenz und Beweis-Frames. Speist Ihre Sicherheits-Datenbank, Ihren Historian, Ihren Vorfalls-Untersuchungs-Workflow — dasselbe zeitliche Modell, das wir auf Halden-Monitoring einsetzen, übertragen auf Sicherheits-Ereignisse statt Materialhalden. Every detection logged with timestamp, person count, zone, sensor confidence and evidence frames. Feeds your safety database, your historian, your incident-investigation workflow — the same temporal model we use on stockpile monitoring, applied to safety events instead of material piles. Every detection logged with timestamp, person count, zone, sensor confidence and evidence frames. Feeds your safety database, your historian, your incident-investigation workflow — the same temporal model we use on stockpile monitoring, applied to safety events instead of material piles. Every detection logged with timestamp, person count, zone, sensor confidence and evidence frames. Feeds your safety database, your historian, your incident-investigation workflow — the same temporal model we use on stockpile monitoring, applied to safety events instead of material piles. Every detection logged with timestamp, person count, zone, sensor confidence and evidence frames. Feeds your safety database, your historian, your incident-investigation workflow — the same temporal model we use on stockpile monitoring, applied to safety events instead of material piles. Toda detecção registrada com timestamp, contagem de pessoas, zona, confiança do sensor e frames de evidência. Alimenta o seu banco de segurança, o seu historian, o seu fluxo de investigação de incidentes — o mesmo modelo temporal que usamos no monitoramento de pilhas, aplicado a eventos de segurança em vez de pilhas de material.

Operator HUDOperator-HUDOperator HUDOperator HUDOperator HUDOperator HUDHUD do operador

A live overlay so the control-room operator sees who is where in real time — zone outlines, active detections, current safety state per area. Same dashboard surfaces the recent event history for shift handover and supervisor reviews. Ein Live-Overlay, damit der Leitstand-Operator in Echtzeit sieht, wer wo ist — Zonen-Umrisse, aktive Detektionen, aktueller Sicherheits-Status je Bereich. Dasselbe Dashboard zeigt die jüngste Ereignis-Historie für Schichtübergabe und Vorgesetzten-Reviews. A live overlay so the control-room operator sees who is where in real time — zone outlines, active detections, current safety state per area. Same dashboard surfaces the recent event history for shift handover and supervisor reviews. A live overlay so the control-room operator sees who is where in real time — zone outlines, active detections, current safety state per area. Same dashboard surfaces the recent event history for shift handover and supervisor reviews. A live overlay so the control-room operator sees who is where in real time — zone outlines, active detections, current safety state per area. Same dashboard surfaces the recent event history for shift handover and supervisor reviews. A live overlay so the control-room operator sees who is where in real time — zone outlines, active detections, current safety state per area. Same dashboard surfaces the recent event history for shift handover and supervisor reviews. Uma sobreposição ao vivo para que o operador da sala de controle veja quem está onde em tempo real — contornos de zona, detecções ativas, estado de segurança atual por área. O mesmo dashboard mostra o histórico recente de eventos para passagem de turno e revisão do supervisor.

Why customWarum CustomWhy customWhy customWhy customWhy customPor que sob medida

Why a custom build — not an off-the-shelf product. Warum nach Maß — und nicht von der Stange. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product. Por que um build sob medida — e não um produto de prateleira.

Every plant has its own ATEX zone topology, its own crane envelopes, its own safety PLC and its own lockout-tagout culture. A generic safety appliance solves the generic case; your case is not the generic case. Jede Anlage hat eigene ATEX-Zonen-Topologie, eigene Kran-Hüllen, eigene Sicherheits-SPS und eigene Lockout-Tagout-Kultur. Ein generisches Sicherheits-Gerät löst den generischen Fall; Ihr Fall ist nicht der generische Fall. Every plant has its own ATEX zone topology, its own crane envelopes, its own safety PLC and its own lockout-tagout culture. A generic safety appliance solves the generic case; your case is not the generic case. Every plant has its own ATEX zone topology, its own crane envelopes, its own safety PLC and its own lockout-tagout culture. A generic safety appliance solves the generic case; your case is not the generic case. Every plant has its own ATEX zone topology, its own crane envelopes, its own safety PLC and its own lockout-tagout culture. A generic safety appliance solves the generic case; your case is not the generic case. Every plant has its own ATEX zone topology, its own crane envelopes, its own safety PLC and its own lockout-tagout culture. A generic safety appliance solves the generic case; your case is not the generic case. Cada planta tem a sua própria topologia de zonas ATEX, seus próprios envelopes de ponte rolante, seu próprio PLC de segurança e sua própria cultura de bloqueio-etiquetagem. Um equipamento genérico de segurança resolve o caso genérico; o seu caso não é o caso genérico.

