HEATGait: Hop-Extracted Adjacency Technique in Graph Convolution based Gait Recognition

TL;DR

HEATGait introduces a hop-extraction technique in graph convolution to enhance gait recognition accuracy, addressing biases in multi-scale methods, and achieves state-of-the-art results on CASIA-B dataset.

Contribution

The paper proposes HEATGait, a novel hop-extraction method in graph convolution that improves gait feature extraction over existing multi-scale approaches.

Findings

Achieves state-of-the-art performance on CASIA-B dataset.

Effectively alleviates bias in long-range joint relationship modeling.

Utilizes ResGCN with preprocessing and augmentation for robust gait recognition.

Abstract

Biometric authentication using gait has become a promising field due to its unobtrusive nature. Recent approaches in model-based gait recognition techniques utilize spatio-temporal graphs for the elegant extraction of gait features. However, existing methods often rely on multi-scale operators for extracting long-range relationships among joints resulting in biased weighting. In this paper, we present HEATGait, a gait recognition system that improves the existing multi-scale graph convolution by efficient hop-extraction technique to alleviate the issue. Combined with preprocessing and augmentation techniques, we propose a powerful feature extractor that utilizes ResGCN to achieve state-of-the-art performance in model-based gait recognition on the CASIA-B gait dataset.