Gait Recognition via Disentangled Representation Learning

TL;DR

This paper introduces a novel autoencoder-based approach for gait recognition that explicitly disentangles pose and appearance features from RGB images, improving recognition accuracy especially in challenging frontal views.

Contribution

The paper proposes a new disentangled representation learning framework for gait recognition and introduces the FVG dataset for frontal-view gait analysis.

Findings

Outperforms state-of-the-art methods on multiple datasets

Demonstrates effective feature disentanglement qualitatively

Achieves promising computational efficiency

Abstract

Gait, the walking pattern of individuals, is one of the most important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as the gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and view angle. To remedy this issue, we propose a novel AutoEncoder framework to explicitly disentangle pose and appearance features from RGB imagery and the LSTM-based integration of pose features over time produces the gait feature. 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 state of the arts quantitatively, the ability of feature disentanglement qualitatively, and promising computational efficiency.