ADMap: Anti-disturbance framework for reconstructing online vectorized HD map
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929259016093696 |
|---|---|
| author | Hu, Haotian Wang, Fanyi Wang, Yaonong Hu, Laifeng Xu, Jingwei Zhang, Zhiwang |
| author_facet | Hu, Haotian Wang, Fanyi Wang, Yaonong Hu, Laifeng Xu, Jingwei Zhang, Zhiwang |
| contents | In the field of autonomous driving, online high-definition (HD) map reconstruction is crucial for planning tasks. Recent research has developed several high-performance HD map reconstruction models to meet this necessity. However, the point sequences within the instance vectors may be jittery or jagged due to prediction bias, which can impact subsequent tasks. Therefore, this paper proposes the Anti-disturbance Map reconstruction framework (ADMap). To mitigate point-order jitter, the framework consists of three modules: Multi-Scale Perception Neck, Instance Interactive Attention (IIA), and Vector Direction Difference Loss (VDDL). By exploring the point-order relationships between and within instances in a cascading manner, the model can monitor the point-order prediction process more effectively. ADMap achieves state-of-the-art performance on the nuScenes and Argoverse2 datasets. Extensive results demonstrate its ability to produce stable and reliable map elements in complex and changing driving scenarios. Code and more demos are available at https://github.com/hht1996ok/ADMap. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13172 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ADMap: Anti-disturbance framework for reconstructing online vectorized HD map Hu, Haotian Wang, Fanyi Wang, Yaonong Hu, Laifeng Xu, Jingwei Zhang, Zhiwang Computer Vision and Pattern Recognition In the field of autonomous driving, online high-definition (HD) map reconstruction is crucial for planning tasks. Recent research has developed several high-performance HD map reconstruction models to meet this necessity. However, the point sequences within the instance vectors may be jittery or jagged due to prediction bias, which can impact subsequent tasks. Therefore, this paper proposes the Anti-disturbance Map reconstruction framework (ADMap). To mitigate point-order jitter, the framework consists of three modules: Multi-Scale Perception Neck, Instance Interactive Attention (IIA), and Vector Direction Difference Loss (VDDL). By exploring the point-order relationships between and within instances in a cascading manner, the model can monitor the point-order prediction process more effectively. ADMap achieves state-of-the-art performance on the nuScenes and Argoverse2 datasets. Extensive results demonstrate its ability to produce stable and reliable map elements in complex and changing driving scenarios. Code and more demos are available at https://github.com/hht1996ok/ADMap. |
| title | ADMap: Anti-disturbance framework for reconstructing online vectorized HD map |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.13172 |