Saved in:
Bibliographic Details
Main Authors: Zhang, Zhengbin, Wu, Yan, Zhang, Hongkun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.00740
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912357496651776
author Zhang, Zhengbin
Wu, Yan
Zhang, Hongkun
author_facet Zhang, Zhengbin
Wu, Yan
Zhang, Hongkun
contents Collaborative perception has the potential to significantly enhance perceptual accuracy through the sharing of complementary information among agents. However, real-world collaborative perception faces persistent challenges, particularly in balancing perception performance and bandwidth limitations, as well as coping with localization errors. To address these challenges, we propose Fast2comm, a prior knowledge-based collaborative perception framework. Specifically, (1)we propose a prior-supervised confidence feature generation method, that effectively distinguishes foreground from background by producing highly discriminative confidence features; (2)we propose GT Bounding Box-based spatial prior feature selection strategy to ensure that only the most informative prior-knowledge features are selected and shared, thereby minimizing background noise and optimizing bandwidth efficiency while enhancing adaptability to localization inaccuracies; (3)we decouple the feature fusion strategies between model training and testing phases, enabling dynamic bandwidth adaptation. To comprehensively validate our framework, we conduct extensive experiments on both real-world and simulated datasets. The results demonstrate the superior performance of our model and highlight the necessity of the proposed methods. Our code is available at https://github.com/Zhangzhengbin-TJ/Fast2comm.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00740
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast2comm:Collaborative perception combined with prior knowledge
Zhang, Zhengbin
Wu, Yan
Zhang, Hongkun
Computer Vision and Pattern Recognition
Multiagent Systems
Collaborative perception has the potential to significantly enhance perceptual accuracy through the sharing of complementary information among agents. However, real-world collaborative perception faces persistent challenges, particularly in balancing perception performance and bandwidth limitations, as well as coping with localization errors. To address these challenges, we propose Fast2comm, a prior knowledge-based collaborative perception framework. Specifically, (1)we propose a prior-supervised confidence feature generation method, that effectively distinguishes foreground from background by producing highly discriminative confidence features; (2)we propose GT Bounding Box-based spatial prior feature selection strategy to ensure that only the most informative prior-knowledge features are selected and shared, thereby minimizing background noise and optimizing bandwidth efficiency while enhancing adaptability to localization inaccuracies; (3)we decouple the feature fusion strategies between model training and testing phases, enabling dynamic bandwidth adaptation. To comprehensively validate our framework, we conduct extensive experiments on both real-world and simulated datasets. The results demonstrate the superior performance of our model and highlight the necessity of the proposed methods. Our code is available at https://github.com/Zhangzhengbin-TJ/Fast2comm.
title Fast2comm:Collaborative perception combined with prior knowledge
topic Computer Vision and Pattern Recognition
Multiagent Systems
url https://arxiv.org/abs/2505.00740