IA de Percepção Industrial — Software LiDAR e Visão

SERVICESERVICESERVICESERVICESERVICESERVICESERVIÇO · Industrial perception AI · LiDAR + computer visionIndustrielle Objekterkennung · LiDAR + BildverarbeitungIndustrial perception AI · LiDAR + computer visionIndustrial perception AI · LiDAR + computer visionIndustrial perception AI · LiDAR + computer visionIndustrial perception AI · LiDAR + computer visionIA de percepção industrial · LiDAR + visão computacional

Custom perception software, built by people who run it in production. Wahrnehmungs-Software nach Maß, gebaut von Leuten, die sie selbst produktiv betreiben. Custom perception software, built by people who run it in production. Custom perception software, built by people who run it in production. Custom perception software, built by people who run it in production. Custom perception software, built by people who run it in production. Software de percepção sob medida, feito por quem opera na produção.

Industrial perception AI is software that turns raw 3D point clouds and 2D camera images into machine-readable decisions on a plant floor. We design, build and ship those pipelines for industrial customers — scrap-vs-slag classification, crane and vehicle detection, worker safety in ATEX zones, material-flow optimisation.Industrielle Objekterkennung ist Software, die rohe 3D-Punktwolken und 2D-Kamerabilder in maschinenlesbare Entscheidungen auf der Werksebene umwandelt. Wir entwerfen, bauen und liefern diese Pipelines für industrielle Kunden — Schrott-/Schlacke-Klassifikation, Kran- und Fahrzeugerkennung, Personenschutz in ATEX-Zonen, Materialfluss-Optimierung.Industrial perception AI is software that turns raw 3D point clouds and 2D camera images into machine-readable decisions on a plant floor. We design, build and ship those pipelines for industrial customers — scrap-vs-slag classification, crane and vehicle detection, worker safety in ATEX zones, material-flow optimisation.Industrial perception AI is software that turns raw 3D point clouds and 2D camera images into machine-readable decisions on a plant floor. We design, build and ship those pipelines for industrial customers — scrap-vs-slag classification, crane and vehicle detection, worker safety in ATEX zones, material-flow optimisation.Industrial perception AI is software that turns raw 3D point clouds and 2D camera images into machine-readable decisions on a plant floor. We design, build and ship those pipelines for industrial customers — scrap-vs-slag classification, crane and vehicle detection, worker safety in ATEX zones, material-flow optimisation.Industrial perception AI is software that turns raw 3D point clouds and 2D camera images into machine-readable decisions on a plant floor. We design, build and ship those pipelines for industrial customers — scrap-vs-slag classification, crane and vehicle detection, worker safety in ATEX zones, material-flow optimisation.A IA de percepção industrial é o software que transforma nuvens 3D brutas de pontos e imagens 2D de câmeras em decisões legíveis por máquina no chão de fábrica. Projetamos, construímos e entregamos esses pipelines para clientes industriais — classificação de sucata versus escória, detecção de guindastes e veículos, segurança de trabalhadores em zonas ATEX, otimização de fluxo de material.

We started with one job: measuring stockpiles with LiDAR inside an active mining operation. Five years and forty live installations later, we have a deep toolbox for industrial point-cloud and computer-vision work — Riegl, Livox and Faro on the hardware side; PCL, Open3D, OpenCV and PyTorch on the software side; OPC UA, REST and MQTT into your control system. We bring that toolbox to your data.Angefangen haben wir mit einer einzigen Aufgabe: Halden mit LiDAR im aktiven Bergbaubetrieb zu vermessen. Fünf Jahre und vierzig produktive Installationen später haben wir einen tiefen Werkzeugkasten für industrielle Punktwolken- und Bildverarbeitungs-Arbeit — Riegl, Livox und Faro auf der Hardware-Seite; PCL, Open3D, OpenCV und PyTorch auf der Software-Seite; OPC UA, REST und MQTT in Ihre Leittechnik. Diesen Werkzeugkasten bringen wir an Ihre Daten.We started with one job: measuring stockpiles with LiDAR inside an active mining operation. Five years and forty live installations later, we have a deep toolbox for industrial point-cloud and computer-vision work — Riegl, Livox and Faro on the hardware side; PCL, Open3D, OpenCV and PyTorch on the software side; OPC UA, REST and MQTT into your control system. We bring that toolbox to your data.We started with one job: measuring stockpiles with LiDAR inside an active mining operation. Five years and forty live installations later, we have a deep toolbox for industrial point-cloud and computer-vision work — Riegl, Livox and Faro on the hardware side; PCL, Open3D, OpenCV and PyTorch on the software side; OPC UA, REST and MQTT into your control system. We bring that toolbox to your data.We started with one job: measuring stockpiles with LiDAR inside an active mining operation. Five years and forty live installations later, we have a deep toolbox for industrial point-cloud and computer-vision work — Riegl, Livox and Faro on the hardware side; PCL, Open3D, OpenCV and PyTorch on the software side; OPC UA, REST and MQTT into your control system. We bring that toolbox to your data.We started with one job: measuring stockpiles with LiDAR inside an active mining operation. Five years and forty live installations later, we have a deep toolbox for industrial point-cloud and computer-vision work — Riegl, Livox and Faro on the hardware side; PCL, Open3D, OpenCV and PyTorch on the software side; OPC UA, REST and MQTT into your control system. We bring that toolbox to your data.Começamos com uma missão: medir pilhas com LiDAR dentro de uma operação de mineração ativa. Cinco anos e quarenta instalações ativas depois, temos uma caixa de ferramentas profunda para trabalho industrial com nuvem de pontos e visão computacional — Riegl, Livox e Faro no lado do hardware; PCL, Open3D, OpenCV e PyTorch no lado do software; OPC UA, REST e MQTT para o seu sistema de controle. Trazemos essa caixa de ferramentas para os seus dados.

