Vehicle Gate Detection AI — LiDAR + Camera at Gates

USE CASEANWENDUNGSFALLUSE CASEUSE CASEUSE CASEUSE CASE · Vehicle gate detection · LiDAR + camera fusionFahrzeugerkennung Werkstor · Fusion aus LiDAR und KameraVehicle gate detection · LiDAR + camera fusionVehicle gate detection · LiDAR + camera fusionVehicle gate detection · LiDAR + camera fusionVehicle gate detection · LiDAR + camera fusion

Identify the vehicle at the gate, before it queues or blocks the lane. Fahrzeug am Werkstor erkennen, bevor es steht oder die Spur blockiert. Identify the vehicle at the gate, before it queues or blocks the lane. Identify the vehicle at the gate, before it queues or blocks the lane. Identify the vehicle at the gate, before it queues or blocks the lane. Identify the vehicle at the gate, before it queues or blocks the lane.

Vehicle gate detection AI is a perception pipeline mounted at industrial plant gates, intersections and weighbridges that uses LiDAR and a calibrated camera to identify and classify approaching vehicles (truck, wheel loader, forklift, AGV) in real time and drives gate-control, weighing and in-plant routing decisions.Fahrzeugerkennung KI ist eine Wahrnehmungs-Pipeline an industriellen Werkstoren, Kreuzungen und Brückenwaagen, die mit LiDAR und kalibrierter Kamera heranfahrende Fahrzeuge (LKW, Radlader, Stapler, AGV) in Echtzeit identifiziert und klassifiziert — und das Ergebnis direkt in Tor-Steuerung, Waage und Werks-Routing speist.Vehicle gate detection AI is a perception pipeline mounted at industrial plant gates, intersections and weighbridges that uses LiDAR and a calibrated camera to identify and classify approaching vehicles (truck, wheel loader, forklift, AGV) in real time and drives gate-control, weighing and in-plant routing decisions.Vehicle gate detection AI is a perception pipeline mounted at industrial plant gates, intersections and weighbridges that uses LiDAR and a calibrated camera to identify and classify approaching vehicles (truck, wheel loader, forklift, AGV) in real time and drives gate-control, weighing and in-plant routing decisions.Vehicle gate detection AI is a perception pipeline mounted at industrial plant gates, intersections and weighbridges that uses LiDAR and a calibrated camera to identify and classify approaching vehicles (truck, wheel loader, forklift, AGV) in real time and drives gate-control, weighing and in-plant routing decisions.Vehicle gate detection AI is a perception pipeline mounted at industrial plant gates, intersections and weighbridges that uses LiDAR and a calibrated camera to identify and classify approaching vehicles (truck, wheel loader, forklift, AGV) in real time and drives gate-control, weighing and in-plant routing decisions.

The pain is well-known to every plant operator. Existing gate automation relies on RFID tags, ANPR cameras and induction loops — and each one fails in a different condition. RFID assumes every vehicle carries a working tag, which falls over the moment a subcontractor, a hire truck or a maintenance vehicle turns up. ANPR cameras lose the plate in dirt, road spray, low sun or driving snow. Induction loops miss small vehicles, forklifts on rubber tyres and pedestrians altogether. The plant ends up paying a manual gate operator or living with a delayed gate, and the queue at peak shifts turns into measurable lost throughput.Den Schmerz kennt jeder Werks-Betreiber. Bestehende Tor-Automatisierung läuft über RFID-Tags, ANPR-Kameras (Kennzeichen-Lese-Kameras) und Induktionsschleifen — und jede einzelne fällt in einer anderen Bedingung aus. RFID setzt voraus, dass jedes Fahrzeug einen funktionierenden Tag trägt — das scheitert sofort, wenn ein Subunternehmer, ein Miet-LKW oder ein Werkstattfahrzeug kommt. ANPR-Kameras verlieren das Kennzeichen bei Schmutz, Spritzwasser, tiefstehender Sonne oder Schneetreiben. Induktionsschleifen übersehen kleine Fahrzeuge, gummibereifte Stapler und Personen komplett. Am Ende steht entweder ein Pförtner manuell am Tor oder das Tor öffnet verzögert — und die Stoßzeit-Schlange wird zum messbaren Durchsatz-Verlust.The pain is well-known to every plant operator. Existing gate automation relies on RFID tags, ANPR cameras and induction loops — and each one fails in a different condition. RFID assumes every vehicle carries a working tag, which falls over the moment a subcontractor, a hire truck or a maintenance vehicle turns up. ANPR cameras lose the plate in dirt, road spray, low sun or driving snow. Induction loops miss small vehicles, forklifts on rubber tyres and pedestrians altogether. The plant ends up paying a manual gate operator or living with a delayed gate, and the queue at peak shifts turns into measurable lost throughput.The pain is well-known to every plant operator. Existing gate automation relies on RFID tags, ANPR cameras and induction loops — and each one fails in a different condition. RFID assumes every vehicle carries a working tag, which falls over the moment a subcontractor, a hire truck or a maintenance vehicle turns up. ANPR cameras lose the plate in dirt, road spray, low sun or driving snow. Induction loops miss small vehicles, forklifts on rubber tyres and pedestrians altogether. The plant ends up paying a manual gate operator or living with a delayed gate, and the queue at peak shifts turns into measurable lost throughput.The pain is well-known to every plant operator. Existing gate automation relies on RFID tags, ANPR cameras and induction loops — and each one fails in a different condition. RFID assumes every vehicle carries a working tag, which falls over the moment a subcontractor, a hire truck or a maintenance vehicle turns up. ANPR cameras lose the plate in dirt, road spray, low sun or driving snow. Induction loops miss small vehicles, forklifts on rubber tyres and pedestrians altogether. The plant ends up paying a manual gate operator or living with a delayed gate, and the queue at peak shifts turns into measurable lost throughput.The pain is well-known to every plant operator. Existing gate automation relies on RFID tags, ANPR cameras and induction loops — and each one fails in a different condition. RFID assumes every vehicle carries a working tag, which falls over the moment a subcontractor, a hire truck or a maintenance vehicle turns up. ANPR cameras lose the plate in dirt, road spray, low sun or driving snow. Induction loops miss small vehicles, forklifts on rubber tyres and pedestrians altogether. The plant ends up paying a manual gate operator or living with a delayed gate, and the queue at peak shifts turns into measurable lost throughput.