Zone-specific safety distance configurationZonen-spezifische Sicherheitsabstand-KonfigurationZone-specific safety distance configurationZone-specific safety distance configurationZone-specific safety distance configurationZone-specific safety distance configurationConfiguração da distância de segurança específica por zona

A crane swing radius needs a larger margin than a robot-cell perimeter; a fertiliser silo with explosive-dust risk needs a different reaction profile than a wood-pellet conveyor. We configure the safety distance, the reaction curve and the false-positive tuning per zone — not one global threshold for everything. Ein Kran-Schwenkbereich braucht einen größeren Abstand als ein Roboter-Zell-Perimeter; ein Düngemittel-Silo mit Staubexplosions-Risiko braucht eine andere Reaktionskurve als ein Holzpellet-Förderband. Wir konfigurieren Sicherheitsabstand, Reaktionskurve und Fehlauslösungs-Abstimmung pro Schutzzone — nicht eine globale Schwelle für alles. A crane swing radius needs a larger margin than a robot-cell perimeter; a fertiliser silo with explosive-dust risk needs a different reaction profile than a wood-pellet conveyor. We configure the safety distance, the reaction curve and the false-positive tuning per zone — not one global threshold for everything. A crane swing radius needs a larger margin than a robot-cell perimeter; a fertiliser silo with explosive-dust risk needs a different reaction profile than a wood-pellet conveyor. We configure the safety distance, the reaction curve and the false-positive tuning per zone — not one global threshold for everything. A crane swing radius needs a larger margin than a robot-cell perimeter; a fertiliser silo with explosive-dust risk needs a different reaction profile than a wood-pellet conveyor. We configure the safety distance, the reaction curve and the false-positive tuning per zone — not one global threshold for everything. A crane swing radius needs a larger margin than a robot-cell perimeter; a fertiliser silo with explosive-dust risk needs a different reaction profile than a wood-pellet conveyor. We configure the safety distance, the reaction curve and the false-positive tuning per zone — not one global threshold for everything. O raio de giro de uma ponte rolante precisa de uma margem maior do que o perímetro de uma célula robotizada; um silo de fertilizante com risco de poeira explosiva precisa de um perfil de reação diferente do de uma correia de pellets de madeira. Configuramos a distância de segurança, a curva de reação e o ajuste de falso-positivo por zona — não um limiar global único para tudo.

Sensor + housing selection for the actual environmentSensor- und Gehäuse-Auswahl für die echte UmgebungSensor + housing selection for the actual environmentSensor + housing selection for the actual environmentSensor + housing selection for the actual environmentSensor + housing selection for the actual environmentEscolha de sensor + invólucro para o ambiente real

ATEX-aware sensor housings where the zone classification requires it — dust zone 22 in grain and pellet handling, gas zone 2 in refinery and chemical, dust-and-gas hybrids in fertiliser, IP66+ wash-down in foundry. We pick the housing per zone, not one catalogue option for the whole plant. ATEX-taugliche Sensor-Gehäuse, wo die Zonen-Einstufung es verlangt — Staubzone 22 in Getreide- und Pellet-Handling, Gaszone 2 in Raffinerie und Chemie, Staub-Gas-Mischformen in Düngemittel-Anlagen, IP66+ Wash-Down in der Gießerei. Wir wählen das Gehäuse pro Zone, nicht eine Katalog-Option für die ganze Anlage. ATEX-aware sensor housings where the zone classification requires it — dust zone 22 in grain and pellet handling, gas zone 2 in refinery and chemical, dust-and-gas hybrids in fertiliser, IP66+ wash-down in foundry. We pick the housing per zone, not one catalogue option for the whole plant. ATEX-aware sensor housings where the zone classification requires it — dust zone 22 in grain and pellet handling, gas zone 2 in refinery and chemical, dust-and-gas hybrids in fertiliser, IP66+ wash-down in foundry. We pick the housing per zone, not one catalogue option for the whole plant. ATEX-aware sensor housings where the zone classification requires it — dust zone 22 in grain and pellet handling, gas zone 2 in refinery and chemical, dust-and-gas hybrids in fertiliser, IP66+ wash-down in foundry. We pick the housing per zone, not one catalogue option for the whole plant. ATEX-aware sensor housings where the zone classification requires it — dust zone 22 in grain and pellet handling, gas zone 2 in refinery and chemical, dust-and-gas hybrids in fertiliser, IP66+ wash-down in foundry. We pick the housing per zone, not one catalogue option for the whole plant. Invólucros compatíveis com ATEX onde a classificação de zona exige — Zona de poeira 22 em grãos e pellets, Zona de gás 2 em refinaria e química, híbridos poeira-e-gás em fertilizantes, IP66+ lava-jato em fundição. Escolhemos o invólucro por zona, não uma única opção de catálogo para toda a planta.

