Industrial Perception AI — LiDAR & Vision Software

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?Ile kosztuje dedykowane oprogramowanie AI do percepcji?Quanto costa un software di perception AI su misura?Combien coûte un logiciel de perception IA sur mesure ?¿Cuánto cuesta un software de percepción con IA a medida?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.
Nie publikujemy cennika, ponieważ każdy projekt jest wyceniany na podstawie Państwa danych i Państwa logiki decyzyjnej — pracujemy jednak w trzech przewidywalnych wariantach.

Discovery & Assessment — warsztat 1–3-dniowy, na miejscu lub zdalnie, w stałej cenie rzędu niskiej kwoty czterocyfrowej. Otrzymują Państwo pisemną notę wykonalności, rekomendowany kolejny krok oraz (w stosownych przypadkach) ofertę ze stałą ceną na projekt kontynuacyjny. Warsztat jest użyteczny nawet wtedy, gdy nie zdecydują się Państwo na dalszą współpracę — wielu klientów wykorzystuje notę do porównania dwóch lub trzech dostawców.

Custom Pipeline / Tool — projekt trwający 4–12 tygodni, dostarczający działający potok percepcji (parser + algorytm + pulpit lub integracja OPC UA). Stały zakres, stała cena, kod przechodzi na Państwa własność przy odbiorze. Typowa wielkość projektu mieści się w przedziale od średniej kwoty pięciocyfrowej do niskiej sześciocyfrowej, zależnie od wolumenu danych, liczby czujników i głębokości integracji.

Long-term Partnership — miesięczny abonament (retainer) na bieżący rozwój i wsparcie na wezwanie. Wymiarowany według potrzebnej Państwu przepustowości zespołu (zwykle odpowiednik 0,5–2 etatu). W cenie kwartalne planowanie mapy drogowej.

Wszystkie trzy warianty obejmują kod źródłowy, pisemną dokumentację i czyste przekazanie — bez uzależnienia licencyjnego od nas. Pełny model współpracy opisuje nasza usługa Industrial Perception AI.
Non pubblichiamo listini perché ogni progetto viene dimensionato sui vostri dati e sulla vostra logica decisionale — ma lavoriamo su tre fasce prevedibili.

Discovery & Assessment — un workshop di 1–3 giorni, in sede o da remoto, a prezzo fisso nell'ordine delle poche migliaia di euro. Ricevete una nota di fattibilità scritta, un passo successivo raccomandato e (se applicabile) un'offerta a prezzo fisso per il progetto successivo. Utile anche se poi non procedete — molti clienti usano la nota per valutare due o tre fornitori.

Custom Pipeline / Tool — un progetto di 4–12 settimane che consegna una pipeline di percezione funzionante (parser + algoritmo + dashboard o integrazione OPC UA). Perimetro fisso, prezzo fisso, il codice è vostro alla consegna. La dimensione tipica del progetto va da un valore medio a cinque cifre fino a uno basso a sei cifre, a seconda del volume di dati, del numero di sensori e della profondità di integrazione.

Long-term Partnership — un canone mensile per sviluppo continuo e supporto on-call. Dimensionato sulla capacità di team di cui avete bisogno (tipicamente l'equivalente di 0,5–2 FTE). Roadmap trimestrale inclusa.

Tutte e tre le fasce includono codice sorgente, documentazione scritta e un passaggio di consegne pulito — nessuna dipendenza da licenze verso di noi. Consultate il nostro servizio Industrial Perception AI per il modello di collaborazione completo.
Nous ne publions pas de tarifs catalogue, car chaque projet est dimensionné en fonction de vos données et de votre logique décisionnelle — mais nous travaillons selon trois paliers prévisibles.

Discovery & Assessment — un atelier de 1 à 3 jours, sur site ou à distance, à prix forfaitaire de l'ordre de quelques milliers d'euros. Vous recevez une note de faisabilité écrite, une recommandation pour l'étape suivante et (le cas échéant) un devis à prix fixe pour le projet de suite. Utile même si vous ne poursuivez pas — de nombreux clients utilisent la note pour évaluer deux ou trois fournisseurs.

Pipeline / outil sur mesure — un projet de 4 à 12 semaines livrant un pipeline de perception opérationnel (parseur + algorithme + tableau de bord ou intégration OPC UA). Périmètre fixe, prix fixe, le code vous appartient à la livraison. La taille de projet typique se situe entre le milieu des cinq chiffres et le bas des six chiffres, selon le volume de données, le nombre de capteurs et la profondeur d'intégration.

