V2X-BGN: Camera-based V2X-Collaborative 3D Object Detection with BEV Global Non-Maximum Suppression | |
Zhang Caiji2,3; Tian Bin2,3; Meng Shi2,3; Qi Shuangying1; Sun Yang5; Ai Yunfeng2; Chen Long3,4 | |
2024-04 | |
会议日期 | June 2-5, 2024 |
会议地点 | Jeju Island, South Korea |
关键词 | V2X |
英文摘要 | In recent years, research on Vehicle-to-Everything (V2X) collaborative perception algorithms mainly focuses on the fusion of intermediate features from LiDAR point clouds. Since the emergence of excellent single-vehicle visual perception mod els like BEVFormer, collaborative perception schemes based on camera and late-fusion have become feasible approaches. This paper proposes a V2X-collaborative 3D object detection structure in Bird’s Eye View (BEV) space, based on global non-maximum suppression and late-fusion (V2X-BGN), and conducts experiments on the V2X-Set dataset. Focusing on complex road conditions with extreme occlusion, the paper compares the camera-based algorithm with the LiDAR-based algorithm, validating the effectiveness of pure visual solutions in the collaborative 3D object detection task. Additionally, this paper highlights the complementary potential of camera-based and LiDAR-based approaches and the importance of object to-ego vehicle distance in the collaborative 3D object detection task. |
会议录出版者 | IEEE |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57597] ![]() |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Tian Bin |
作者单位 | 1.Chongqing Iron and Steel Group Mining Co., Ltd. 2.University of Chinese Academy of Sciences(UCAS) 3.Institute of Automation, Chinese Academy of Sciences 4.Waytous 5.Hebei University of Engineering, School of Mechanical and Equipment Engineering |
推荐引用方式 GB/T 7714 | Zhang Caiji,Tian Bin,Meng Shi,et al. V2X-BGN: Camera-based V2X-Collaborative 3D Object Detection with BEV Global Non-Maximum Suppression[C]. 见:. Jeju Island, South Korea. June 2-5, 2024. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论