Integration with existing safety PLC + lockout-tagoutAnbindung an bestehende Sicherheits-SPS + Lockout-TagoutIntegration with existing safety PLC + lockout-tagoutIntegration with existing safety PLC + lockout-tagoutIntegration with existing safety PLC + lockout-tagoutIntegration with existing safety PLC + lockout-tagoutIntegração com PLC de segurança e bloqueio-etiquetagem existentes

Most plants already have a safety PLC, light curtains, RFID badges and a lockout-tagout procedure. We feed our detections into what's already there as additional inputs — we do not replace your functional-safety regime. Profisafe, CIP Safety, hard-wired safety outputs and OPC UA for the non-safety audit channel all supported. Die meisten Anlagen haben bereits eine Sicherheits-SPS, Lichtvorhänge, RFID-Marken und ein Lockout-Tagout-Verfahren. Wir speisen unsere Detektionen als zusätzliche Eingänge in das, was schon da ist — wir ersetzen Ihr funktionales Sicherheits-Regime nicht. Profisafe, CIP Safety, fest verdrahtete Sicherheits-Ausgänge und OPC UA für den nicht-sicherheits-relevanten Audit-Kanal — alles unterstützt. Most plants already have a safety PLC, light curtains, RFID badges and a lockout-tagout procedure. We feed our detections into what's already there as additional inputs — we do not replace your functional-safety regime. Profisafe, CIP Safety, hard-wired safety outputs and OPC UA for the non-safety audit channel all supported. Most plants already have a safety PLC, light curtains, RFID badges and a lockout-tagout procedure. We feed our detections into what's already there as additional inputs — we do not replace your functional-safety regime. Profisafe, CIP Safety, hard-wired safety outputs and OPC UA for the non-safety audit channel all supported. Most plants already have a safety PLC, light curtains, RFID badges and a lockout-tagout procedure. We feed our detections into what's already there as additional inputs — we do not replace your functional-safety regime. Profisafe, CIP Safety, hard-wired safety outputs and OPC UA for the non-safety audit channel all supported. Most plants already have a safety PLC, light curtains, RFID badges and a lockout-tagout procedure. We feed our detections into what's already there as additional inputs — we do not replace your functional-safety regime. Profisafe, CIP Safety, hard-wired safety outputs and OPC UA for the non-safety audit channel all supported. A maioria das plantas já tem PLC de segurança, cortinas de luz, crachás RFID e um procedimento de bloqueio-etiquetagem. Alimentamos nossas detecções no que já existe como entradas adicionais — não substituímos o seu regime de segurança funcional. Profisafe, CIP Safety, saídas de segurança cabeadas e OPC UA para o canal de auditoria não relacionado à segurança, todos suportados.

IP ownership + audit-log ownershipIP-Eigentum + Audit-Log-EigentumIP ownership + audit-log ownershipIP ownership + audit-log ownershipIP ownership + audit-log ownershipIP ownership + audit-log ownershipTitularidade da PI + titularidade do log de auditoria

You own the source code, the model weights, the labelled dataset and the audit log at handover. The audit log lives in your historian, not on a vendor cloud. We document the system, train your team, and walk away clean. No black box, no monthly per-zone licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. Sie besitzen Quellcode, Modell-Gewichte, gelabelten Datensatz und Audit-Log nach der Übergabe. Das Audit-Log lebt in Ihrem Historian, nicht in einer Anbieter-Cloud. Wir dokumentieren das System, schulen Ihr Team und gehen sauber raus. Keine Black Box, keine monatliche Pro-Zonen-Lizenz, kein Servicevertrag, aus dem Sie nicht rauskommen. Standard-Bedingungen siehe unsere FAQs zu IP und Zusammenarbeits-Modell. You own the source code, the model weights, the labelled dataset and the audit log at handover. The audit log lives in your historian, not on a vendor cloud. We document the system, train your team, and walk away clean. No black box, no monthly per-zone licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the model weights, the labelled dataset and the audit log at handover. The audit log lives in your historian, not on a vendor cloud. We document the system, train your team, and walk away clean. No black box, no monthly per-zone licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the model weights, the labelled dataset and the audit log at handover. The audit log lives in your historian, not on a vendor cloud. We document the system, train your team, and walk away clean. No black box, no monthly per-zone licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the model weights, the labelled dataset and the audit log at handover. The audit log lives in your historian, not on a vendor cloud. We document the system, train your team, and walk away clean. No black box, no monthly per-zone licence, no service contract you can't exit. See our FAQs on IP and engagement model for the standard terms. Você é dono do código-fonte, dos pesos do modelo, do dataset rotulado e do log de auditoria na entrega. O log de auditoria vive no seu historian, não numa nuvem de fornecedor. Documentamos o sistema, treinamos a sua equipe e saímos limpos. Sem caixa-preta, sem licença mensal por zona, sem contrato de serviço do qual você não possa sair. Veja nossas FAQs sobre PI e modelo de contratação para os termos padrão.