Partenariat de long terme — un forfait mensuel pour le développement continu et le support d'astreinte. Dimensionné selon la capacité d'équipe dont vous avez besoin (typiquement l'équivalent de 0,5 à 2 ETP). Feuille de route trimestrielle incluse.

Les trois paliers incluent le code source, une documentation écrite et une passation propre — aucune dépendance de licence envers nous. Consultez notre service Industrial Perception AI pour le modèle d'engagement complet.
No publicamos precios de lista porque cada proyecto se dimensiona en función de sus datos y de su lógica de decisión — pero trabajamos con tres niveles predecibles.

Discovery & Assessment — un taller de 1–3 días, in situ o en remoto, a precio fijo en el rango bajo de cuatro cifras. Usted recibe una nota de viabilidad por escrito, una recomendación del siguiente paso y (si procede) una oferta a precio fijo para el proyecto posterior. Útil incluso si después no sigue adelante — muchos clientes utilizan la nota para evaluar a dos o tres proveedores.

Pipeline / herramienta a medida — un proyecto de 4–12 semanas que entrega un pipeline de percepción operativo (parser + algoritmo + panel de control o integración OPC UA). Alcance fijo, precio fijo, y usted es propietario del código en la entrega. El tamaño típico del proyecto se sitúa entre el rango medio de cinco cifras y el rango bajo de seis cifras, según el volumen de datos, el número de sensores y la profundidad de la integración.

Colaboración a largo plazo — una cuota mensual para desarrollo continuo y soporte de guardia. Dimensionada según la capacidad de equipo que usted necesite (normalmente el equivalente a 0,5–2 FTE). Incluye planificación de hoja de ruta trimestral.

Los tres niveles incluyen código fuente, documentación escrita y una entrega limpia — sin dependencia de licencias con nosotros. Consulte nuestro servicio de Industrial Perception AI para conocer el modelo de colaboración completo.
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?Ile trwa budowa dedykowanego potoku percepcji?Quanto tempo richiede lo sviluppo di una pipeline di percezione su misura?Combien de temps faut-il pour développer un pipeline de perception sur mesure ?¿Cuánto tiempo lleva desarrollar un pipeline de percepción a medida?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.
Od podpisania umowy do działającego narzędzia na produkcji należy założyć 4–12 tygodni dla standardowego projektu typu custom pipeline. Rozpiętość wynika z trzech czynników.

Gotowość danych. Jeśli mają już Państwo oznakowane dane lub reprezentatywne nagrania, trening zaczynamy w 1. tygodniu. Jeśli trzeba zorganizować zbieranie danych, dodać czujnik lub etykietować dane od zera, początkowa faza wydłuża projekt o 1–3 tygodnie.

Głębokość integracji. Samodzielny pulpit z wyjściem REST to najszybsza ścieżka — zwykle 4–6 tygodni. Integracja OPC UA z pracującym systemem sterowania, z blokadami, fabrycznymi testami odbiorczymi i procesem zarządzania zmianą po stronie klienta, to bliżej 8–12 tygodni.

Liczba czujników i złożoność obiektu. Jeden LiDAR + jedna kamera w czystym środowisku wewnątrz hali to szybsza droga niż sześcioczujnikowa bramka na zewnątrz, z pyłem, śniegiem i zmiennym oświetleniem. Różnicę wyceniamy z góry podczas warsztatu Discovery.

Aby szybciej uzyskać pierwszy sygnał, polecamy wariant Discovery & Assessment — 1–3 dni, stała cena, pisemna nota wykonalności w ciągu tygodnia. Pełny model opisuje strona Industrial Perception AI.
Dal contratto firmato a uno strumento funzionante in produzione, prevedete 4–12 settimane per un incarico standard di pipeline su misura. La forbice dipende da tre fattori.

Maturità dei dati. Se disponete già di dati etichettati o di registrazioni rappresentative, iniziamo l'addestramento nella settimana 1. Se dobbiamo impostare la raccolta dati, aggiungere un sensore o etichettare da zero, la fase iniziale aggiunge 1–3 settimane.

Profondità di integrazione. Una dashboard standalone con output REST è la via più rapida — tipicamente 4–6 settimane. Un'integrazione OPC UA in un sistema di controllo in esercizio, con interblocchi, collaudi FAT e un processo di change management del cliente, si avvicina alle 8–12 settimane.

Numero di sensori e complessità del sito. Un LiDAR + una telecamera in un ambiente indoor pulito è più rapido di un portale outdoor a sei sensori con polvere, neve e illuminazione dinamica. Dimensioniamo la differenza fin dall'inizio nel workshop Discovery.

