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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Avola, Danilo, Emam, Emad, Montagnini, Dario, Pannone, Daniele, Ranaldi, Amedeo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915424922238976
author Avola, Danilo
Emam, Emad
Montagnini, Dario
Pannone, Daniele
Ranaldi, Amedeo
author_facet Avola, Danilo
Emam, Emad
Montagnini, Dario
Pannone, Daniele
Ranaldi, Amedeo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12869
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WhoFi: Deep Person Re-Identification via Wi-Fi Channel Signal Encoding
Avola, Danilo
Emam, Emad
Montagnini, Dario
Pannone, Daniele
Ranaldi, Amedeo
Computer Vision and Pattern Recognition
Machine Learning
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.
title WhoFi: Deep Person Re-Identification via Wi-Fi Channel Signal Encoding
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2507.12869