Our approach fuses two sensors at the gate. A 3D-LiDAR delivers geometry-based detection that does not care about paint, lighting, dirt or weather — a truck has the silhouette of a truck whether it is clean, muddy or covered in road salt. A calibrated camera adds visual confirmation and, where the camera angle allows, fuses with existing ANPR for plate identification. A custom classifier — trained on your fleet, your wheel loaders, your forklifts, your AGVs — returns a per-vehicle class plus track ID, written directly into the gate PLC or the weighbridge controller. Pedestrians are detected as a separate safety class.Unser Ansatz fusioniert zwei Sensoren am Werkstor. Ein 3D-LiDAR liefert geometrie-basierte Erkennung, die sich nicht für Lack, Licht, Schmutz oder Wetter interessiert — ein LKW hat die Silhouette eines LKW, ob sauber, schlammig oder mit Streusalz überzogen. Eine kalibrierte Kamera ergänzt die visuelle Bestätigung und fusioniert dort, wo der Winkel passt, mit der bestehenden ANPR-Kamera für die Kennzeichen-Lesung. Ein eigener Klassifikator — trainiert auf Ihrem Fuhrpark, Ihren Radladern, Ihren Staplern, Ihren AGV — liefert pro Fahrzeug eine Klasse plus Track-ID und schreibt direkt in die Tor-SPS oder den Waage-Controller. Personen werden als eigene Sicherheits-Klasse erkannt.Our approach fuses two sensors at the gate. A 3D-LiDAR delivers geometry-based detection that does not care about paint, lighting, dirt or weather — a truck has the silhouette of a truck whether it is clean, muddy or covered in road salt. A calibrated camera adds visual confirmation and, where the camera angle allows, fuses with existing ANPR for plate identification. A custom classifier — trained on your fleet, your wheel loaders, your forklifts, your AGVs — returns a per-vehicle class plus track ID, written directly into the gate PLC or the weighbridge controller. Pedestrians are detected as a separate safety class.Our approach fuses two sensors at the gate. A 3D-LiDAR delivers geometry-based detection that does not care about paint, lighting, dirt or weather — a truck has the silhouette of a truck whether it is clean, muddy or covered in road salt. A calibrated camera adds visual confirmation and, where the camera angle allows, fuses with existing ANPR for plate identification. A custom classifier — trained on your fleet, your wheel loaders, your forklifts, your AGVs — returns a per-vehicle class plus track ID, written directly into the gate PLC or the weighbridge controller. Pedestrians are detected as a separate safety class.Our approach fuses two sensors at the gate. A 3D-LiDAR delivers geometry-based detection that does not care about paint, lighting, dirt or weather — a truck has the silhouette of a truck whether it is clean, muddy or covered in road salt. A calibrated camera adds visual confirmation and, where the camera angle allows, fuses with existing ANPR for plate identification. A custom classifier — trained on your fleet, your wheel loaders, your forklifts, your AGVs — returns a per-vehicle class plus track ID, written directly into the gate PLC or the weighbridge controller. Pedestrians are detected as a separate safety class.Our approach fuses two sensors at the gate. A 3D-LiDAR delivers geometry-based detection that does not care about paint, lighting, dirt or weather — a truck has the silhouette of a truck whether it is clean, muddy or covered in road salt. A calibrated camera adds visual confirmation and, where the camera angle allows, fuses with existing ANPR for plate identification. A custom classifier — trained on your fleet, your wheel loaders, your forklifts, your AGVs — returns a per-vehicle class plus track ID, written directly into the gate PLC or the weighbridge controller. Pedestrians are detected as a separate safety class.

This is not an off-the-shelf SaaS. Every plant has its own gate layout, its own fleet, its own weighbridge interlock logic. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically a retrofit: we add the sensor portal next to your existing gate, RFID reader, ANPR camera and weighbridge — we do not replace what already works. The code and the model are handed over to you at the end. Related capability: truck terminal LiDAR volume measurement.Das ist kein SaaS von der Stange. Jedes Werk hat sein eigenes Tor-Layout, seinen eigenen Fuhrpark, seine eigene Waage-Verriegelungs-Logik. Wir behandeln jedes Projekt als Discovery + Festscope-Build, abgeleitet aus unserem Hub-Service Industrielle Objekterkennung. Typisch als Retrofit: Wir setzen das Sensor-Portal neben Ihr bestehendes Tor, RFID-Lesegerät, ANPR-Kamera und die Brückenwaage — wir ersetzen nicht, was schon funktioniert. Code und Modell gehören Ihnen bei der Übergabe. Verwandte Lösung: Truck Terminal — LiDAR-Volumenmessung am LKW.This is not an off-the-shelf SaaS. Every plant has its own gate layout, its own fleet, its own weighbridge interlock logic. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically a retrofit: we add the sensor portal next to your existing gate, RFID reader, ANPR camera and weighbridge — we do not replace what already works. The code and the model are handed over to you at the end. Related capability: truck terminal LiDAR volume measurement.This is not an off-the-shelf SaaS. Every plant has its own gate layout, its own fleet, its own weighbridge interlock logic. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically a retrofit: we add the sensor portal next to your existing gate, RFID reader, ANPR camera and weighbridge — we do not replace what already works. The code and the model are handed over to you at the end. Related capability: truck terminal LiDAR volume measurement.This is not an off-the-shelf SaaS. Every plant has its own gate layout, its own fleet, its own weighbridge interlock logic. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically a retrofit: we add the sensor portal next to your existing gate, RFID reader, ANPR camera and weighbridge — we do not replace what already works. The code and the model are handed over to you at the end. Related capability: truck terminal LiDAR volume measurement.This is not an off-the-shelf SaaS. Every plant has its own gate layout, its own fleet, its own weighbridge interlock logic. We treat every engagement as a discovery + fixed-scope build, descending from our hub service Industrial Perception AI. Typically a retrofit: we add the sensor portal next to your existing gate, RFID reader, ANPR camera and weighbridge — we do not replace what already works. The code and the model are handed over to you at the end. Related capability: truck terminal LiDAR volume measurement.

