Person Re-identification in 3D Space: A WiFi Vision-based Approach
Person Re-identification in 3D Space: A WiFi Vision-based Approach
复制标题
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Ren;J. Yang
中科院分区：
文献类型：
--
作者：
Ren;J. Yang
人员重新识别 (Re-ID) 变得越来越重要，因为它支持广泛的安全应用。传统的行人重识别主要依赖于基于光学摄像头的系统，由于人的外观、遮挡和人体姿势的变化，该系统存在一些局限性。在这项工作中，我们提出了一种基于 WiFi 视觉的系统 3D-ID，用于 3D 空间中的人员重新识别。我们的系统利用 WiFi 和深度学习的进步来帮助 WiFi 设备“看到”、识别和识别人。特别是，我们利用下一代 WiFi 设备上的多个天线和信号反射的 2D AoA 估计，使 WiFi 能够可视化物理环境中的人。然后，我们利用深度学习将人的可视化数字化为 3D 身体表示，并提取静态身体形状和动态行走模式以进行人重新识别。我们在各种室内环境下的评估结果表明，3D-ID系统的整体Rank-1精度达到85。 3%。结果还表明我们的系统能够抵抗各种攻击。因此，所提出的 3D-ID 非常有前途，因为它可以增强或补充基于摄像头的系统。
Person re-identification (Re-ID) has become increasingly important as it supports a wide range of security applications. Traditional person Re-ID mainly relies on optical camera-based systems, which incur several limitations due to the changes in the appearance of people, occlusions, and human poses. In this work, we propose a WiFi vision-based system, 3D-ID, for person Re-ID in 3D space. Our system leverages the advances of WiFi and deep learning to help WiFi devices “see”, identify, and recognize people. In particular, we leverage multiple antennas on next-generation WiFi devices and 2D AoA estimation of the signal reflections to enable WiFi to visualize a person in the physical environment. We then leverage deep learning to digitize the visualization of the person into 3D body representation and extract both the static body shape and dynamic walking patterns for person Re-ID. Our evaluation results under various indoor environments show that the 3D-ID system achieves an overall rank-1 accuracy of 85 . 3%. Results also show that our system is resistant to various attacks. The proposed 3D-ID is thus very promising as it could augment or complement camera-based systems.