We don't sell a generic AI platform. Every engagement starts with a short data audit: what sensors do you have, what does your data look like, what decision are you trying to automate? From there we propose a fixed-scope pipeline — typically 4–12 weeks from contract to live tool. For larger programmes we move into a monthly retainer model with shared road-mapping. Either way you own the code: see our FAQs on IP and hardware reuse for the standard terms.Wir verkaufen keine generische KI-Plattform. Jedes Projekt startet mit einem kurzen Daten-Audit: Welche Sensoren haben Sie, wie sieht Ihre Datenlage aus, welche Entscheidung wollen Sie automatisieren? Daraus entsteht ein fester Projektrahmen — typisch 4–12 Wochen vom Vertrag bis zum produktiven Tool. Für größere Programme wechseln wir in ein monatliches Retainer-Modell mit gemeinsamer Roadmap. In jedem Fall gehört der Code Ihnen: Details zur IP und zur Wiederverwendung Ihrer Hardware stehen in unseren FAQs.We don't sell a generic AI platform. Every engagement starts with a short data audit: what sensors do you have, what does your data look like, what decision are you trying to automate? From there we propose a fixed-scope pipeline — typically 4–12 weeks from contract to live tool. For larger programmes we move into a monthly retainer model with shared road-mapping. Either way you own the code: see our FAQs on IP and hardware reuse for the standard terms.We don't sell a generic AI platform. Every engagement starts with a short data audit: what sensors do you have, what does your data look like, what decision are you trying to automate? From there we propose a fixed-scope pipeline — typically 4–12 weeks from contract to live tool. For larger programmes we move into a monthly retainer model with shared road-mapping. Either way you own the code: see our FAQs on IP and hardware reuse for the standard terms.We don't sell a generic AI platform. Every engagement starts with a short data audit: what sensors do you have, what does your data look like, what decision are you trying to automate? From there we propose a fixed-scope pipeline — typically 4–12 weeks from contract to live tool. For larger programmes we move into a monthly retainer model with shared road-mapping. Either way you own the code: see our FAQs on IP and hardware reuse for the standard terms.We don't sell a generic AI platform. Every engagement starts with a short data audit: what sensors do you have, what does your data look like, what decision are you trying to automate? From there we propose a fixed-scope pipeline — typically 4–12 weeks from contract to live tool. For larger programmes we move into a monthly retainer model with shared road-mapping. Either way you own the code: see our FAQs on IP and hardware reuse for the standard terms.Não vendemos uma plataforma genérica de IA. Cada engajamento começa com uma breve auditoria de dados: quais sensores você tem, como são os seus dados, que decisão você está tentando automatizar? A partir daí, propomos um pipeline de escopo fixo — normalmente de 4 a 12 semanas do contrato à ferramenta em produção. Para programas maiores, passamos a um modelo de retentor mensal com roadmap compartilhado. Em qualquer caso, você é dono do código: veja nossas FAQs sobre propriedade intelectual e reutilização de hardware para os termos padrão.

„If we can run it on our own mining site, we can run it on yours." „Wenn wir es auf unserem eigenen Bergbau-Standort fahren können, fährt es auch bei Ihnen." „If we can run it on our own mining site, we can run it on yours." „If we can run it on our own mining site, we can run it on yours." „If we can run it on our own mining site, we can run it on yours." „If we can run it on our own mining site, we can run it on yours." "Se conseguimos rodar na nossa própria mina, conseguimos rodar na sua."

Production references across salt, sugar, copper, charcoal and minerals. Produktive Referenzen in Salz, Zucker, Kupfer, Holzkohle und Mineralien. Production references across salt, sugar, copper, charcoal and minerals. Production references across salt, sugar, copper, charcoal and minerals. Production references across salt, sugar, copper, charcoal and minerals. Production references across salt, sugar, copper, charcoal and minerals. Referências em produção em sal, açúcar, cobre, carvão vegetal e minerais.

