arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.03033cs.CV
收藏

基于激光雷达的行人重识别

LiDAR-based Person Re-identification

Tsinghua University(清华大学);Beijing Institute of Technology(北京理工大学)

Wenxuan Guo, Zhiyu Pan, Yingping Liang, Ziheng Xi, Zhi Chen Zhong, Jianjiang Feng, Jie Zhou

AI总结:

针对摄像头行人重识别存在的三维信息缺失、易受环境限制及隐私问题,本文提出基于激光雷达的ReID3D框架,构建首个激光雷达行人ReID数据集LReID及模拟预训练数据集,实现94.0的rank-1准确率。

摘要:

基于摄像头的行人重识别(ReID)系统已在公共安全领域得到广泛应用。然而,摄像头通常无法感知人体的三维形态信息,且易受光照不足、背景复杂以及个人隐私等多种限制因素的影响。本文提出了一种基于激光雷达的ReID框架ReID3D,该框架采用预训练策略提取三维人体形状特征,并引入基于图的互补增强编码器来提取全面特征。由于激光雷达数据集匮乏,我们构建了首个基于激光雷达的行人重识别数据集LReID,该数据集在多个自然条件各异的室外场景中采集。此外,我们还推出了LReID-sync这一模拟行人数据集,专为通过点云补全和形状参数学习任务预训练编码器而设计。在LReID上开展的大量实验表明,ReID3D取得了卓越性能,其rank-1准确率达94.0,凸显了激光雷达在解决行人重识别任务方面的巨大潜力。据我们所知,我们是首个提出基于激光雷达的行人重识别解决方案的团队。代码和数据集将于近期发布。

英文摘要:

Camera-based person re-identification (ReID) systems have been widely applied in the field of public security. However, cameras often lack the perception of 3D morphological information of human and are susceptible to various limitations, such as inadequate illumination, complex background, and personal privacy. In this paper, we propose a LiDAR-based ReID framework, ReID3D, that utilizes pre-training strategy to retrieve features of 3D body shape and introduces Graph-based Complementary Enhancement Encoder for extracting comprehensive features. Due to the lack of LiDAR datasets, we build LReID, the first LiDAR-based person ReID dataset, which is collected in several outdoor scenes with variations in natural conditions. Additionally, we introduce LReID-sync, a simulated pedestrian dataset designed for pre-training encoders with tasks of point cloud completion and shape parameter learning. Extensive experiments on LReID show that ReID3D achieves exceptional performance with a rank-1 accuracy of 94.0, highlighting the significant potential of LiDAR in addressing person ReID tasks. To the best of our knowledge, we are the first to propose a solution for LiDAR-based ReID. The code and datasets will be released soon.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