Towards Efficient 3D Object Detection in Bird's-Eye-View Space for Autonomous Driving: A Convolutional-Only Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916426503159808 |
|---|---|
| author | Li, Yuxin Han, Qiang Yu, Mengying Jiang, Yuxin Yeo, Chaikiat Li, Yiheng Huang, Zihang Liu, Nini Chen, Hsuanhan Wu, Xiaojun |
| author_facet | Li, Yuxin Han, Qiang Yu, Mengying Jiang, Yuxin Yeo, Chaikiat Li, Yiheng Huang, Zihang Liu, Nini Chen, Hsuanhan Wu, Xiaojun |
| contents | 3D object detection in Bird's-Eye-View (BEV) space has recently emerged as a prevalent approach in the field of autonomous driving. Despite the demonstrated improvements in accuracy and velocity estimation compared to perspective view methods, the deployment of BEV-based techniques in real-world autonomous vehicles remains challenging. This is primarily due to their reliance on vision-transformer (ViT) based architectures, which introduce quadratic complexity with respect to the input resolution. To address this issue, we propose an efficient BEV-based 3D detection framework called BEVENet, which leverages a convolutional-only architectural design to circumvent the limitations of ViT models while maintaining the effectiveness of BEV-based methods. Our experiments show that BEVENet is 3$\times$ faster than contemporary state-of-the-art (SOTA) approaches on the NuScenes challenge, achieving a mean average precision (mAP) of 0.456 and a nuScenes detection score (NDS) of 0.555 on the NuScenes validation dataset, with an inference speed of 47.6 frames per second. To the best of our knowledge, this study stands as the first to achieve such significant efficiency improvements for BEV-based methods, highlighting their enhanced feasibility for real-world autonomous driving applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_00633 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Towards Efficient 3D Object Detection in Bird's-Eye-View Space for Autonomous Driving: A Convolutional-Only Approach Li, Yuxin Han, Qiang Yu, Mengying Jiang, Yuxin Yeo, Chaikiat Li, Yiheng Huang, Zihang Liu, Nini Chen, Hsuanhan Wu, Xiaojun Computer Vision and Pattern Recognition Artificial Intelligence 3D object detection in Bird's-Eye-View (BEV) space has recently emerged as a prevalent approach in the field of autonomous driving. Despite the demonstrated improvements in accuracy and velocity estimation compared to perspective view methods, the deployment of BEV-based techniques in real-world autonomous vehicles remains challenging. This is primarily due to their reliance on vision-transformer (ViT) based architectures, which introduce quadratic complexity with respect to the input resolution. To address this issue, we propose an efficient BEV-based 3D detection framework called BEVENet, which leverages a convolutional-only architectural design to circumvent the limitations of ViT models while maintaining the effectiveness of BEV-based methods. Our experiments show that BEVENet is 3$\times$ faster than contemporary state-of-the-art (SOTA) approaches on the NuScenes challenge, achieving a mean average precision (mAP) of 0.456 and a nuScenes detection score (NDS) of 0.555 on the NuScenes validation dataset, with an inference speed of 47.6 frames per second. To the best of our knowledge, this study stands as the first to achieve such significant efficiency improvements for BEV-based methods, highlighting their enhanced feasibility for real-world autonomous driving applications. |
| title | Towards Efficient 3D Object Detection in Bird's-Eye-View Space for Autonomous Driving: A Convolutional-Only Approach |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2312.00633 |