Per un primo riscontro più rapido raccomandiamo la fascia Discovery & Assessment — 1–3 giorni, prezzo fisso, nota di fattibilità scritta entro una settimana. Consultate Industrial Perception AI per il modello completo.
De la signature du contrat à un outil opérationnel en production, comptez 4 à 12 semaines pour un projet de pipeline sur mesure standard. L'écart s'explique par trois facteurs.

Maturité des données. Si vous disposez déjà de données annotées ou d'enregistrements représentatifs, nous commençons l'entraînement dès la semaine 1. S'il faut mettre en place la collecte de données, ajouter un capteur ou annoter à partir de zéro, la phase amont ajoute 1 à 3 semaines.

Profondeur d'intégration. Un tableau de bord autonome avec sortie REST est la voie la plus rapide — typiquement 4 à 6 semaines. Une intégration OPC UA dans un système de conduite en exploitation, avec verrouillages, tests de recette usine et processus de gestion du changement côté client, se rapproche de 8 à 12 semaines.

Nombre de capteurs et complexité du site. Un LiDAR + une caméra dans un environnement intérieur propre vont plus vite qu'un portail extérieur à six capteurs avec poussière, neige et éclairage changeant. Nous chiffrons la différence d'emblée lors de l'atelier Discovery.

Pour un premier signal plus rapide, nous recommandons le palier Discovery & Assessment — 1 à 3 jours, prix fixe, note de faisabilité écrite sous une semaine. Consultez Industrial Perception AI pour le modèle complet.
Desde la firma del contrato hasta una herramienta operativa en producción, cuente con 4–12 semanas para un proyecto estándar de pipeline a medida. La horquilla depende de tres factores.

Preparación de los datos. Si usted ya dispone de datos etiquetados o de grabaciones representativas, empezamos a entrenar en la semana 1. Si tenemos que montar la recogida de datos, añadir un sensor o etiquetar desde cero, la fase inicial añade 1–3 semanas.

Profundidad de la integración. Un panel de control independiente con salida REST es la vía más rápida — normalmente 4–6 semanas. Una integración OPC UA en un sistema de control en funcionamiento, con enclavamientos, pruebas de aceptación en fábrica y un proceso de gestión de cambios del cliente, se acerca más a las 8–12 semanas.

Número de sensores y complejidad del emplazamiento. Un LiDAR + una cámara en un entorno interior limpio es más rápido que un portal exterior de seis sensores con polvo, nieve e iluminación cambiante. Dimensionamos la diferencia desde el principio en el taller Discovery.

Para obtener una primera señal más rápida recomendamos el nivel Discovery & Assessment — 1–3 días, precio fijo, nota de viabilidad por escrito en una semana. Consulte Industrial Perception AI para conocer el modelo completo.
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?Kto jest właścicielem kodu i własności intelektualnej, za których stworzenie płacimy?A chi appartengono il codice e la proprietà intellettuale che ci pagate per sviluppare?À qui appartiennent le code et la propriété intellectuelle que nous vous payons pour développer ?¿Quién es el propietario del código y de la propiedad intelectual que les pagamos por desarrollar?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.
Państwo. Nasza standardowa umowa przenosi na Państwa pełną własność kodu powstałego w projekcie, wag modeli, danych treningowych (o ile dane należą do Państwa) oraz dokumentacji z chwilą odbioru końcowego. Nie zachowujemy licencyjnej „tylnej furtki" i nie wiążemy Państwa umową serwisową.

To, co zatrzymujemy, to nasz istniejący wcześniej zestaw narzędzi — biblioteki wielokrotnego użytku, narzędzia kalibracyjne, uniwersalne parsery danych, rdzeń OWL EYE® — który licencjonujemy Państwu nieodpłatnie (royalty-free) do użytku w dostarczonym narzędziu. To ta sama granica, którą wyznacza każda renomowana firma inżynierska: my wnosimy skrzynkę z narzędziami, Państwo zatrzymują produkt końcowy.

Jeśli potrzebują Państwo innego układu własności intelektualnej — na przykład wspólnego patentu na nowatorski algorytm albo współtworzonego modelu, z którego obie strony korzystają za obopólną zgodą — regulujemy to wprost w umowie projektowej. Prosimy zasygnalizować to na początku, podczas warsztatu Discovery.

Pełne zasady współpracy: nasza strona Industrial Perception AI.
A voi. Il nostro contratto standard trasferisce a voi, all'accettazione finale, la piena proprietà del codice specifico di progetto, dei pesi dei modelli, dei dati di addestramento (dove i dati sono vostri) e della documentazione. Non ci riserviamo alcuna licenza dalla porta di servizio e non vi vincoliamo a un contratto di manutenzione.