FAQ

Questions about ATEX worker safety AI. Fragen zur Personenerkennung in ATEX-Zonen. Questions about ATEX worker safety AI. Questions about ATEX worker safety AI. Questions about ATEX worker safety AI. Questions about ATEX worker safety AI. Perguntas sobre IA de segurança ATEX.

The engagement-model questions we hear from every plant safety officer considering a custom perception build. Need something more specific to your zone? Ask us. Die Fragen zum Zusammenarbeits-Modell, die wir von jedem Sicherheits-Beauftragten hören, der einen Custom-Perception-Build erwägt. Brauchen Sie etwas Spezifischeres zu Ihrer Zone? Sprechen Sie uns an. The engagement-model questions we hear from every plant safety officer considering a custom perception build. Need something more specific to your zone? Ask us. The engagement-model questions we hear from every plant safety officer considering a custom perception build. Need something more specific to your zone? Ask us. The engagement-model questions we hear from every plant safety officer considering a custom perception build. Need something more specific to your zone? Ask us. The engagement-model questions we hear from every plant safety officer considering a custom perception build. Need something more specific to your zone? Ask us. As perguntas sobre modelo de contratação que ouvimos de todo técnico de segurança de planta considerando um build sob medida de percepção. Precisa de algo mais específico para a sua zona? Fale com a gente.

Industrial Perception AIIndustrielle ObjekterkennungIndustrial Perception AIIndustrial Perception AIIndustrial Perception AIIndustrial Perception AIIndustrial Perception AI

