Time-Frequency Analysis of Variable-Length WiFi CSI Signals for Person Re-Identification

TL;DR

This paper presents a WiFi CSI-based person re-identification method that uses a two-stream network to analyze time and frequency domain features, achieving high accuracy without relying on visual data.

Contribution

It introduces a novel two-stream network processing variable-length WiFi CSI signals for person ReID, combining time-frequency analysis and advanced learning techniques.

Findings

Achieves 93.68% mAP on real-world dataset

Achieves 98.13% Rank-1 accuracy

Utilizes multipath WiFi signals for privacy-preserving ReID

Abstract

Person re-identification (ReID), as a crucial technology in the field of security, plays an important role in security detection and people counting. Current security and monitoring systems largely rely on visual information, which may infringe on personal privacy and be susceptible to interference from pedestrian appearances and clothing in certain scenarios. Meanwhile, the widespread use of routers offers new possibilities for ReID. This letter introduces a method using WiFi Channel State Information (CSI), leveraging the multipath propagation characteristics of WiFi signals as a basis for distinguishing different pedestrian features. We propose a two-stream network structure capable of processing variable-length data, which analyzes the amplitude in the time domain and the phase in the frequency domain of WiFi signals, fuses time-frequency information through continuous lateral connections, and employs advanced objective functions for representation and metric learning. Tested on a dataset collected in the real world, our method achieves 93.68% mAP and 98.13% Rank-1.