Three problem clustersDrei ProblemfelderThree problem clustersThree problem clustersThree problem clustersThree problem clustersTrês grupos de problemas

What we build — in three clusters. Was wir bauen — in drei Feldern. What we build — in three clusters. What we build — in three clusters. What we build — in three clusters. What we build — in three clusters. O que construímos — em três grupos.

Material classificationMaterialklassifikationMaterial classificationMaterial classificationMaterial classificationMaterial classificationClassificação de materiais

Scrap-vs-slag classification on steel-mill yards, ore-grade detection on conveyors, mixed-material search and segmentation on stockpiles. Point-cloud classifiers and 2D vision models trained on your material — not a public benchmark. Schrott-/Schlacke-Klassifikation auf Stahlwerks-Höfen, Erz-Qualitäts-Erkennung auf Förderbändern, Mischmaterial-Suche und -Segmentierung auf Halden. Punktwolken-Klassifikatoren und 2D-Bildmodelle, trainiert auf Ihrem Material — nicht auf einem öffentlichen Benchmark. Scrap-vs-slag classification on steel-mill yards, ore-grade detection on conveyors, mixed-material search and segmentation on stockpiles. Point-cloud classifiers and 2D vision models trained on your material — not a public benchmark. Scrap-vs-slag classification on steel-mill yards, ore-grade detection on conveyors, mixed-material search and segmentation on stockpiles. Point-cloud classifiers and 2D vision models trained on your material — not a public benchmark. Scrap-vs-slag classification on steel-mill yards, ore-grade detection on conveyors, mixed-material search and segmentation on stockpiles. Point-cloud classifiers and 2D vision models trained on your material — not a public benchmark. Scrap-vs-slag classification on steel-mill yards, ore-grade detection on conveyors, mixed-material search and segmentation on stockpiles. Point-cloud classifiers and 2D vision models trained on your material — not a public benchmark. Classificação de sucata versus escória em pátios de siderúrgicas, detecção de teor de minério em correias, busca e segmentação de material misto em pilhas. Classificadores de nuvem de pontos e modelos de visão 2D treinados com o seu material — não com um benchmark público.

Asset trackingAnlagen- & Fahrzeug-TrackingAsset trackingAsset trackingAsset trackingAsset trackingRastreamento de ativos

Crane position + anti-collision in waste bunkers and warehouses, vehicle detection at plant gates and weighbridges, railcar and wagon recognition for loading automation. LiDAR-based, lighting-independent, works in dust. Kran-Position und Anti-Kollision in Müllbunkern und Hallen, Fahrzeugerkennung an Werkstoren und Waagen, Waggon- und Wagen-Identifikation für die Verladeautomatisierung. LiDAR-basiert, lichtunabhängig, staubtauglich. Crane position + anti-collision in waste bunkers and warehouses, vehicle detection at plant gates and weighbridges, railcar and wagon recognition for loading automation. LiDAR-based, lighting-independent, works in dust. Crane position + anti-collision in waste bunkers and warehouses, vehicle detection at plant gates and weighbridges, railcar and wagon recognition for loading automation. LiDAR-based, lighting-independent, works in dust. Crane position + anti-collision in waste bunkers and warehouses, vehicle detection at plant gates and weighbridges, railcar and wagon recognition for loading automation. LiDAR-based, lighting-independent, works in dust. Crane position + anti-collision in waste bunkers and warehouses, vehicle detection at plant gates and weighbridges, railcar and wagon recognition for loading automation. LiDAR-based, lighting-independent, works in dust. Posição de guindastes + anticolisão em bunkers de resíduos e armazéns, detecção de veículos em portarias e balanças, reconhecimento de vagões ferroviários para automação de carregamento. Baseado em LiDAR, independente da iluminação, funciona na poeira.

Safety & complianceSicherheit & ComplianceSafety & complianceSafety & complianceSafety & complianceSafety & complianceSegurança e conformidade

Worker detection inside ATEX zones and around moving plant equipment, safety-distance monitoring on automated cranes and AGVs, hazard-zone clearance checks before a process restart. Auditable event logs included. Personenerkennung in ATEX-Zonen und im Schwenkbereich beweglicher Anlagenteile, Sicherheitsabstand-Überwachung auf automatisierten Kranen und FTS, Räumungskontrolle vor dem Wieder-Anfahren. Auditfähiger Ereignis-Log inklusive. Worker detection inside ATEX zones and around moving plant equipment, safety-distance monitoring on automated cranes and AGVs, hazard-zone clearance checks before a process restart. Auditable event logs included. Worker detection inside ATEX zones and around moving plant equipment, safety-distance monitoring on automated cranes and AGVs, hazard-zone clearance checks before a process restart. Auditable event logs included. Worker detection inside ATEX zones and around moving plant equipment, safety-distance monitoring on automated cranes and AGVs, hazard-zone clearance checks before a process restart. Auditable event logs included. Worker detection inside ATEX zones and around moving plant equipment, safety-distance monitoring on automated cranes and AGVs, hazard-zone clearance checks before a process restart. Auditable event logs included. Detecção de trabalhadores dentro de zonas ATEX e ao redor de equipamentos móveis, monitoramento de distância de segurança em guindastes automatizados e AGVs, verificações de liberação de zonas de perigo antes do religamento de um processo. Logs de eventos auditáveis incluídos.

