Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2404.11127 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917642375266304 |
|---|---|
| author | Zhao, Jiaxing Zheng, Peng Ma, Rui |
| author_facet | Zhao, Jiaxing Zheng, Peng Ma, Rui |
| contents | Creating large LiDAR datasets with pixel-level labeling poses significant challenges. While numerous data augmentation methods have been developed to reduce the reliance on manual labeling, these methods predominantly focus on static scenes and they overlook the importance of data augmentation for dynamic scenes, which is critical for autonomous driving. To address this issue, we propose D-Aug, a LiDAR data augmentation method tailored for augmenting dynamic scenes. D-Aug extracts objects and inserts them into dynamic scenes, considering the continuity of these objects across consecutive frames. For seamless insertion into dynamic scenes, we propose a reference-guided method that involves dynamic collision detection and rotation alignment. Additionally, we present a pixel-level road identification strategy to efficiently determine suitable insertion positions. We validated our method using the nuScenes dataset with various 3D detection and tracking methods. Comparative experiments demonstrate the superiority of D-Aug. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11127 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | D-Aug: Enhancing Data Augmentation for Dynamic LiDAR Scenes Zhao, Jiaxing Zheng, Peng Ma, Rui Computer Vision and Pattern Recognition I.4.3 Creating large LiDAR datasets with pixel-level labeling poses significant challenges. While numerous data augmentation methods have been developed to reduce the reliance on manual labeling, these methods predominantly focus on static scenes and they overlook the importance of data augmentation for dynamic scenes, which is critical for autonomous driving. To address this issue, we propose D-Aug, a LiDAR data augmentation method tailored for augmenting dynamic scenes. D-Aug extracts objects and inserts them into dynamic scenes, considering the continuity of these objects across consecutive frames. For seamless insertion into dynamic scenes, we propose a reference-guided method that involves dynamic collision detection and rotation alignment. Additionally, we present a pixel-level road identification strategy to efficiently determine suitable insertion positions. We validated our method using the nuScenes dataset with various 3D detection and tracking methods. Comparative experiments demonstrate the superiority of D-Aug. |
| title | D-Aug: Enhancing Data Augmentation for Dynamic LiDAR Scenes |
| topic | Computer Vision and Pattern Recognition I.4.3 |
| url | https://arxiv.org/abs/2404.11127 |