Deep Generic Dynamic Object Detection Based on Dynamic Grid Maps
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913554230149120 |
|---|---|
| author | Yan, Rujiao Schubert, Linda Kamm, Alexander Komar, Matthias Schreier, Matthias |
| author_facet | Yan, Rujiao Schubert, Linda Kamm, Alexander Komar, Matthias Schreier, Matthias |
| contents | This paper describes a method to detect generic dynamic objects for automated driving. First, a LiDAR-based dynamic grid is generated online. Second, a deep learning-based detector is trained on the dynamic grid to infer the presence of dynamic objects of any type, which is a prerequisite for safe automated vehicles in arbitrary, edge-case scenarios. The Rotation-equivariant Detector (ReDet) - originally designed for oriented object detection on aerial images - was chosen due to its high detection performance. Experiments are conducted based on real sensor data and the benefits in comparison to classic dynamic cell clustering strategies are highlighted. The false positive object detection rate is strongly reduced by the proposed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14799 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Generic Dynamic Object Detection Based on Dynamic Grid Maps Yan, Rujiao Schubert, Linda Kamm, Alexander Komar, Matthias Schreier, Matthias Computer Vision and Pattern Recognition Artificial Intelligence This paper describes a method to detect generic dynamic objects for automated driving. First, a LiDAR-based dynamic grid is generated online. Second, a deep learning-based detector is trained on the dynamic grid to infer the presence of dynamic objects of any type, which is a prerequisite for safe automated vehicles in arbitrary, edge-case scenarios. The Rotation-equivariant Detector (ReDet) - originally designed for oriented object detection on aerial images - was chosen due to its high detection performance. Experiments are conducted based on real sensor data and the benefits in comparison to classic dynamic cell clustering strategies are highlighted. The false positive object detection rate is strongly reduced by the proposed approach. |
| title | Deep Generic Dynamic Object Detection Based on Dynamic Grid Maps |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2410.14799 |