Engagement modelZusammenarbeits-ModellEngagement modelEngagement modelEngagement modelEngagement modelModelo de engajamento

Three ways to work with us. Drei Wege, mit uns zu arbeiten. Three ways to work with us. Three ways to work with us. Three ways to work with us. Three ways to work with us. Três formas de trabalhar conosco.

No long sales cycles. We scope every engagement around your data — start with a workshop, move to a fixed-scope project, optionally into a long-term retainer. Keine langen Vertriebszyklen. Wir schneiden jedes Projekt um Ihre Daten — Start mit einem Workshop, dann ein Fest-Scope-Projekt, optional ein langfristiger Retainer. No long sales cycles. We scope every engagement around your data — start with a workshop, move to a fixed-scope project, optionally into a long-term retainer. No long sales cycles. We scope every engagement around your data — start with a workshop, move to a fixed-scope project, optionally into a long-term retainer. No long sales cycles. We scope every engagement around your data — start with a workshop, move to a fixed-scope project, optionally into a long-term retainer. No long sales cycles. We scope every engagement around your data — start with a workshop, move to a fixed-scope project, optionally into a long-term retainer. Sem ciclos longos de venda. Definimos o escopo de cada engajamento em torno dos seus dados — começamos com um workshop, passamos a um projeto de escopo fixo, opcionalmente até um retentor de longo prazo.

Discovery & AssessmentDiscovery & AssessmentDiscovery & AssessmentDiscovery & AssessmentDiscovery & AssessmentDiscovery & AssessmentDiscovery e diagnóstico

A 1–3 day on-site or remote workshop. We audit your sensors, your data pipeline and the decision you want to automate, and ship a written feasibility note with a recommended next step. Starting at a few days. Fixed price. Ein 1–3-tägiger Workshop, vor Ort oder remote. Wir auditieren Ihre Sensoren, Ihre Datenpipeline und die zu automatisierende Entscheidung, und liefern eine schriftliche Machbarkeits-Note mit empfohlenem nächsten Schritt. Ab wenigen Tagen. Festpreis. A 1–3 day on-site or remote workshop. We audit your sensors, your data pipeline and the decision you want to automate, and ship a written feasibility note with a recommended next step. Starting at a few days. Fixed price. A 1–3 day on-site or remote workshop. We audit your sensors, your data pipeline and the decision you want to automate, and ship a written feasibility note with a recommended next step. Starting at a few days. Fixed price. A 1–3 day on-site or remote workshop. We audit your sensors, your data pipeline and the decision you want to automate, and ship a written feasibility note with a recommended next step. Starting at a few days. Fixed price. A 1–3 day on-site or remote workshop. We audit your sensors, your data pipeline and the decision you want to automate, and ship a written feasibility note with a recommended next step. Starting at a few days. Fixed price. Um workshop de 1 a 3 dias, presencial ou remoto. Auditamos seus sensores, seu pipeline de dados e a decisão que você quer automatizar, e entregamos uma nota de viabilidade por escrito com um próximo passo recomendado. A partir de alguns dias. Preço fixo.

Custom Pipeline / ToolCustom Pipeline / ToolCustom Pipeline / ToolCustom Pipeline / ToolCustom Pipeline / ToolCustom Pipeline / ToolPipeline / ferramenta sob medida

A 4–12 week project that delivers a working perception pipeline — data parser, detection/classification algorithm, dashboard or OPC UA integration into your control room. Fixed scope, fixed price, you own the code at handover. Ein 4–12-Wochen-Projekt, das eine fertige Wahrnehmungs-Pipeline liefert — Daten-Parser, Erkennungs-/Klassifikations-Algorithmus, Dashboard oder OPC-UA-Anbindung an Ihre Leittechnik. Fester Scope, Festpreis, Code-Übergabe am Ende. A 4–12 week project that delivers a working perception pipeline — data parser, detection/classification algorithm, dashboard or OPC UA integration into your control room. Fixed scope, fixed price, you own the code at handover. A 4–12 week project that delivers a working perception pipeline — data parser, detection/classification algorithm, dashboard or OPC UA integration into your control room. Fixed scope, fixed price, you own the code at handover. A 4–12 week project that delivers a working perception pipeline — data parser, detection/classification algorithm, dashboard or OPC UA integration into your control room. Fixed scope, fixed price, you own the code at handover. A 4–12 week project that delivers a working perception pipeline — data parser, detection/classification algorithm, dashboard or OPC UA integration into your control room. Fixed scope, fixed price, you own the code at handover. Um projeto de 4 a 12 semanas que entrega um pipeline de percepção em funcionamento — parser de dados, algoritmo de detecção/classificação, painel ou integração OPC UA para a sua sala de controle. Escopo fixo, preço fixo, você é dono do código na entrega.

