Motion Gait: Gait Recognition via Motion Excitation

TL;DR

This paper introduces a novel gait recognition method that emphasizes dynamic motion features using a Motion Excitation Module and a Fine Feature Extractor, improving recognition accuracy under varying appearance conditions.

Contribution

It proposes the Motion Excitation Module (MEM) and Fine Feature Extractor (FFE) to enhance spatio-temporal feature learning for gait recognition, especially under challenging conditions.

Findings

Outperforms existing gait recognition methods on CASIA-B dataset

Effectively captures dynamic motion changes for better identification

No additional parameters introduced by the proposed modules

Abstract

Gait recognition, which can realize long-distance and contactless identification, is an important biometric technology. Recent gait recognition methods focus on learning the pattern of human movement or appearance during walking, and construct the corresponding spatio-temporal representations. However, different individuals have their own laws of movement patterns, simple spatial-temporal features are difficult to describe changes in motion of human parts, especially when confounding variables such as clothing and carrying are included, thus distinguishability of features is reduced. In this paper, we propose the Motion Excitation Module (MEM) to guide spatio-temporal features to focus on human parts with large dynamic changes, MEM learns the difference information between frames and intervals, so as to obtain the representation of temporal motion changes, it is worth mentioning that MEM can adapt to frame sequences with uncertain length, and it does not add any additional parameters. Furthermore, we present the Fine Feature Extractor (FFE), which independently learns the spatio-temporal representations of human body according to different horizontal parts of individuals. Benefiting from MEM and FFE, our method innovatively combines motion change information, significantly improving the performance of the model under cross appearance conditions. On the popular dataset CASIA-B, our proposed Motion Gait is better than the existing gait recognition methods.