Ciò che manteniamo è la nostra cassetta degli attrezzi preesistente — librerie riutilizzabili, utility di calibrazione, parser dati generici, il core OWL EYE® — che vi concediamo in licenza, esente da royalty, per l'uso sullo strumento consegnato. È lo stesso confine che traccia qualsiasi società di ingegneria seria: noi portiamo gli attrezzi, voi tenete il risultato.

Se desiderate un assetto IP diverso — per esempio un brevetto congiunto su un algoritmo innovativo, o un modello co-sviluppato che entrambi riutilizziamo previo consenso — lo strutturiamo esplicitamente nel contratto di progetto. Comunicatecelo fin dall'inizio nel workshop Discovery.

Tutti i dettagli della collaborazione sulla nostra pagina Industrial Perception AI.
À vous. Notre contrat standard vous transfère la pleine propriété du code spécifique au projet, des poids de modèles, des données d'entraînement (lorsque les données sont les vôtres) et de la documentation à la recette finale. Nous ne conservons aucune licence dissimulée et nous ne vous enfermons pas dans un contrat de maintenance.

Ce que nous conservons, c'est notre boîte à outils préexistante — bibliothèques réutilisables, utilitaires d'étalonnage, parseurs de données génériques, le cœur OWL EYE® — que nous vous concédons sous licence, libre de redevances, pour l'utilisation de l'outil livré. C'est la même frontière que trace tout bureau d'ingénierie sérieux : nous apportons la boîte à outils, vous gardez le livrable.

Si vous souhaitez un arrangement de propriété intellectuelle différent — par exemple un brevet conjoint sur un algorithme inédit, ou un modèle co-développé que nous réutilisons tous deux avec consentement — nous le structurons explicitement dans le contrat de projet. Dites-le-nous d'emblée lors de l'atelier Discovery.

Tous les détails de l'engagement sur notre page Industrial Perception AI.
Usted. Nuestro contrato estándar le transfiere la plena propiedad del código específico del proyecto, los pesos del modelo, los datos de entrenamiento (cuando los datos son suyos) y la documentación en el momento de la aceptación final. No conservamos ninguna licencia encubierta ni le atamos a un contrato de mantenimiento.

Lo que retenemos es nuestra caja de herramientas preexistente — bibliotecas reutilizables, utilidades de calibración, parsers de datos genéricos, el núcleo OWL EYE® — que le licenciamos, libre de regalías, para su uso en la herramienta entregada. Es la misma frontera que traza cualquier firma de ingeniería seria: nosotros aportamos la caja de herramientas, usted se queda con el entregable.

Si desea un acuerdo de propiedad intelectual diferente — por ejemplo, una patente conjunta sobre un algoritmo novedoso, o un modelo codesarrollado que ambas partes reutilicen con consentimiento — lo estructuramos de forma explícita en el contrato del proyecto. Comuníquenoslo desde el principio en el taller Discovery.

Todos los detalles de la colaboración en nuestra página de Industrial Perception AI.
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?Czy mogą Państwo wykorzystać nasze istniejące kamery i czujniki LiDAR?Potete usare le nostre telecamere e i nostri sensori LiDAR esistenti?Pouvez-vous utiliser nos caméras et capteurs LiDAR existants ?¿Pueden utilizar nuestras cámaras y sensores LiDAR existentes?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.
Tak — w większości przypadków. Nasz zestaw narzędzi jest na warstwie danych niezależny od czujników. Jeśli Państwa czujniki dostarczają dane w standardowym formacie (PCD, LAS, E57 dla chmur punktów; RTSP, GigE Vision, USB3 Vision dla kamer), możemy je podłączyć w jeden dzień. Pracowaliśmy z urządzeniami Riegl, Livox, Faro, Hesai, Velodyne i Ouster oraz z kamerami Basler, FLIR, Allied Vision i IDS.

Powiemy Państwu szczerze, gdy istniejący sprzęt nie jest właściwym narzędziem. Typowe przypadki, w których zalecamy wymianę:

- Istniejący LiDAR jest zbyt wąski (pole widzenia lub zasięg), aby pokryć obszar, który ma być klasyfikowany — zwykle rozwiązuje to zmiana pozycji montażu, zanim cokolwiek nowego zostanie kupione.
- Kamera pracuje z automatyczną ekspozycją w scenie o wysokim kontraście (słońce + cień przy bramie), co niszczy niezawodność klasyfikacji — rozwiązaniem jest przejście na przemysłową kamerę z ręczną ekspozycją i sensorem HDR.
- Uzależnienie od dostawcy istniejącego czujnika (własnościowy format strumienia, brak udokumentowanego SDK) sprawia, że integracja kosztuje więcej niż wymiana na Livox.