What does custom perception AI software cost?Was kostet maßgeschneiderte Wahrnehmungs-Software?What does custom perception AI software cost?What does custom perception AI software cost?What does custom perception AI software cost?What does custom perception AI software cost?Quanto custa um software de perception AI sob medida?
We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers. Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors. Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth. Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included. All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model. Wir veröffentlichen keine Listenpreise, weil jedes Projekt auf Ihre Daten und Ihre Entscheidungs-Logik zugeschnitten wird — aber wir arbeiten in drei berechenbaren Tiers. Discovery & Assessment — ein 1–3-tägiger Workshop, vor Ort oder remote, Festpreis im unteren vierstelligen Bereich. Sie erhalten eine schriftliche Machbarkeits-Note, einen empfohlenen nächsten Schritt und ggf. ein Festpreis-Angebot für das Folge-Projekt. Lohnt sich auch ohne Folge-Auftrag — viele Kunden nutzen die Note, um zwei oder drei Anbieter zu vergleichen. Custom Pipeline / Tool — ein 4–12-Wochen-Projekt, das eine fertige Wahrnehmungs-Pipeline liefert (Parser + Algorithmus + Dashboard oder OPC-UA-Anbindung). Fester Scope, Festpreis, Code-Übergabe am Ende. Übliche Projektgröße liegt im mittleren fünf- bis unteren sechsstelligen Bereich, je nach Datenvolumen, Sensor-Anzahl und Integrations-Tiefe. Langfristige Partnerschaft — monatlicher Retainer für laufende Entwicklung und On-Call-Support. Dimensioniert nach benötigter Team-Kapazität (typisch 0,5–2 FTE-Äquivalente). Quartalsweise Roadmap inklusive. Alle drei Tiers enthalten Quellcode, schriftliche Dokumentation und saubere Übergabe — keine Lizenz-Abhängigkeit von uns. Vollständiges Zusammenarbeits-Modell siehe unsere Industrielle Objekterkennung. We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers. Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors. Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth. Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included. All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model. We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers. Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors. Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth. Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included. All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model. We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers. Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors. Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth. Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included. All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model. We don't publish list prices because every project is scoped against your data and your decision logic — but we work to three predictable tiers. Discovery & Assessment — a 1–3 day workshop, on-site or remote, fixed price in the low-four-figure range. You receive a written feasibility note, a recommended next step and (if applicable) a fixed-price quote for the follow-on project. Useful even if you don't then go ahead — many customers use the note to evaluate two or three vendors. Custom Pipeline / Tool — a 4–12 week project delivering a working perception pipeline (parser + algorithm + dashboard or OPC UA integration). Fixed scope, fixed price, you own the code at handover. Typical project size is in the mid-five to low-six-figure range depending on data volume, sensor count and integration depth. Long-term Partnership — a monthly retainer for ongoing development and on-call support. Sized to the team capacity you need (typically 0.5–2 FTE equivalent). Quarterly road-mapping included. All three tiers include source code, written documentation and a clean handover — no licence dependence on us. See our Industrial Perception AI service for the full engagement model. Não divulgamos preços de tabela porque cada projeto é dimensionado conforme os seus dados e a sua lógica de decisão — mas trabalhamos em três tiers previsíveis. Discovery & Assessment — um workshop de 1 a 3 dias, presencial ou remoto, preço fechado na faixa dos quatro dígitos baixos. Você recebe uma nota escrita de viabilidade, um próximo passo recomendado e (se aplicável) uma proposta de preço fechado para o projeto subsequente. Útil mesmo que você não avance depois — muitos clientes usam a nota para avaliar dois ou três fornecedores. Custom Pipeline / Tool — um projeto de 4 a 12 semanas que entrega uma pipeline de percepção pronta (parser + algoritmo + painel ou integração OPC UA). Escopo fechado, preço fechado, você é dono do código na entrega. O tamanho típico do projeto fica entre a faixa média de cinco dígitos e a faixa baixa de seis dígitos, dependendo do volume de dados, número de sensores e profundidade da integração. Long-term Partnership — um retainer mensal para desenvolvimento contínuo e suporte on-call. Dimensionado conforme a capacidade de equipe necessária (tipicamente 0,5 a 2 equivalentes de FTE). Road-mapping trimestral incluído. Todos os três tiers incluem código-fonte, documentação escrita e uma entrega limpa — sem dependência de licença nossa. Consulte o nosso serviço Industrial Perception AI para o modelo completo de colaboração.
How long does it take to build a custom perception pipeline?Wie lange dauert eine maßgeschneiderte Wahrnehmungs-Pipeline?How long does it take to build a custom perception pipeline?How long does it take to build a custom perception pipeline?How long does it take to build a custom perception pipeline?How long does it take to build a custom perception pipeline?Quanto tempo leva para construir uma pipeline de percepção sob medida?
From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors. Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks. Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks. Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop. For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model. Vom unterzeichneten Vertrag bis zum produktiven Tool rechnen Sie mit 4–12 Wochen für ein Standard-Custom-Pipeline-Projekt. Die Spanne wird von drei Faktoren bestimmt. Datenlage. Wenn Sie bereits gelabelte Daten oder repräsentative Aufnahmen haben, starten wir in Woche 1 mit dem Training. Müssen wir Datenerfassung aufsetzen, einen Sensor ergänzen oder von Null labeln, kommt vorne 1–3 Wochen dazu. Integrations-Tiefe. Ein eigenständiges Dashboard mit REST-Schnittstelle ist der schnellste Weg — typisch 4–6 Wochen. OPC-UA-Anbindung in eine laufende Leittechnik, mit Verriegelungen, Werks-Abnahme und kundenseitigem Change-Management, eher 8–12 Wochen. Sensor-Anzahl und Anlagen-Komplexität. Ein LiDAR + eine Kamera in einer sauberen Innen-Umgebung geht schneller als ein 6-Sensor-Portal im Freien mit Staub, Schnee und wechselndem Licht. Den Unterschied schneiden wir vorab im Discovery-Workshop sauber zu. Für ein schnelleres erstes Signal empfehlen wir das Discovery & Assessment-Tier — 1–3 Tage, Festpreis, schriftliche Machbarkeits-Note innerhalb einer Woche. Vollständiges Modell siehe Industrielle Objekterkennung. From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors. Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks. Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks. Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop. For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model. From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors. Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks. Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks. Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop. For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model. From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors. Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks. Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks. Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop. For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model. From signed contract to a working tool in production, expect 4–12 weeks for a standard custom-pipeline engagement. The spread is driven by three factors. Data readiness. If you already have labelled data or representative recordings, we start training in week 1. If we need to set up data collection, add a sensor, or label from scratch, the front end adds 1–3 weeks. Integration depth. A standalone dashboard with REST output is the fastest path — typically 4–6 weeks. OPC UA integration into a running control system, with interlocks, factory-acceptance tests and a customer change-management process, is closer to 8–12 weeks. Sensor count and site complexity. One LiDAR + one camera in a clean indoor environment is faster than a six-sensor outdoor portal with dust, snow and dynamic lighting. We scope the difference up-front in the Discovery workshop. For a faster first signal we recommend the Discovery & Assessment tier — 1–3 days, fixed price, written feasibility note within a week. See Industrial Perception AI for the full model. Do contrato assinado à ferramenta funcionando em produção, espere 4 a 12 semanas para um projeto padrão de pipeline sob medida. A variação é determinada por três fatores. Prontidão dos dados. Se você já tem dados rotulados ou gravações representativas, começamos o treinamento na semana 1. Se precisarmos configurar a coleta de dados, adicionar um sensor ou rotular do zero, o front end acrescenta de 1 a 3 semanas. Profundidade de integração. Um painel autônomo com saída REST é o caminho mais rápido — tipicamente de 4 a 6 semanas. Integração OPC UA em um sistema de controle em operação, com intertravamentos, testes de aceitação de fábrica e um processo de gestão de mudanças do cliente, fica mais próxima de 8 a 12 semanas. Número de sensores e complexidade do site. Um LiDAR + uma câmera em um ambiente interno limpo é mais rápido do que um pórtico externo com seis sensores em meio a poeira, neve e iluminação dinâmica. Nós dimensionamos essa diferença antecipadamente no workshop Discovery. Para um primeiro sinal mais rápido recomendamos o tier Discovery & Assessment — 1 a 3 dias, preço fechado, nota escrita de viabilidade em até uma semana. Consulte Industrial Perception AI para o modelo completo.