Long-term PartnershipLangfristige PartnerschaftLong-term PartnershipLong-term PartnershipLong-term PartnershipLong-term PartnershipParceria de longo prazo

A monthly retainer for ongoing model retraining, sensor migrations, new use cases and on-call support. The right fit when you want a perception engineering team without hiring one. Quarterly road-mapping. Monatlicher Retainer für laufendes Re-Training, Sensor-Migrationen, neue Anwendungsfälle und On-Call-Support. Passt, wenn Sie ein Perception-Engineering-Team haben wollen, ohne eines einzustellen. Quartalsweise Roadmap. A monthly retainer for ongoing model retraining, sensor migrations, new use cases and on-call support. The right fit when you want a perception engineering team without hiring one. Quarterly road-mapping. A monthly retainer for ongoing model retraining, sensor migrations, new use cases and on-call support. The right fit when you want a perception engineering team without hiring one. Quarterly road-mapping. A monthly retainer for ongoing model retraining, sensor migrations, new use cases and on-call support. The right fit when you want a perception engineering team without hiring one. Quarterly road-mapping. A monthly retainer for ongoing model retraining, sensor migrations, new use cases and on-call support. The right fit when you want a perception engineering team without hiring one. Quarterly road-mapping. Um retentor mensal para retreinamento contínuo de modelos, migrações de sensores, novos casos de uso e suporte sob demanda. O encaixe certo quando você quer uma equipe de engenharia de percepção sem precisar contratá-la. Roadmap trimestral.

All three tiers include source code, documentation and a written handover — no black boxes, no licence dependence on us. Alle drei Tiers enthalten Quellcode, Dokumentation und schriftliche Übergabe — keine Black Box, keine Lizenz-Abhängigkeit von uns. All three tiers include source code, documentation and a written handover — no black boxes, no licence dependence on us. All three tiers include source code, documentation and a written handover — no black boxes, no licence dependence on us. All three tiers include source code, documentation and a written handover — no black boxes, no licence dependence on us. All three tiers include source code, documentation and a written handover — no black boxes, no licence dependence on us. Os três níveis incluem código-fonte, documentação e uma passagem formal por escrito — sem caixas-pretas, sem dependência de licença conosco.

Use cases · #use-casesAnwendungsfälle · #use-casesUse cases · #use-casesUse cases · #use-casesUse cases · #use-casesUse cases · #use-casesCasos de uso · #use-cases

Six places where perception AI earns its keep. Sechs Stellen, an denen Objekterkennung sich rechnet. Six places where perception AI earns its keep. Six places where perception AI earns its keep. Six places where perception AI earns its keep. Six places where perception AI earns its keep. Seis lugares onde a IA de percepção paga o próprio salário.

Scrap-vs-slag classificationSchrott-/Schlacke-KlassifikationScrap-vs-slag classificationScrap-vs-slag classificationScrap-vs-slag classificationScrap-vs-slag classificationClassificação de sucata versus escória

Distinguish ferrous scrap from cooled slag on a steel-mill yard, in real time, from a portal-mounted LiDAR + camera pair. Feeds the EAF charging schedule and reduces sorting labour on the yard. Read the deep dive → Eisenschrott in Echtzeit von erkalteter Schlacke trennen — auf dem Stahlwerks-Hof, über ein Portal mit LiDAR und Kamera. Speist die EAF-Chargenplanung und reduziert Sortier-Aufwand auf dem Hof. Zum Use-Case-Deep-Dive → Distinguish ferrous scrap from cooled slag on a steel-mill yard, in real time, from a portal-mounted LiDAR + camera pair. Feeds the EAF charging schedule and reduces sorting labour on the yard. Read the deep dive → Distinguish ferrous scrap from cooled slag on a steel-mill yard, in real time, from a portal-mounted LiDAR + camera pair. Feeds the EAF charging schedule and reduces sorting labour on the yard. Read the deep dive → Distinguish ferrous scrap from cooled slag on a steel-mill yard, in real time, from a portal-mounted LiDAR + camera pair. Feeds the EAF charging schedule and reduces sorting labour on the yard. Read the deep dive → Distinguish ferrous scrap from cooled slag on a steel-mill yard, in real time, from a portal-mounted LiDAR + camera pair. Feeds the EAF charging schedule and reduces sorting labour on the yard. Read the deep dive → Distinga sucata ferrosa de escória resfriada em um pátio de siderúrgica, em tempo real, a partir de um par LiDAR + câmera montado em pórtico. Alimenta o cronograma de carregamento do EAF e reduz a mão de obra de triagem no pátio. Leia o aprofundamento →

Material flow optimisationMaterialfluss-OptimierungMaterial flow optimisationMaterial flow optimisationMaterial flow optimisationMaterial flow optimisationOtimização de fluxo de material

