CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 三维可视计算
FeaCo: Reaching Robust Feature-Level Consensus in Noisy Pose Conditions
Gu JM(谷佳铭)1,2; Jingyu Zhang3; Zhang MY(张沐阳)1,2; Meng WL(孟维亮)1,2; Xu SB(徐士彪)4; Zhang JG(张吉光)1,2; Zhang XP(张晓鹏)1,2
2023
Conference NameMM '23: Proceedings of the 31st ACM International Conference on Multimedia
Conference Date2023.10.27-2023.11.2
Conference PlaceOttawa, Canada
Abstract

Collaborative perception offers a promising solution to overcome
challenges such as occlusion and long-range data processing. However, limited sensor accuracy leads to noisy poses that misalign observations among vehicles. To address this problem, we propose the FeaCo, which achieves robust Feature-level Consensus among collaborating agents in noisy pose conditions without additional training. We design an efficient Pose-error Rectification Module (PRM) to align derived feature maps from different vehicles, reducing the adverse effect of noisy pose and bandwidth requirements. We also provide an effective multi-scale Cross-level Attention Module (CAM) to enhance information aggregation and interaction between various scales. Our FeaCo outperforms all other localization rectification methods, as validated on both the collaborative perception simulation dataset OPV2V and real-world dataset V2V4Real, reducing heading error and enhancing localization accuracy across various error levels. Our code is available at: https://github.com/jmgu0212/FeaCo.git.

Indexed BySCI
Sub direction classification目标检测、跟踪与识别
planning direction of the national heavy laboratory环境多维感知
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57361
Collection多模态人工智能系统全国重点实验室_三维可视计算
Corresponding AuthorGu JM(谷佳铭); Xu SB(徐士彪)
Affiliation1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute ofAutomation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences Beijing, China
3.Academy for Engineering and Technology, Fudan University Shanghai, China
4.School of Artificial Intelligence, Beijing University of Posts and Telecommunications Beijing, China
Recommended Citation
GB/T 7714
Gu JM,Jingyu Zhang,Zhang MY,et al. FeaCo: Reaching Robust Feature-Level Consensus in Noisy Pose Conditions[C],2023.
Files in This Item: Download All
File Name/Size DocType Version Access License
Feaco-MM-publishvers(5119KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gu JM(谷佳铭)]'s Articles
[Jingyu Zhang]'s Articles
[Zhang MY(张沐阳)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gu JM(谷佳铭)]'s Articles
[Jingyu Zhang]'s Articles
[Zhang MY(张沐阳)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gu JM(谷佳铭)]'s Articles
[Jingyu Zhang]'s Articles
[Zhang MY(张沐阳)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Feaco-MM-publishversion.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.