Who owns the code and IP we pay you to build?Wem gehören Code und IP, die wir bei Ihnen beauftragen?Who owns the code and IP we pay you to build?Who owns the code and IP we pay you to build?Who owns the code and IP we pay you to build?Who owns the code and IP we pay you to build?Quem é dono do código e da PI que pagamos para vocês construírem?
You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract. What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable. If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop. Full engagement details on our Industrial Perception AI page. Ihnen. Unser Standard-Vertrag überträgt das volle Eigentum am projektspezifischen Code, an den Modell-Gewichten, an Trainingsdaten (soweit die Daten Ihnen gehören) und an der Dokumentation bei der Abnahme an Sie. Wir behalten keine Hintertür-Lizenz und binden Sie nicht an einen Wartungsvertrag. Was bei uns bleibt, ist unser vorhandener Werkzeugkasten — wiederverwendbare Bibliotheken, Kalibrier-Utilities, generische Daten-Parser, der OWL EYE®-Kern — den wir Ihnen lizenzgebührenfrei für das gelieferte Tool lizenzieren. Das ist dieselbe Grenze, die jedes seriöse Ingenieurbüro zieht: Wir bringen den Werkzeugkasten, Sie behalten das Ergebnis. Wenn Sie eine andere IP-Vereinbarung wollen — etwa ein gemeinsames Patent auf einen neuartigen Algorithmus oder ein gemeinsam entwickeltes Modell, das wir beide mit Einwilligung wiederverwenden — regeln wir das explizit im Projektvertrag. Sagen Sie es vorab im Discovery-Workshop. Vollständige Details auf unserer Seite zur Industriellen Objekterkennung. You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract. What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable. If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop. Full engagement details on our Industrial Perception AI page. You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract. What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable. If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop. Full engagement details on our Industrial Perception AI page. You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract. What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable. If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop. Full engagement details on our Industrial Perception AI page. You do. Our standard contract transfers full ownership of the project-specific code, model weights, training data (where the data is yours) and documentation to you on final acceptance. We don't keep a back-door licence and we don't lock you into a maintenance contract. What we retain is our pre-existing toolbox — reusable libraries, calibration utilities, generic data parsers, the OWL EYE® core — which we license to you, royalty-free, for use on the delivered tool. This is the same boundary that any reputable engineering firm draws: we bring the toolbox, you keep the deliverable. If you want a different IP arrangement — for example a joint patent on a novel algorithm, or a co-developed model that we both reuse with consent — we structure that explicitly in the project contract. Tell us up-front in the Discovery workshop. Full engagement details on our Industrial Perception AI page. Você é. Nosso contrato padrão transfere a propriedade total do código específico do projeto, dos pesos do modelo, dos dados de treinamento (quando os dados são seus) e da documentação para você na aceitação final. Não mantemos uma licença "porta dos fundos" e não prendemos você em um contrato de manutenção. O que retemos é a nossa toolbox pré-existente — bibliotecas reutilizáveis, utilitários de calibração, parsers genéricos de dados, o núcleo do OWL EYE® — que licenciamos para você, isenta de royalties, para uso na ferramenta entregue. Esse é o mesmo limite que qualquer empresa de engenharia respeitável estabelece: nós trazemos a caixa de ferramentas, você fica com o entregável. Se você quiser um arranjo de PI diferente — por exemplo, uma patente conjunta sobre um algoritmo inovador ou um modelo co-desenvolvido que ambos reutilizamos com consentimento — estruturamos isso explicitamente no contrato do projeto. Nos avise antecipadamente no workshop Discovery. Detalhes completos do engajamento em nossa página Industrial Perception AI.
Can you use our existing cameras and LiDAR sensors?Können Sie unsere vorhandenen Kameras und LiDAR-Sensoren weiterverwenden?Can you use our existing cameras and LiDAR sensors?Can you use our existing cameras and LiDAR sensors?Can you use our existing cameras and LiDAR sensors?Can you use our existing cameras and LiDAR sensors?Vocês conseguem usar as nossas câmeras e sensores LiDAR existentes?
Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras. We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement: - The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new. - The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor. - The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement. We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it. In den meisten Fällen ja. Unsere Toolchain ist auf der Datenebene sensor-agnostisch. Wenn Ihre Sensoren ein Standard-Format liefern (PCD, LAS, E57 für Punktwolken; RTSP, GigE Vision, USB3 Vision für Kameras), binden wir sie an einem Tag an. Wir haben mit Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision und IDS gearbeitet. Wir sagen Ihnen ehrlich, wenn die vorhandene Hardware nicht das richtige Werkzeug ist. Übliche Fälle, in denen wir zum Tausch raten: - Der vorhandene LiDAR ist zu schmal (FoV oder Reichweite), um den gewünschten Bereich abzudecken — meist durch Repositionierung gelöst, bevor neu gekauft wird. - Die Kamera auto-belichtet auf einer Szene mit hohem Kontrast (Sonne + Schatten am Tor), das bricht die Klassifikations-Zuverlässigkeit — gelöst durch Wechsel auf eine manuell belichtbare Industrie-Kamera mit HDR-Sensor. - Vendor-Lock-in des vorhandenen Sensors (proprietärer Stream, kein dokumentiertes SDK) macht die Anbindung teurer als ein Livox-Ersatz. Wir verdienen nicht am Weiterverkauf von Hardware an Sie. Wenn Sie wollen, dass wir neue Sensoren beschaffen, läuft das über unseren regulären Kanal Handelsware & Produkte zum Listenpreis. Scoping-Modell siehe Industrielle Objekterkennung. Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras. We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement: - The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new. - The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor. - The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement. We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it. Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras. We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement: - The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new. - The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor. - The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement. We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it. Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras. We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement: - The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new. - The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor. - The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement. We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it. Yes — in most cases. Our toolchain is sensor-agnostic on the data layer. If your sensors deliver a standard format (PCD, LAS, E57 for point clouds; RTSP, GigE Vision, USB3 Vision for cameras) we can ingest them in a day. We've worked with Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision and IDS cameras. We'll tell you honestly when the existing hardware isn't the right tool. Common cases where we recommend a replacement: - The existing LiDAR is too narrow (FoV or range) to cover the area you want classified — usually solved by repositioning before buying anything new. - The camera is auto-exposing on a high-contrast scene (sun + shadow at a gate), which breaks classification reliability — solved by switching to a manual-exposure industrial camera with HDR sensor. - The existing sensor's vendor lock-in (proprietary stream format, no documented SDK) makes integration cost more than a Livox replacement. We don't earn a margin on reselling hardware to you. If you do want us to source new sensors, we do that through our normal Hardware & products channel at list price. See Industrial Perception AI for how we scope it. Sim — na maioria dos casos. Nossa toolchain é agnóstica a sensor na camada de dados. Se os seus sensores entregam um formato padrão (PCD, LAS, E57 para nuvens de pontos; RTSP, GigE Vision, USB3 Vision para câmeras), conseguimos ingeri-los em um dia. Já trabalhamos com câmeras Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision e IDS. Vamos dizer honestamente quando o hardware existente não for a ferramenta certa. Casos comuns em que recomendamos substituição: - O LiDAR existente é muito estreito (FoV ou alcance) para cobrir a área que você quer classificar — geralmente resolvido reposicionando antes de comprar qualquer coisa nova. - A câmera está fazendo auto-exposição em uma cena de alto contraste (sol + sombra em um portão), o que quebra a confiabilidade da classificação — resolvido trocando para uma câmera industrial de exposição manual com sensor HDR. - O bloqueio de fornecedor do sensor existente (formato de stream proprietário, sem SDK documentado) faz com que a integração custe mais do que uma substituição por Livox. Não ganhamos margem revendendo hardware para você. Se você quiser que a gente forneça sensores novos, fazemos isso através do nosso canal normal de Hardware & products a preço de tabela. Consulte Industrial Perception AI para saber como dimensionamos.