Continuous classification of bulk material on conveyors and at transfer points — feeds blending models, prevents off-spec batches and gives the control room a real material-balance instead of an inferred one. Read the deep dive → Kontinuierliche Klassifikation von Schüttgut auf Förderbändern und Übergaben — speist Mischmodelle, vermeidet Off-Spec-Chargen und gibt der Leitwarte eine echte Materialbilanz statt einer abgeleiteten. Zum Use-Case-Deep-Dive → Continuous classification of bulk material on conveyors and at transfer points — feeds blending models, prevents off-spec batches and gives the control room a real material-balance instead of an inferred one. Read the deep dive → Continuous classification of bulk material on conveyors and at transfer points — feeds blending models, prevents off-spec batches and gives the control room a real material-balance instead of an inferred one. Read the deep dive → Continuous classification of bulk material on conveyors and at transfer points — feeds blending models, prevents off-spec batches and gives the control room a real material-balance instead of an inferred one. Read the deep dive → Continuous classification of bulk material on conveyors and at transfer points — feeds blending models, prevents off-spec batches and gives the control room a real material-balance instead of an inferred one. Read the deep dive → Classificação contínua de material a granel em correias transportadoras e pontos de transferência — alimenta modelos de blendagem, previne lotes fora da especificação e dá à sala de controle um balanço de material real em vez de um inferido. Leia o aprofundamento →

Crane detection & anti-collisionKranerkennung & Anti-KollisionCrane detection & anti-collisionCrane detection & anti-collisionCrane detection & anti-collisionCrane detection & anti-collisionDetecção de guindastes e anticolisão

LiDAR tracks crane bridge, trolley and hook position in a waste bunker or warehouse. Drives anti-collision interlocks, optimises grab routing, integrates with the crane PLC over OPC UA. See OWL EYE® Waste Bunker for a productised version. Read the deep dive → LiDAR verfolgt Brücke, Katze und Greifer im Müllbunker oder in der Halle. Treibt Anti-Kollisions-Verriegelungen, optimiert Greif-Routen, koppelt über OPC UA an die Kran-SPS. Produkt-Version siehe OWL EYE® Müllbunker-Monitoring. Zum Use-Case-Deep-Dive → LiDAR tracks crane bridge, trolley and hook position in a waste bunker or warehouse. Drives anti-collision interlocks, optimises grab routing, integrates with the crane PLC over OPC UA. See OWL EYE® Waste Bunker for a productised version. Read the deep dive → LiDAR tracks crane bridge, trolley and hook position in a waste bunker or warehouse. Drives anti-collision interlocks, optimises grab routing, integrates with the crane PLC over OPC UA. See OWL EYE® Waste Bunker for a productised version. Read the deep dive → LiDAR tracks crane bridge, trolley and hook position in a waste bunker or warehouse. Drives anti-collision interlocks, optimises grab routing, integrates with the crane PLC over OPC UA. See OWL EYE® Waste Bunker for a productised version. Read the deep dive → LiDAR tracks crane bridge, trolley and hook position in a waste bunker or warehouse. Drives anti-collision interlocks, optimises grab routing, integrates with the crane PLC over OPC UA. See OWL EYE® Waste Bunker for a productised version. Read the deep dive → LiDAR rastreia a ponte, o trole e o gancho do guindaste em um bunker de resíduos ou armazém. Aciona intertravamentos anticolisão, otimiza o roteamento da garra, integra-se ao CLP do guindaste via OPC UA. Veja OWL EYE® Waste Bunker para uma versão produtizada. Leia o aprofundamento →

Vehicle detectionFahrzeugerkennungVehicle detectionVehicle detectionVehicle detectionVehicle detectionDetecção de veículos

Truck, loader and forklift recognition at plant gates, in-plant intersections and weighbridges. Drives gate control, traffic-light interlocks and in-plant routing — works at night, in fog and in dust. Read the deep dive → LKW-, Lader- und Stapler-Erkennung an Werkstoren, innerbetrieblichen Kreuzungen und Waagen. Treibt Tor-Steuerung, Ampel-Verriegelungen und innerbetriebliche Wegeführung — funktioniert nachts, im Nebel und im Staub. Zum Use-Case-Deep-Dive → Truck, loader and forklift recognition at plant gates, in-plant intersections and weighbridges. Drives gate control, traffic-light interlocks and in-plant routing — works at night, in fog and in dust. Read the deep dive → Truck, loader and forklift recognition at plant gates, in-plant intersections and weighbridges. Drives gate control, traffic-light interlocks and in-plant routing — works at night, in fog and in dust. Read the deep dive → Truck, loader and forklift recognition at plant gates, in-plant intersections and weighbridges. Drives gate control, traffic-light interlocks and in-plant routing — works at night, in fog and in dust. Read the deep dive → Truck, loader and forklift recognition at plant gates, in-plant intersections and weighbridges. Drives gate control, traffic-light interlocks and in-plant routing — works at night, in fog and in dust. Read the deep dive → Reconhecimento de caminhões, carregadeiras e empilhadeiras em portarias, cruzamentos internos e balanças. Aciona controle de portaria, intertravamentos de semáforos e roteamento interno — funciona à noite, no nevoeiro e na poeira. Leia o aprofundamento →

