Toward Robust LiDAR-Camera Fusion in BEV Space via Mutual Deformable Attention and Temporal Aggregation

激光雷达 计算机视觉 人工智能 计算机科学 传感器融合 点云 探测器 目标检测 稳健性(进化) 特征提取 遥感 模式识别(心理学) 电信 生物化学 化学 基因 地质学
作者
Jian Wang,Fan Li,Yi An,Xuchong Zhang,Hongbin Sun
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:34 (7): 5753-5764 被引量:53
标识
DOI:10.1109/tcsvt.2024.3366664
摘要

LiDAR and camera are two critical sensors that can provide complementary information for accurate 3D object detection. Most works are devoted to improving the detection performance of fusion models on the clean and well-collected datasets. However, the collected point clouds and images in real scenarios may be corrupted to various degrees due to potential sensor malfunctions, which greatly affects the robustness of the fusion model and poses a threat to safe deployment. In this paper, we first analyze the shortcomings of most fusion detectors, which rely mainly on the LiDAR branch, and the potential of the bird's eye-view (BEV) paradigm in dealing with partial sensor failures. Based on that, we present a robust LiDAR-camera fusion pipeline in unified BEV space with two novel designs under four typical LiDAR-camera malfunction cases. Specifically, a mutual deformable attention is proposed to dynamically model the spatial feature relationship and reduce the interference caused by the corrupted modality, and a temporal aggregation module is devised to fully utilize the rich information in the temporal domain. Together with the decoupled feature extraction for each modality and holistic BEV space fusion, the proposed detector, termed RobBEV, can work stably regardless of single-modality data corruption. Extensive experiments on the large-scale nuScenes dataset under robust settings demonstrate the effectiveness of our approach.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
wsd886发布了新的文献求助10
刚刚
眼睛大的傲菡完成签到,获得积分10
1秒前
江水完成签到,获得积分10
1秒前
歪比八不完成签到,获得积分20
1秒前
彭于晏应助xxn采纳,获得10
1秒前
奥里给完成签到,获得积分10
1秒前
glany发布了新的文献求助10
1秒前
cc发布了新的文献求助10
1秒前
2秒前
童年的秋千完成签到,获得积分10
2秒前
典雅碧空应助稳重傲柔采纳,获得10
2秒前
彩虹宇宙完成签到,获得积分10
2秒前
沐青应助科研通管家采纳,获得30
2秒前
英俊的铭应助科研通管家采纳,获得10
2秒前
2秒前
2秒前
李爱国应助科研通管家采纳,获得10
2秒前
2秒前
Crystal发布了新的文献求助10
2秒前
2秒前
2秒前
yydragen应助科研通管家采纳,获得50
2秒前
英俊的铭应助科研通管家采纳,获得10
3秒前
掉头发的小白完成签到,获得积分10
4秒前
小甑完成签到,获得积分10
4秒前
4秒前
4秒前
zhaoshao完成签到,获得积分10
5秒前
kecheng应助刻苦的安白采纳,获得20
5秒前
薏米人儿完成签到,获得积分10
5秒前
酷波er应助卫川影采纳,获得10
5秒前
Lucas应助glany采纳,获得30
6秒前
所所应助Cartes采纳,获得30
6秒前
7秒前
露露发布了新的文献求助10
7秒前
安详的曲奇完成签到,获得积分10
7秒前
8秒前
8秒前
小帆同学完成签到,获得积分10
9秒前
虚心的芹发布了新的文献求助10
9秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969322
求助须知:如何正确求助?哪些是违规求助? 3514152
关于积分的说明 11172188
捐赠科研通 3249407
什么是DOI,文献DOI怎么找? 1794832
邀请新用户注册赠送积分活动 875437
科研通“疑难数据库(出版商)”最低求助积分说明 804781