WhoFi: Deep Person Re-Identification via Wi-Fi Channel Signal Encoding

2025-07-17

AI Summary

To address the degradation of pedestrian re-identification (re-ID) performance in visual surveillance under low-light conditions, severe occlusion, and limited viewing angles, this paper proposes a novel wireless human re-ID paradigm leveraging Wi-Fi channel state information (CSI). We introduce a Transformer-based encoder for CSI sequence modeling—marking the first application of Transformers to CSI-based re-ID—and design a modular deep neural network to explicitly learn robust wireless biometric representations. Furthermore, we adopt an in-batch negative sampling loss to enhance cross-scenario identity discriminability. Extensive experiments on the NTU-Fi dataset demonstrate that our method achieves state-of-the-art performance, significantly improving re-ID accuracy under low-visibility conditions and boosting cross-scenario generalization. These results validate the effectiveness and feasibility of Wi-Fi CSI as a non-visual biometric signal source for human re-identification.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Humans and AI: Interaction Techniques and Devices
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Person Re-Identification is a key and challenging task in video surveillance. While traditional methods rely on visual data, issues like poor lighting, occlusion, and suboptimal angles often hinder performance. To address these challenges, we introduce WhoFi, a novel pipeline that utilizes Wi-Fi signals for person re-identification. Biometric features are extracted from Channel State Information (CSI) and processed through a modular Deep Neural Network (DNN) featuring a Transformer-based encoder. The network is trained using an in-batch negative loss function to learn robust and generalizable biometric signatures. Experiments on the NTU-Fi dataset show that our approach achieves competitive results compared to state-of-the-art methods, confirming its effectiveness in identifying individuals via Wi-Fi signals.

Problem

• Person Re-Identification using Wi-Fi signals instead of visual data
• Overcoming limitations like poor lighting and occlusion in surveillance
• Extracting biometric features from Wi-Fi CSI with Transformer-based DNN

Innovation

• Uses Wi-Fi signals for person re-identification
• Extracts biometric features from CSI data
• Employs Transformer-based DNN for processing