„A gate that opens for the right vehicle and only the right vehicle pays for itself in queue minutes alone." „Ein Tor, das für das richtige Fahrzeug aufgeht und nur für das richtige, zahlt sich allein über Wartezeiten aus." „A gate that opens for the right vehicle and only the right vehicle pays for itself in queue minutes alone." „A gate that opens for the right vehicle and only the right vehicle pays for itself in queue minutes alone." „A gate that opens for the right vehicle and only the right vehicle pays for itself in queue minutes alone." „A gate that opens for the right vehicle and only the right vehicle pays for itself in queue minutes alone."

Built on the same perception stack we use for our LiDAR wagon-detection and truck-terminal volume pipelines — sub-5 cm geometry, two-second response. Gebaut auf demselben Wahrnehmungs-Stack, mit dem wir LiDAR-Waggon-Erkennung und Truck-Terminal-Volumenmessung liefern — Geometrie unter 5 cm, Antwort in zwei Sekunden. Built on the same perception stack we use for our LiDAR wagon-detection and truck-terminal volume pipelines — sub-5 cm geometry, two-second response. Built on the same perception stack we use for our LiDAR wagon-detection and truck-terminal volume pipelines — sub-5 cm geometry, two-second response. Built on the same perception stack we use for our LiDAR wagon-detection and truck-terminal volume pipelines — sub-5 cm geometry, two-second response. Built on the same perception stack we use for our LiDAR wagon-detection and truck-terminal volume pipelines — sub-5 cm geometry, two-second response.

Three stagesDrei StufenThree stagesThree stagesThree stagesThree stages

From approach to gate signal — three stages of the pipeline. Vom Anfahren bis zum Tor-Signal — drei Stufen der Pipeline. From approach to gate signal — three stages of the pipeline. From approach to gate signal — three stages of the pipeline. From approach to gate signal — three stages of the pipeline. From approach to gate signal — three stages of the pipeline.

1 · Sensor at the gate1 · Sensor am Werkstor1 · Sensor at the gate1 · Sensor at the gate1 · Sensor at the gate1 · Sensor at the gate

One LiDAR plus one calibrated camera mounted on a portal, mast or existing gate structure at the plant entrance, weighbridge approach or dispatch shed. Detection range 3–30 m, throughput beyond 300 vehicles per hour. IP65+ housings, dust-tolerant optics, runs in fog, snow, night and direct sunshine — no maintenance call when the weather turns. Ein LiDAR plus eine kalibrierte Kamera, montiert auf einem Portal, Mast oder der bestehenden Tor-Konstruktion am Werks-Eingang, in der Waage-Zufahrt oder am Versand-Schuppen. Erfassungs-Reichweite 3–30 m, Durchsatz über 300 Fahrzeuge pro Stunde. IP65+-Gehäuse, staubtolerante Optik — läuft bei Nebel, Schnee, Nacht und direkter Sonne, kein Service-Einsatz bei Wetterumschwung. One LiDAR plus one calibrated camera mounted on a portal, mast or existing gate structure at the plant entrance, weighbridge approach or dispatch shed. Detection range 3–30 m, throughput beyond 300 vehicles per hour. IP65+ housings, dust-tolerant optics, runs in fog, snow, night and direct sunshine — no maintenance call when the weather turns. One LiDAR plus one calibrated camera mounted on a portal, mast or existing gate structure at the plant entrance, weighbridge approach or dispatch shed. Detection range 3–30 m, throughput beyond 300 vehicles per hour. IP65+ housings, dust-tolerant optics, runs in fog, snow, night and direct sunshine — no maintenance call when the weather turns. One LiDAR plus one calibrated camera mounted on a portal, mast or existing gate structure at the plant entrance, weighbridge approach or dispatch shed. Detection range 3–30 m, throughput beyond 300 vehicles per hour. IP65+ housings, dust-tolerant optics, runs in fog, snow, night and direct sunshine — no maintenance call when the weather turns. One LiDAR plus one calibrated camera mounted on a portal, mast or existing gate structure at the plant entrance, weighbridge approach or dispatch shed. Detection range 3–30 m, throughput beyond 300 vehicles per hour. IP65+ housings, dust-tolerant optics, runs in fog, snow, night and direct sunshine — no maintenance call when the weather turns.