Nie zarabiamy marży na odsprzedaży sprzętu. Jeśli jednak chcą Państwo, abyśmy dostarczyli nowe czujniki, robimy to przez nasz standardowy kanał Hardware & products po cenach katalogowych. Sposób wyceny opisuje strona Industrial Perception AI.
Sì — nella maggior parte dei casi. La nostra toolchain è agnostica rispetto ai sensori sul livello dati. Se i vostri sensori forniscono un formato standard (PCD, LAS, E57 per le nuvole di punti; RTSP, GigE Vision, USB3 Vision per le telecamere) possiamo acquisirli in un giorno. Abbiamo lavorato con telecamere e sensori Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision e IDS.

Vi diremo onestamente quando l'hardware esistente non è lo strumento giusto. Casi tipici in cui raccomandiamo una sostituzione:

- Il LiDAR esistente è troppo limitato (FoV o portata) per coprire l'area che volete classificare — di solito si risolve riposizionandolo prima di acquistare qualcosa di nuovo.
- La telecamera esegue l'esposizione automatica su una scena ad alto contrasto (sole + ombra a un varco), il che compromette l'affidabilità della classificazione — si risolve passando a una telecamera industriale a esposizione manuale con sensore HDR.
- Il vendor lock-in del sensore esistente (formato di streaming proprietario, nessun SDK documentato) rende l'integrazione più costosa di una sostituzione con Livox.

Non guadagniamo margini rivendendovi hardware. Se desiderate che siamo noi a procurare nuovi sensori, lo facciamo tramite il nostro normale canale Hardware & prodotti a prezzo di listino. Consultate Industrial Perception AI per come dimensioniamo il progetto.
Oui — dans la plupart des cas. Notre chaîne d'outils est agnostique vis-à-vis des capteurs au niveau de la couche de données. Si vos capteurs livrent un format standard (PCD, LAS, E57 pour les nuages de points ; RTSP, GigE Vision, USB3 Vision pour les caméras), nous pouvons les intégrer en une journée. Nous avons travaillé avec des LiDAR Riegl, Livox, Faro, Hesai, Velodyne, Ouster et des caméras Basler, FLIR, Allied Vision et IDS.

Nous vous dirons honnêtement quand le matériel existant n'est pas le bon outil. Cas courants où nous recommandons un remplacement :

- Le LiDAR existant est trop étroit (champ de vision ou portée) pour couvrir la zone à classifier — généralement résolu par un repositionnement avant tout nouvel achat.
- La caméra fonctionne en exposition automatique sur une scène très contrastée (soleil + ombre à un portail), ce qui compromet la fiabilité de la classification — résolu en passant à une caméra industrielle à exposition manuelle avec capteur HDR.
- Le verrouillage propriétaire du capteur existant (format de flux propriétaire, pas de SDK documenté) rend l'intégration plus coûteuse qu'un remplacement par un Livox.

Nous ne prenons pas de marge sur la revente de matériel. Si vous souhaitez que nous fournissions de nouveaux capteurs, nous le faisons via notre canal habituel Hardware & produits au prix catalogue. Consultez Industrial Perception AI pour notre méthode de cadrage.
Sí — en la mayoría de los casos. Nuestra cadena de herramientas es agnóstica al sensor en la capa de datos. Si sus sensores entregan un formato estándar (PCD, LAS, E57 para nubes de puntos; RTSP, GigE Vision, USB3 Vision para cámaras), podemos integrarlos en un día. Hemos trabajado con cámaras Riegl, Livox, Faro, Hesai, Velodyne, Ouster, Basler, FLIR, Allied Vision e IDS.

Le diremos con honestidad cuándo el hardware existente no es la herramienta adecuada. Casos frecuentes en los que recomendamos una sustitución:

- El LiDAR existente es demasiado limitado (campo de visión o alcance) para cubrir el área que usted quiere clasificar — normalmente se resuelve reposicionándolo antes de comprar nada nuevo.
- La cámara aplica exposición automática en una escena de alto contraste (sol + sombra en un portón), lo que arruina la fiabilidad de la clasificación — se resuelve cambiando a una cámara industrial de exposición manual con sensor HDR.
- La dependencia del fabricante del sensor existente (formato de transmisión propietario, sin SDK documentado) hace que la integración cueste más que una sustitución por Livox.

No obtenemos margen revendiéndole hardware. Si desea que nosotros nos encarguemos de adquirir sensores nuevos, lo hacemos a través de nuestro canal habitual de Hardware y productos a precio de lista. Consulte Industrial Perception AI para ver cómo lo dimensionamos.
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.
 