Send us a zone map and a sample scan.Schicken Sie uns einen Zonen-Plan und einen Beispiel-Scan.Send us a zone map and a sample scan.Send us a zone map and a sample scan.Send us a zone map and a sample scan.Send us a zone map and a sample scan.Envie um mapa de zonas e uma varredura de amostra.

A zone layout, a few sample point clouds, a description of your existing safety PLC and lockout-tagout procedure — we come back within two business days with a written feasibility note and a fixed-price scope for the discovery workshop. Part of our Industrial Perception AI service.Ein Zonen-Layout, ein paar Beispiel-Punktwolken, eine Beschreibung Ihrer bestehenden Sicherheits-SPS und Ihres Lockout-Tagout-Verfahrens — wir kommen innerhalb von zwei Werktagen mit einer schriftlichen Machbarkeits-Note und einem Festpreis-Angebot für den Discovery-Workshop zurück. Teil unseres Services Industrielle Objekterkennung.A zone layout, a few sample point clouds, a description of your existing safety PLC and lockout-tagout procedure — we come back within two business days with a written feasibility note and a fixed-price scope for the discovery workshop. Part of our Industrial Perception AI service.A zone layout, a few sample point clouds, a description of your existing safety PLC and lockout-tagout procedure — we come back within two business days with a written feasibility note and a fixed-price scope for the discovery workshop. Part of our Industrial Perception AI service.A zone layout, a few sample point clouds, a description of your existing safety PLC and lockout-tagout procedure — we come back within two business days with a written feasibility note and a fixed-price scope for the discovery workshop. Part of our Industrial Perception AI service.A zone layout, a few sample point clouds, a description of your existing safety PLC and lockout-tagout procedure — we come back within two business days with a written feasibility note and a fixed-price scope for the discovery workshop. Part of our Industrial Perception AI service.Um layout de zonas, algumas nuvens de pontos de amostra, uma descrição do seu PLC de segurança existente e do procedimento de bloqueio-etiquetagem — respondemos em dois dias úteis com uma nota escrita de viabilidade e um escopo de preço fechado para o workshop de descoberta. Parte do nosso serviço Industrial Perception AI.