2 · Vehicle classification + class-aware logic2 · Fahrzeug-Klassifikation + klassen-bezogene Logik2 · Vehicle classification + class-aware logic2 · Vehicle classification + class-aware logic2 · Vehicle classification + class-aware logic2 · Vehicle classification + class-aware logic

The fusion classifier separates the scene into your vehicle classes — truck, wheel loader, forklift, AGV, passenger car, pedestrian — plus an "unknown" fallback. Class-aware rules let the gate open for trucks at the goods entrance, route loaders to the dispatch shed, hold the gate when a pedestrian is in the lane. Models retrained on your labelled data, not on a public benchmark. Der Fusions-Klassifikator trennt die Szene in Ihre Fahrzeug-Klassen — LKW, Radlader, Stapler, AGV, PKW, Person — plus eine "unbekannt"-Rückfall-Klasse. Klassen-bezogene Regeln öffnen das Tor für LKW am Wareneingang, leiten Radlader zum Versand-Schuppen, halten das Tor bei Person in der Spur. Modelle trainiert auf Ihren gelabelten Daten — nicht auf einem öffentlichen Benchmark. The fusion classifier separates the scene into your vehicle classes — truck, wheel loader, forklift, AGV, passenger car, pedestrian — plus an "unknown" fallback. Class-aware rules let the gate open for trucks at the goods entrance, route loaders to the dispatch shed, hold the gate when a pedestrian is in the lane. Models retrained on your labelled data, not on a public benchmark. The fusion classifier separates the scene into your vehicle classes — truck, wheel loader, forklift, AGV, passenger car, pedestrian — plus an "unknown" fallback. Class-aware rules let the gate open for trucks at the goods entrance, route loaders to the dispatch shed, hold the gate when a pedestrian is in the lane. Models retrained on your labelled data, not on a public benchmark. The fusion classifier separates the scene into your vehicle classes — truck, wheel loader, forklift, AGV, passenger car, pedestrian — plus an "unknown" fallback. Class-aware rules let the gate open for trucks at the goods entrance, route loaders to the dispatch shed, hold the gate when a pedestrian is in the lane. Models retrained on your labelled data, not on a public benchmark. The fusion classifier separates the scene into your vehicle classes — truck, wheel loader, forklift, AGV, passenger car, pedestrian — plus an "unknown" fallback. Class-aware rules let the gate open for trucks at the goods entrance, route loaders to the dispatch shed, hold the gate when a pedestrian is in the lane. Models retrained on your labelled data, not on a public benchmark.

3 · Gate-controller integration3 · Anbindung an die Tor-Steuerung3 · Gate-controller integration3 · Gate-controller integration3 · Gate-controller integration3 · Gate-controller integration

Classification results write into the gate PLC, the weighbridge controller and the yard-management system over OPC UA, REST, MQTT or digital I/O. The gate opens, the weighbridge triggers, the event is logged with class and image evidence, the ticket hands off to ERP. Fuses with existing RFID and ANPR — we strengthen what you have, we do not replace it. Klassifikations-Ergebnisse schreiben in die Tor-SPS, den Waage-Controller und das Werks-Management-System per OPC UA, REST, MQTT oder digitale I/O. Das Tor öffnet, die Brückenwaage löst aus, das Ereignis wird mit Klasse und Bildbeweis geloggt, der Ticket geht ins ERP. Fusioniert mit bestehendem RFID und ANPR — wir verstärken, was Sie haben, wir ersetzen es nicht. Classification results write into the gate PLC, the weighbridge controller and the yard-management system over OPC UA, REST, MQTT or digital I/O. The gate opens, the weighbridge triggers, the event is logged with class and image evidence, the ticket hands off to ERP. Fuses with existing RFID and ANPR — we strengthen what you have, we do not replace it. Classification results write into the gate PLC, the weighbridge controller and the yard-management system over OPC UA, REST, MQTT or digital I/O. The gate opens, the weighbridge triggers, the event is logged with class and image evidence, the ticket hands off to ERP. Fuses with existing RFID and ANPR — we strengthen what you have, we do not replace it. Classification results write into the gate PLC, the weighbridge controller and the yard-management system over OPC UA, REST, MQTT or digital I/O. The gate opens, the weighbridge triggers, the event is logged with class and image evidence, the ticket hands off to ERP. Fuses with existing RFID and ANPR — we strengthen what you have, we do not replace it. Classification results write into the gate PLC, the weighbridge controller and the yard-management system over OPC UA, REST, MQTT or digital I/O. The gate opens, the weighbridge triggers, the event is logged with class and image evidence, the ticket hands off to ERP. Fuses with existing RFID and ANPR — we strengthen what you have, we do not replace it.

Pipeline architecture · #how-it-worksPipeline-Architektur · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-worksPipeline architecture · #how-it-works

How the pipeline works — concretely. Wie die Pipeline arbeitet — konkret. How the pipeline works — concretely. How the pipeline works — concretely. How the pipeline works — concretely. How the pipeline works — concretely.

We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. Wir halten die Architektur absichtlich langweilig. Drei lose gekoppelte Stufen, jede einzeln testbar, jede einzeln tauschbar, wenn sich der Sensor-Stack ändert. Gebaut auf demselben Stack, den wir für unsere gesamte Wahrnehmungs-Arbeit nutzen: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch. We keep the architecture boring on purpose. Three loosely coupled stages, each one independently testable, each one swappable when the sensor stack changes. Built on the same stack we use across all our perception work: PCL, Open3D, OpenCV, PyTorch.

