TrackletGait: A Robust Framework for Gait Recognition in the Wild

TL;DR

TrackletGait introduces a robust gait recognition framework for wild scenarios, utilizing novel sampling, downsampling, and loss techniques to improve accuracy and handle occlusions and non-periodic sequences.

Contribution

The paper presents TrackletGait, a new gait recognition framework with innovative sampling, downsampling, and loss methods tailored for wild environments, achieving state-of-the-art results.

Findings

Achieves 77.8% rank-1 accuracy on Gait3D dataset.

Achieves 80.4% rank-1 accuracy on GREW dataset.

Uses only 10.3 million backbone parameters.

Abstract

Gait recognition aims to identify individuals based on their body shape and walking patterns. Though much progress has been achieved driven by deep learning, gait recognition in real-world surveillance scenarios remains quite challenging to current methods. Conventional approaches, which rely on periodic gait cycles and controlled environments, struggle with the non-periodic and occluded silhouette sequences encountered in the wild. In this paper, we propose a novel framework, TrackletGait, designed to address these challenges in the wild. We propose Random Tracklet Sampling, a generalization of existing sampling methods, which strikes a balance between robustness and representation in capturing diverse walking patterns. Next, we introduce Haar Wavelet-based Downsampling to preserve information during spatial downsampling. Finally, we present a Hardness Exclusion Triplet Loss, designed to exclude low-quality silhouettes by discarding hard triplet samples. TrackletGait achieves state-of-the-art results, with 77.8 and 80.4 rank-1 accuracy on the Gait3D and GREW datasets, respectively, while using only 10.3M backbone parameters. Extensive experiments are also conducted to further investigate the factors affecting gait recognition in the wild.