Railcar & wagon recognitionWaggon- & Wagen-ErkennungRailcar & wagon recognitionRailcar & wagon recognitionRailcar & wagon recognitionRailcar & wagon recognitionReconhecimento de vagões ferroviários

Detect, count and identify railcars at a loading station. Drives automated loading sequences, prevents misroutes and feeds a per-wagon material log into ERP. Read the deep dive → Waggons an einer Verlade-Station erkennen, zählen, identifizieren. Treibt automatisierte Verlade-Sequenzen, verhindert Fehl-Verladungen und speist ein Material-Log pro Waggon ins ERP. Zum Use-Case-Deep-Dive → Detect, count and identify railcars at a loading station. Drives automated loading sequences, prevents misroutes and feeds a per-wagon material log into ERP. Read the deep dive → Detect, count and identify railcars at a loading station. Drives automated loading sequences, prevents misroutes and feeds a per-wagon material log into ERP. Read the deep dive → Detect, count and identify railcars at a loading station. Drives automated loading sequences, prevents misroutes and feeds a per-wagon material log into ERP. Read the deep dive → Detect, count and identify railcars at a loading station. Drives automated loading sequences, prevents misroutes and feeds a per-wagon material log into ERP. Read the deep dive → Detecte, conte e identifique vagões em uma estação de carregamento. Aciona sequências automatizadas de carregamento, previne desvios de rota e alimenta um log de material por vagão diretamente no ERP. Leia o aprofundamento →

Worker detection & ATEX zonesPersonenerkennung & ATEX-ZonenWorker detection & ATEX zonesWorker detection & ATEX zonesWorker detection & ATEX zonesWorker detection & ATEX zonesDetecção de trabalhadores e zonas ATEX

Person detection in hazard zones — ATEX areas, swing radius of cranes, conveyor pull-cords. Triggers slowdowns, hard stops or audible warnings. Auditable event log for the safety officer. Read the deep dive → Personenerkennung in Gefahrenbereichen — ATEX-Zonen, Schwenkbereich von Kranen, Reißleinen an Bändern. Löst Drosselungen, Hart-Stopps oder Warnungen aus. Auditfähiger Ereignis-Log für die Sicherheits-Beauftragten. Zum Use-Case-Deep-Dive → Person detection in hazard zones — ATEX areas, swing radius of cranes, conveyor pull-cords. Triggers slowdowns, hard stops or audible warnings. Auditable event log for the safety officer. Read the deep dive → Person detection in hazard zones — ATEX areas, swing radius of cranes, conveyor pull-cords. Triggers slowdowns, hard stops or audible warnings. Auditable event log for the safety officer. Read the deep dive → Person detection in hazard zones — ATEX areas, swing radius of cranes, conveyor pull-cords. Triggers slowdowns, hard stops or audible warnings. Auditable event log for the safety officer. Read the deep dive → Person detection in hazard zones — ATEX areas, swing radius of cranes, conveyor pull-cords. Triggers slowdowns, hard stops or audible warnings. Auditable event log for the safety officer. Read the deep dive → Detecção de pessoas em zonas de perigo — áreas ATEX, raio de giro de guindastes, cabos de tração de correias. Dispara reduções de velocidade, paradas totais ou avisos sonoros. Log de eventos auditável para o técnico de segurança. Leia o aprofundamento →

Stack we useUnser StackStack we useStack we useStack we useStack we useStack que usamos

Mature tools — industry-standard, not experimental. Reife Werkzeuge — Industrie-Standard, nicht experimentell. Mature tools — industry-standard, not experimental. Mature tools — industry-standard, not experimental. Mature tools — industry-standard, not experimental. Mature tools — industry-standard, not experimental. Ferramentas maduras — padrão da indústria, não experimentais.

We keep the stack boring on purpose. Every library on this list has a multi-year track record in industrial production environments. Wir halten den Stack absichtlich langweilig. Jede Bibliothek auf dieser Liste hat einen mehrjährigen Track-Record in industriellen Produktionsumgebungen. We keep the stack boring on purpose. Every library on this list has a multi-year track record in industrial production environments. We keep the stack boring on purpose. Every library on this list has a multi-year track record in industrial production environments. We keep the stack boring on purpose. Every library on this list has a multi-year track record in industrial production environments. We keep the stack boring on purpose. Every library on this list has a multi-year track record in industrial production environments. Mantemos o stack propositalmente sem novidades. Toda biblioteca desta lista tem histórico de vários anos em ambientes industriais de produção.

