Logo image
Back
On Learning Disentangled Representations for Gait Recognition
Journal article   Open access   Peer reviewed

On Learning Disentangled Representations for Gait Recognition

Ziyuan Zhang, Luan Tran, Feng Liu and Xiaoming Liu
IEEE transactions on pattern analysis and machine intelligence, v 44(1), pp 345-360
01 Jan 2022
DOI: https://doi.org/10.1109/TPAMI.2020.2998790
PMID: 32750777
url
https://arxiv.org/abs/1909.03051View
Submitted Open arXiv.org - Non-exclusive license to distribute

Abstract

auto-encoder Cameras canonical representation Clothing Databases deep convolutional neural networks disentangled representation learning Face recognition Feature extraction Gait recognition Legged locomotion LSTM
Gait, the walking pattern of individuals, is one of the important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and viewing angle. To remedy this issue, we propose a novel AutoEncoder framework, GaitNet, to explicitly disentangle appearance, canonical and pose features from RGB imagery. The LSTM integrates pose features over time as a dynamic gait feature while canonical features are averaged as a static gait feature. Both of them are utilized as classification features. In addition, we collect a Frontal-View Gait (FVG) dataset to focus on gait recognition from frontal-view walking, which is a challenging problem since it contains minimal gait cues compared to other views. FVG also includes other important variations, e.g., walking speed, carrying, and clothing. With extensive experiments on CASIA-B, USF, and FVG datasets, our method demonstrates superior performance to the SOTA quantitatively, the ability of feature disentanglement qualitatively, and promising computational efficiency. We further compare our GaitNet with state-of-the-art face recognition to demonstrate the advantages of gait biometrics identification under certain scenarios, e.g., long-distance/lower resolutions, cross viewing angles. Source code is available at http://cvlab.cse.msu.edu/project-gaitnet.html .

Metrics

6 Record Views
107 citations in Web of Science
102 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
Logo image