Verfahren und System für Aktives Lernen in Automatisierten Fahrzeugen auf Basis von Rahmenbewertungen

Details

Veröffentlichungs-Nr.

EP4734072

Anmeldetag

23. Oktober 2024

Veröffentlichung

29. April 2026

Rechtsraum

EP

Abstract

The present disclosure relates to enabling active learning for object classification by an automotive vision system configured to perform visual perception tasks, based on which a vehicle is configured to perform at least one driving automation system feature. The automotive vision system determines one or more 3D bounding boxes and a corresponding object class within three-dimensional sets of automotive sensor data, which including at least one automotive camera frame, i.e. two-dimensional data, while a secondary vision system determines one or more 2D bounding box vectors for each automotive camera frame. Based at least on the one or more 2D bounding box vectors, a frame score is calculated for each automotive camera frame. Then, one or more automotive camera frames are provided to an oracle based on the corresponding frame scores. The oracle returns annotated camera frames, which may then be used to retrain the automotive vision system.

Anmelder

Firma

Bayerische Motoren Werke Aktiengesellschaft

Land

🇩🇪 Deutschland