Point cloudPunktwolkePoint cloudPoint cloudPoint cloudPoint cloudNuvem de pontos

PCL, Open3D

Computer visionBildverarbeitungComputer visionComputer visionComputer visionComputer visionVisão computacional

OpenCV

Deep learningDeep LearningDeep learningDeep learningDeep learningDeep learningAprendizado profundo

PyTorch

LanguagesSprachenLanguagesLanguagesLanguagesLanguagesLinguagens

Python, C++

DeploymentDeploymentDeploymentDeploymentDeploymentDeploymentImplantação

Docker, Linux, Windows

Robotics middlewareRobotik-MiddlewareRobotics middlewareRobotics middlewareRobotics middlewareRobotics middlewareMiddleware de robótica

ROS / ROS 2

Plant integrationAnlagen-AnbindungPlant integrationPlant integrationPlant integrationPlant integrationIntegração com planta

OPC UA, MQTT, REST, Analog outOPC UA, MQTT, REST, Analog-AusgangOPC UA, MQTT, REST, Analog outOPC UA, MQTT, REST, Analog outOPC UA, MQTT, REST, Analog outOPC UA, MQTT, REST, Analog outOPC UA, MQTT, REST, saída analógica

LiDAR sensorsLiDAR-SensorenLiDAR sensorsLiDAR sensorsLiDAR sensorsLiDAR sensorsSensores LiDAR

Riegl, Livox, Hesai, Ouster, Veyond, Faro

CamerasKamerasCamerasCamerasCamerasCamerasCâmeras

Basler, FLIR, Allied Vision, IDS

Real examplePraxisbeispielReal exampleReal exampleReal exampleReal exampleExemplo real

Railway wagon lid detection — custom geometric pipeline. Bahnwagen-Deckelerkennung — geometrische Pipeline nach Maß. Railway wagon lid detection — custom geometric pipeline. Railway wagon lid detection — custom geometric pipeline. Railway wagon lid detection — custom geometric pipeline. Railway wagon lid detection — custom geometric pipeline. Detecção de tampas em vagões ferroviários — pipeline geométrico sob medida.

Single raw 3D point-cloud scan in, six lid centerpoints plus the wagon number out. Built as a stateless six-stage geometric pipeline (NumPy + scipy) so the core ports cleanly to C++/C# for the final controller. Wrapped in an Electron + Vue 3 + Three.js desktop UI for the plant operators. Scan processed in under two seconds, mean centroid error under five centimetres against hand-labelled ground truth. Ein einziger 3D-Rohscan rein — sechs Deckel-Mittelpunkte plus die Wagennummer raus. Realisiert als zustandslose sechsstufige geometrische Pipeline (NumPy + scipy), damit der Kern sauber nach C++/C# für die finale Steuerung portiert. Verpackt in einer Electron + Vue 3 + Three.js Desktop-Oberfläche für die Anlagenbediener. Scan-Verarbeitung unter zwei Sekunden, mittlerer Mittelpunkt-Fehler unter fünf Zentimeter gegen handgelabelte Ground-Truth. Single raw 3D point-cloud scan in, six lid centerpoints plus the wagon number out. Built as a stateless six-stage geometric pipeline (NumPy + scipy) so the core ports cleanly to C++/C# for the final controller. Wrapped in an Electron + Vue 3 + Three.js desktop UI for the plant operators. Scan processed in under two seconds, mean centroid error under five centimetres against hand-labelled ground truth. Single raw 3D point-cloud scan in, six lid centerpoints plus the wagon number out. Built as a stateless six-stage geometric pipeline (NumPy + scipy) so the core ports cleanly to C++/C# for the final controller. Wrapped in an Electron + Vue 3 + Three.js desktop UI for the plant operators. Scan processed in under two seconds, mean centroid error under five centimetres against hand-labelled ground truth. Single raw 3D point-cloud scan in, six lid centerpoints plus the wagon number out. Built as a stateless six-stage geometric pipeline (NumPy + scipy) so the core ports cleanly to C++/C# for the final controller. Wrapped in an Electron + Vue 3 + Three.js desktop UI for the plant operators. Scan processed in under two seconds, mean centroid error under five centimetres against hand-labelled ground truth. Single raw 3D point-cloud scan in, six lid centerpoints plus the wagon number out. Built as a stateless six-stage geometric pipeline (NumPy + scipy) so the core ports cleanly to C++/C# for the final controller. Wrapped in an Electron + Vue 3 + Three.js desktop UI for the plant operators. Scan processed in under two seconds, mean centroid error under five centimetres against hand-labelled ground truth. Uma única varredura de nuvem de pontos 3D bruta entra, seis centros de tampas mais o número do vagão saem. Construído como pipeline geométrico sem estado, de seis estágios (NumPy + scipy), para que o núcleo seja portado limpamente para C++/C# no controlador final. Envolvido em uma UI desktop Electron + Vue 3 + Three.js para os operadores da planta. Varredura processada em menos de dois segundos, erro médio de centroide abaixo de cinco centímetros contra a verdade de campo rotulada à mão.

FAQ

Questions about custom perception AI. Fragen zur maßgeschneiderten Objekterkennung. Questions about custom perception AI. Questions about custom perception AI. Questions about custom perception AI. Questions about custom perception AI. Perguntas sobre IA de percepção sob medida.

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.
 