Portal capture (LiDAR + camera)Portal-Erfassung (LiDAR + Kamera)Portal capture (LiDAR + camera)Portal capture (LiDAR + camera)Portal capture (LiDAR + camera)Portal capture (LiDAR + camera)

The LiDAR delivers a 3D point cloud of the approach lane — hundreds of thousands of points per frame at portal speed. The camera adds a synchronised colour image, lens-calibrated and time-stamped. Per-vehicle UUID assigned on first contact and carried through the full track. Raw data writes to local storage for audit trail and re-labelling. Der LiDAR liefert eine 3D-Punktwolke der Zufahrtsspur — hunderttausende Punkte pro Frame bei Portal-Geschwindigkeit. Die Kamera ergänzt ein synchronisiertes Farbbild, objektiv-kalibriert und zeit-gestempelt. Pro Fahrzeug eine UUID, vergeben beim ersten Kontakt und über den gesamten Track mitgeführt. Rohdaten schreiben auf lokalen Speicher für Audit-Trail und Re-Labelling. The LiDAR delivers a 3D point cloud of the approach lane — hundreds of thousands of points per frame at portal speed. The camera adds a synchronised colour image, lens-calibrated and time-stamped. Per-vehicle UUID assigned on first contact and carried through the full track. Raw data writes to local storage for audit trail and re-labelling. The LiDAR delivers a 3D point cloud of the approach lane — hundreds of thousands of points per frame at portal speed. The camera adds a synchronised colour image, lens-calibrated and time-stamped. Per-vehicle UUID assigned on first contact and carried through the full track. Raw data writes to local storage for audit trail and re-labelling. The LiDAR delivers a 3D point cloud of the approach lane — hundreds of thousands of points per frame at portal speed. The camera adds a synchronised colour image, lens-calibrated and time-stamped. Per-vehicle UUID assigned on first contact and carried through the full track. Raw data writes to local storage for audit trail and re-labelling. The LiDAR delivers a 3D point cloud of the approach lane — hundreds of thousands of points per frame at portal speed. The camera adds a synchronised colour image, lens-calibrated and time-stamped. Per-vehicle UUID assigned on first contact and carried through the full track. Raw data writes to local storage for audit trail and re-labelling.

Vehicle classification + ANPR fusionFahrzeug-Klassifikation + ANPR-FusionVehicle classification + ANPR fusionVehicle classification + ANPR fusionVehicle classification + ANPR fusionVehicle classification + ANPR fusion

The point cloud goes through ground removal, voxel down-sampling and a PointNet-style classifier trained on your fleet. The camera image goes through a CNN trained on the same labels — and, where the geometry allows, into the existing ANPR pipeline for plate readout. The heads fuse into a per-track class plus optional plate ID. Pedestrians are detected as a dedicated safety class with a hard interlock. Die Punktwolke läuft durch Boden-Entfernung, Voxel-Downsampling und einen PointNet-artigen Klassifikator, trainiert auf Ihrem Fuhrpark. Das Kamerabild läuft durch ein CNN, trainiert auf denselben Labels — und dort, wo die Geometrie passt, in die bestehende ANPR-Pipeline für die Kennzeichen-Lesung. Beide Köpfe fusionieren zu einer Track-Klasse plus optionalem Kennzeichen. Personen werden als eigene Sicherheits-Klasse mit harter Verriegelung erkannt. The point cloud goes through ground removal, voxel down-sampling and a PointNet-style classifier trained on your fleet. The camera image goes through a CNN trained on the same labels — and, where the geometry allows, into the existing ANPR pipeline for plate readout. The heads fuse into a per-track class plus optional plate ID. Pedestrians are detected as a dedicated safety class with a hard interlock. The point cloud goes through ground removal, voxel down-sampling and a PointNet-style classifier trained on your fleet. The camera image goes through a CNN trained on the same labels — and, where the geometry allows, into the existing ANPR pipeline for plate readout. The heads fuse into a per-track class plus optional plate ID. Pedestrians are detected as a dedicated safety class with a hard interlock. The point cloud goes through ground removal, voxel down-sampling and a PointNet-style classifier trained on your fleet. The camera image goes through a CNN trained on the same labels — and, where the geometry allows, into the existing ANPR pipeline for plate readout. The heads fuse into a per-track class plus optional plate ID. Pedestrians are detected as a dedicated safety class with a hard interlock. The point cloud goes through ground removal, voxel down-sampling and a PointNet-style classifier trained on your fleet. The camera image goes through a CNN trained on the same labels — and, where the geometry allows, into the existing ANPR pipeline for plate readout. The heads fuse into a per-track class plus optional plate ID. Pedestrians are detected as a dedicated safety class with a hard interlock.

Gate-PLC write-back + event logRück-Schreibung an die Tor-SPS + Ereignis-LogGate-PLC write-back + event logGate-PLC write-back + event logGate-PLC write-back + event logGate-PLC write-back + event log

Per-vehicle output: class, track ID, plate (if read), timestamp, audit image. Writes to the gate PLC or weighbridge controller over OPC UA — or to the MES, ERP, yard-management system, whatever the plant already runs. Every event is logged with image evidence; the dashboard shows live vehicle positions across the gate area. Pro Fahrzeug: Klasse, Track-ID, Kennzeichen (falls gelesen), Zeitstempel, Audit-Bild. Schreibt an die Tor-SPS oder den Waage-Controller per OPC UA — oder ins MES, ERP, Werks-Management-System, was die Anlage eben hat. Jedes Ereignis wird mit Bildbeweis geloggt; das Dashboard zeigt Live-Fahrzeug-Positionen im Tor-Bereich. Per-vehicle output: class, track ID, plate (if read), timestamp, audit image. Writes to the gate PLC or weighbridge controller over OPC UA — or to the MES, ERP, yard-management system, whatever the plant already runs. Every event is logged with image evidence; the dashboard shows live vehicle positions across the gate area. Per-vehicle output: class, track ID, plate (if read), timestamp, audit image. Writes to the gate PLC or weighbridge controller over OPC UA — or to the MES, ERP, yard-management system, whatever the plant already runs. Every event is logged with image evidence; the dashboard shows live vehicle positions across the gate area. Per-vehicle output: class, track ID, plate (if read), timestamp, audit image. Writes to the gate PLC or weighbridge controller over OPC UA — or to the MES, ERP, yard-management system, whatever the plant already runs. Every event is logged with image evidence; the dashboard shows live vehicle positions across the gate area. Per-vehicle output: class, track ID, plate (if read), timestamp, audit image. Writes to the gate PLC or weighbridge controller over OPC UA — or to the MES, ERP, yard-management system, whatever the plant already runs. Every event is logged with image evidence; the dashboard shows live vehicle positions across the gate area.

All three stages run on an industrial PC in the gate cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. Alle drei Stufen laufen auf einem Industrie-PC im Tor-Schaltschrank. Keine Cloud-Abhängigkeit, keine externe API, kein Lizenz-Heimruf. Der Code gehört Ihnen bei der Übergabe. All three stages run on an industrial PC in the gate cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC in the gate cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC in the gate cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover. All three stages run on an industrial PC in the gate cabinet. No cloud dependency, no external API, no licence dial-home. The code is yours at handover.

What you getWas Sie bekommenWhat you getWhat you getWhat you getWhat you get

Three deliverables — from the same pipeline. Drei Liefer-Ergebnisse — aus derselben Pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline. Three deliverables — from the same pipeline.

Per-vehicle event logEreignis-Log pro FahrzeugPer-vehicle event logPer-vehicle event logPer-vehicle event logPer-vehicle event log

Every gate pass gets a structured record: class, track ID, plate (if read), timestamp, audit image, gate decision. Drops into ERP, into yard management, into the security audit trail. Searchable per shift, per supplier, per vehicle type — and useful for the incident report nobody wants to write from CCTV scrubbing. Jede Tor-Durchfahrt erhält einen strukturierten Datensatz: Klasse, Track-ID, Kennzeichen (falls gelesen), Zeitstempel, Audit-Bild, Tor-Entscheidung. Geht ins ERP, ins Werks-Management, in den Sicherheits-Audit-Trail. Durchsuchbar pro Schicht, pro Lieferant, pro Fahrzeug-Typ — und nützlich für den Vorfalls-Bericht, den niemand aus CCTV-Material zusammensuchen will. Every gate pass gets a structured record: class, track ID, plate (if read), timestamp, audit image, gate decision. Drops into ERP, into yard management, into the security audit trail. Searchable per shift, per supplier, per vehicle type — and useful for the incident report nobody wants to write from CCTV scrubbing. Every gate pass gets a structured record: class, track ID, plate (if read), timestamp, audit image, gate decision. Drops into ERP, into yard management, into the security audit trail. Searchable per shift, per supplier, per vehicle type — and useful for the incident report nobody wants to write from CCTV scrubbing. Every gate pass gets a structured record: class, track ID, plate (if read), timestamp, audit image, gate decision. Drops into ERP, into yard management, into the security audit trail. Searchable per shift, per supplier, per vehicle type — and useful for the incident report nobody wants to write from CCTV scrubbing. Every gate pass gets a structured record: class, track ID, plate (if read), timestamp, audit image, gate decision. Drops into ERP, into yard management, into the security audit trail. Searchable per shift, per supplier, per vehicle type — and useful for the incident report nobody wants to write from CCTV scrubbing.

Gate-control automationTor-Steuerung automatisiertGate-control automationGate-control automationGate-control automationGate-control automation

The gate opens — or stays closed — based on classification plus your business rules: trucks at the goods entrance, loaders at the dispatch shed, only forklifts inside the warehouse aisle. Queue logic handles back-to-back arrivals without bouncing. The manual gate operator becomes an exception handler, not a full-time role. Das Tor öffnet — oder bleibt zu — basierend auf Klassifikation plus Ihren Geschäftsregeln: LKW am Wareneingang, Radlader am Versand-Schuppen, nur Stapler in den Hallen-Gängen. Schlangen-Logik handhabt Rücken-an-Rücken-Anfahrten ohne Schwingen. Der Pförtner am Tor wird zum Ausnahme-Bearbeiter, nicht zur Vollzeit-Rolle. The gate opens — or stays closed — based on classification plus your business rules: trucks at the goods entrance, loaders at the dispatch shed, only forklifts inside the warehouse aisle. Queue logic handles back-to-back arrivals without bouncing. The manual gate operator becomes an exception handler, not a full-time role. The gate opens — or stays closed — based on classification plus your business rules: trucks at the goods entrance, loaders at the dispatch shed, only forklifts inside the warehouse aisle. Queue logic handles back-to-back arrivals without bouncing. The manual gate operator becomes an exception handler, not a full-time role. The gate opens — or stays closed — based on classification plus your business rules: trucks at the goods entrance, loaders at the dispatch shed, only forklifts inside the warehouse aisle. Queue logic handles back-to-back arrivals without bouncing. The manual gate operator becomes an exception handler, not a full-time role. The gate opens — or stays closed — based on classification plus your business rules: trucks at the goods entrance, loaders at the dispatch shed, only forklifts inside the warehouse aisle. Queue logic handles back-to-back arrivals without bouncing. The manual gate operator becomes an exception handler, not a full-time role.

In-plant traffic dashboardWerksverkehr-DashboardIn-plant traffic dashboardIn-plant traffic dashboardIn-plant traffic dashboardIn-plant traffic dashboard

Live view of which vehicles are where in the plant — gate counts, weighbridge throughput, dispatch-shed approach queue, forklift movement in the warehouse aisles. Same temporal model we use on stockpile monitoring — applied to vehicle tracks instead of material piles. Live-Sicht, welche Fahrzeuge wo im Werk sind — Tor-Zähler, Brückenwaage-Durchsatz, Versand-Schuppen-Anfahrt-Schlange, Stapler-Bewegung in den Hallen-Gängen. Dasselbe zeitliche Modell, das wir auf Halden-Monitoring einsetzen — übertragen auf Fahrzeug-Tracks statt Material-Halden. Live view of which vehicles are where in the plant — gate counts, weighbridge throughput, dispatch-shed approach queue, forklift movement in the warehouse aisles. Same temporal model we use on stockpile monitoring — applied to vehicle tracks instead of material piles. Live view of which vehicles are where in the plant — gate counts, weighbridge throughput, dispatch-shed approach queue, forklift movement in the warehouse aisles. Same temporal model we use on stockpile monitoring — applied to vehicle tracks instead of material piles. Live view of which vehicles are where in the plant — gate counts, weighbridge throughput, dispatch-shed approach queue, forklift movement in the warehouse aisles. Same temporal model we use on stockpile monitoring — applied to vehicle tracks instead of material piles. Live view of which vehicles are where in the plant — gate counts, weighbridge throughput, dispatch-shed approach queue, forklift movement in the warehouse aisles. Same temporal model we use on stockpile monitoring — applied to vehicle tracks instead of material piles.

Why customWarum CustomWhy customWhy customWhy customWhy custom

Why a custom build — not an off-the-shelf product. Warum nach Maß — und nicht von der Stange. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product. Why a custom build — not an off-the-shelf product.

Every plant has its own fleet, its own gate layout, its own existing RFID, ANPR and weighbridge infrastructure. A generic classifier solves the generic case; your case is not the generic case. Jedes Werk hat seinen eigenen Fuhrpark, sein eigenes Tor-Layout und eigene bestehende RFID-, ANPR- und Waage-Infrastruktur. Ein generischer Klassifikator löst den generischen Fall; Ihr Fall ist nicht der generische Fall. Every plant has its own fleet, its own gate layout, its own existing RFID, ANPR and weighbridge infrastructure. A generic classifier solves the generic case; your case is not the generic case. Every plant has its own fleet, its own gate layout, its own existing RFID, ANPR and weighbridge infrastructure. A generic classifier solves the generic case; your case is not the generic case. Every plant has its own fleet, its own gate layout, its own existing RFID, ANPR and weighbridge infrastructure. A generic classifier solves the generic case; your case is not the generic case. Every plant has its own fleet, its own gate layout, its own existing RFID, ANPR and weighbridge infrastructure. A generic classifier solves the generic case; your case is not the generic case.

Site-specific class libraryWerks-spezifische Klassen-BibliothekSite-specific class librarySite-specific class librarySite-specific class librarySite-specific class library

Your fleet is not the public benchmark. Your wheel loaders, your forklifts, your AGVs, your subcontractor trucks — we calibrate the model on your vehicles under your gate lighting and dust conditions, and we re-calibrate when the fleet changes or a new subcontractor comes on site. Ihr Fuhrpark ist nicht der öffentliche Benchmark. Ihre Radlader, Ihre Stapler, Ihre AGV, Ihre Subunternehmer-LKW — wir kalibrieren das Modell auf Ihren Fahrzeugen unter Ihrem Tor-Licht und Staub, und wir re-kalibrieren, wenn sich der Fuhrpark ändert oder ein neuer Subunternehmer auf dem Werk anfängt. Your fleet is not the public benchmark. Your wheel loaders, your forklifts, your AGVs, your subcontractor trucks — we calibrate the model on your vehicles under your gate lighting and dust conditions, and we re-calibrate when the fleet changes or a new subcontractor comes on site. Your fleet is not the public benchmark. Your wheel loaders, your forklifts, your AGVs, your subcontractor trucks — we calibrate the model on your vehicles under your gate lighting and dust conditions, and we re-calibrate when the fleet changes or a new subcontractor comes on site. Your fleet is not the public benchmark. Your wheel loaders, your forklifts, your AGVs, your subcontractor trucks — we calibrate the model on your vehicles under your gate lighting and dust conditions, and we re-calibrate when the fleet changes or a new subcontractor comes on site. Your fleet is not the public benchmark. Your wheel loaders, your forklifts, your AGVs, your subcontractor trucks — we calibrate the model on your vehicles under your gate lighting and dust conditions, and we re-calibrate when the fleet changes or a new subcontractor comes on site.

Retrofit-friendly — keep your existing gateRetrofit-freundlich — bestehendes Tor bleibtRetrofit-friendly — keep your existing gateRetrofit-friendly — keep your existing gateRetrofit-friendly — keep your existing gateRetrofit-friendly — keep your existing gate

We add the sensor portal next to your existing gate motor, boom barrier, RFID reader, ANPR camera and induction loop. The mechanical gate stays, the existing automation stays, the cabling stays. We add a perception layer that takes the failure cases off your plate — dirty plates, missing tags, small vehicles. Wir setzen das Sensor-Portal neben Ihren bestehenden Tor-Antrieb, Schlagbaum, RFID-Leser, ANPR-Kamera und die Induktionsschleife. Das mechanische Tor bleibt, die bestehende Automatisierung bleibt, die Verkabelung bleibt. Wir setzen eine Wahrnehmungs-Schicht obendrauf, die die Ausfälle abfängt — verschmutzte Kennzeichen, fehlende Tags, kleine Fahrzeuge. We add the sensor portal next to your existing gate motor, boom barrier, RFID reader, ANPR camera and induction loop. The mechanical gate stays, the existing automation stays, the cabling stays. We add a perception layer that takes the failure cases off your plate — dirty plates, missing tags, small vehicles. We add the sensor portal next to your existing gate motor, boom barrier, RFID reader, ANPR camera and induction loop. The mechanical gate stays, the existing automation stays, the cabling stays. We add a perception layer that takes the failure cases off your plate — dirty plates, missing tags, small vehicles. We add the sensor portal next to your existing gate motor, boom barrier, RFID reader, ANPR camera and induction loop. The mechanical gate stays, the existing automation stays, the cabling stays. We add a perception layer that takes the failure cases off your plate — dirty plates, missing tags, small vehicles. We add the sensor portal next to your existing gate motor, boom barrier, RFID reader, ANPR camera and induction loop. The mechanical gate stays, the existing automation stays, the cabling stays. We add a perception layer that takes the failure cases off your plate — dirty plates, missing tags, small vehicles.

Integrates with weighbridge, ANPR, RFID, gate PLCAnbindung an Brückenwaage, ANPR, RFID, Tor-SPSIntegrates with weighbridge, ANPR, RFID, gate PLCIntegrates with weighbridge, ANPR, RFID, gate PLCIntegrates with weighbridge, ANPR, RFID, gate PLCIntegrates with weighbridge, ANPR, RFID, gate PLC

Most plant gates already run a weighbridge controller, an RFID reader, an ANPR camera and a gate PLC. We fuse the classification output into what is already there — we do not replace your gate-management system. OPC UA, REST, MQTT, digital I/O and analog outputs all supported. Die meisten Werkstore haben bereits einen Waage-Controller, ein RFID-Lesegerät, eine ANPR-Kamera und eine Tor-SPS. Wir fusionieren die Klassifikation in das, was schon da ist — wir ersetzen Ihr Tor-Management nicht. OPC UA, REST, MQTT, digitale I/O und Analog-Ausgänge — alles unterstützt. Most plant gates already run a weighbridge controller, an RFID reader, an ANPR camera and a gate PLC. We fuse the classification output into what is already there — we do not replace your gate-management system. OPC UA, REST, MQTT, digital I/O and analog outputs all supported. Most plant gates already run a weighbridge controller, an RFID reader, an ANPR camera and a gate PLC. We fuse the classification output into what is already there — we do not replace your gate-management system. OPC UA, REST, MQTT, digital I/O and analog outputs all supported. Most plant gates already run a weighbridge controller, an RFID reader, an ANPR camera and a gate PLC. We fuse the classification output into what is already there — we do not replace your gate-management system. OPC UA, REST, MQTT, digital I/O and analog outputs all supported. Most plant gates already run a weighbridge controller, an RFID reader, an ANPR camera and a gate PLC. We fuse the classification output into what is already there — we do not replace your gate-management system. OPC UA, REST, MQTT, digital I/O and analog outputs all supported.

IP ownership + clean handoverIP-Eigentum + saubere ÜbergabeIP ownership + clean handoverIP ownership + clean handoverIP ownership + clean handoverIP ownership + clean handover

You own the source code, the model weights and the labelled dataset at handover. We document the system, train your team, and walk away clean. No black box, no monthly per-vehicle licence, no service contract you cannot exit. See our FAQs on IP and engagement model for the standard terms. Sie besitzen Quellcode, Modell-Gewichte und gelabelten Datensatz nach der Übergabe. Wir dokumentieren das System, schulen Ihr Team und gehen sauber raus. Keine Black Box, keine monatliche Pro-Fahrzeug-Lizenz, kein Servicevertrag, aus dem Sie nicht rauskommen. Standard-Bedingungen siehe unsere FAQs zu IP und Zusammenarbeits-Modell. You own the source code, the model weights and the labelled dataset at handover. We document the system, train your team, and walk away clean. No black box, no monthly per-vehicle licence, no service contract you cannot exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the model weights and the labelled dataset at handover. We document the system, train your team, and walk away clean. No black box, no monthly per-vehicle licence, no service contract you cannot exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the model weights and the labelled dataset at handover. We document the system, train your team, and walk away clean. No black box, no monthly per-vehicle licence, no service contract you cannot exit. See our FAQs on IP and engagement model for the standard terms. You own the source code, the model weights and the labelled dataset at handover. We document the system, train your team, and walk away clean. No black box, no monthly per-vehicle licence, no service contract you cannot exit. See our FAQs on IP and engagement model for the standard terms.

FAQ

Questions about vehicle gate detection AI. Fragen zur Fahrzeugerkennung am Werkstor. Questions about vehicle gate detection AI. Questions about vehicle gate detection AI. Questions about vehicle gate detection AI. Questions about vehicle gate detection AI.

The engagement-model questions we hear from every plant operator considering a custom perception build for the gate. Need something more specific to your site? Ask us. Die Fragen zum Zusammenarbeits-Modell, die wir von jedem Werks-Betreiber hören, der einen Custom-Perception-Build fürs Tor erwägt. Brauchen Sie etwas Spezifischeres zu Ihrem Standort? Sprechen Sie uns an. The engagement-model questions we hear from every plant operator considering a custom perception build for the gate. Need something more specific to your site? Ask us. The engagement-model questions we hear from every plant operator considering a custom perception build for the gate. Need something more specific to your site? Ask us. The engagement-model questions we hear from every plant operator considering a custom perception build for the gate. Need something more specific to your site? Ask us. The engagement-model questions we hear from every plant operator considering a custom perception build for the gate. Need something more specific to your site? Ask us.

Industrial Perception AIIndustrielle ObjekterkennungIndustrial 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? ＋

 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.

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? ＋

 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.

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? ＋

 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.

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? ＋

 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.
 