In a method for detecting obstacles for a rail vehicle, 3D sensor data is detected from a surrounding region, 3D image data is generated from the 3D sensor data, and 2D image data is generated on the basis of the 3D image data. A 2D anomaly mask is ascertained or generated by comparing the 2D image data with reference image data which is free of a collision obstacle. In the process, image regions are identified as mask regions in the 2D image data which differ from the corresponding image regions in the reference image data. By fusing the 2D anomaly mask with the 3D image data, a 3D anomaly mask is generated in the 3D image data. Finally, the 3D image data which is part of the 3D anomaly mask is interpreted as a possible collision obstacle. There is also described an obstacle detection device and a rail vehicle.
SELBSTLERNENDES VERFAHREN ZUR HINDERNISERKENNUNG FÜR EIN SCHIENENFAHRZEUG, HINDERNISERKENNUNGSEINRICHTUNG, UND SCHIENENFAHRZEUG MIT EINER HINDERNISERKENNUNGSEINRICHTUNG
SELF-LEARNING METHOD FOR OBSTACLE DETECTION FOR A RAIL VEHICLE, OBSTACLE DETECTION UNIT, AND RAIL VEHICLE COMPRISING AN OBSTACLE DETEION UNIT
PORCÉDÉ DE DÉTECTION D'OBSTACLES POUR VÉHICULES FERROVIAIRES À APPRENTISSAGE AUTOMATIQUE, UNITÉ DE DÉTECTION D'OBSTACLES ET VÉHICULE FERROVIAIRE COMPRENANT UNE UNITÉ DE DÉTECTION D'OBSTACLES
09.10.2024
Patent
Elektronische Ressource
Deutsch
Europäisches Patentamt | 2018
|Europäisches Patentamt | 2025
|