info@sachtleben-technology.com +49 7831 969 22-190
Send us a messageNachricht sendenSend us a messageSend us a messageSend us a messageSend us a messageEnvie-nos uma mensagem

Tell us about your hazard zone. Erzählen Sie uns von Ihrer Gefahrenzone. Tell us about your hazard zone. Tell us about your hazard zone. Tell us about your hazard zone. Tell us about your hazard zone. Conte-nos sobre sua zona de risco.

Zone classification, sensor setup, your safety PLC interface, your existing lockout-tagout procedure — anything you have. We come back within two business days with an honest first assessment and a fixed-price scope for the Discovery workshop. Zonen-Einstufung, Sensor-Setup, Ihre Sicherheits-SPS-Schnittstelle, Ihr bestehendes Lockout-Tagout-Verfahren — alles, was Sie haben. Wir kommen innerhalb von zwei Werktagen mit einer ehrlichen ersten Einschätzung und einem Festpreis-Angebot für den Discovery-Workshop zurück. Zone classification, sensor setup, your safety PLC interface, your existing lockout-tagout procedure — anything you have. We come back within two business days with an honest first assessment and a fixed-price scope for the Discovery workshop. Zone classification, sensor setup, your safety PLC interface, your existing lockout-tagout procedure — anything you have. We come back within two business days with an honest first assessment and a fixed-price scope for the Discovery workshop. Zone classification, sensor setup, your safety PLC interface, your existing lockout-tagout procedure — anything you have. We come back within two business days with an honest first assessment and a fixed-price scope for the Discovery workshop. Zone classification, sensor setup, your safety PLC interface, your existing lockout-tagout procedure — anything you have. We come back within two business days with an honest first assessment and a fixed-price scope for the Discovery workshop. Classificação da zona, setup dos sensores, interface do seu PLC de segurança, seu procedimento existente de bloqueio-etiquetagem — qualquer coisa que você tenha. Voltamos em dois dias úteis com uma primeira avaliação honesta e um escopo de preço fechado para o workshop de Descoberta.

Direct line Direktwahl Telefon bezpośredni Linea diretta Ligne directe Línea directa Linha direta
Mon — Fri · 08:00 – 17:00 CET Mo — Fr · 08:00 – 17:00 Uhr Pn — Pt · 08:00 – 17:00 CET Lun — Ven · 08:00 – 17:00 CET Lun — Ven · 08:00 – 17:00 CET Lun — Vie · 08:00 – 17:00 CET Seg — Sex · 08:00 – 17:00 CET
Email E-Mail E-mail Email E-mail Correo electrónico E-mail
Response within one business day. Antwort innerhalb eines Werktages. OdpowiedŁº w ciągu jednego dnia roboczego. Risposta entro un giorno lavorativo. Réponse sous un jour ouvré. Respuesta en un día laborable. Resposta em um dia útil.
Headquarters Unternehmenssitz Siedziba główna Sede principale Siège social Sede central Sede
Sachtleben Technology GmbH
Tresdorf 6
24238 Mucheln
Germany Deutschland Niemcy Germania Allemagne Alemania Alemanha
Última atualização: