GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality
This work addresses gait recognition for biometric identification at a distance, offering a more practical end-to-end paradigm, though it is incremental as it builds on existing end-to-end methods.
The paper tackles the problem of gait recognition from RGB images by addressing gait-irrelevant noises like texture and color, proposing GaitEdge to block such information and improve performance, achieving significant outperformance on CASIA-B and TTG-200 datasets.
Gait is one of the most promising biometrics to identify individuals at a long distance. Although most previous methods have focused on recognizing the silhouettes, several end-to-end methods that extract gait features directly from RGB images perform better. However, we demonstrate that these end-to-end methods may inevitably suffer from the gait-irrelevant noises, i.e., low-level texture and colorful information. Experimentally, we design the cross-domain evaluation to support this view. In this work, we propose a novel end-to-end framework named GaitEdge which can effectively block gait-irrelevant information and release end-to-end training potential. Specifically, GaitEdge synthesizes the output of the pedestrian segmentation network and then feeds it to the subsequent recognition network, where the synthetic silhouettes consist of trainable edges of bodies and fixed interiors to limit the information that the recognition network receives. Besides, GaitAlign for aligning silhouettes is embedded into the GaitEdge without losing differentiability. Experimental results on CASIA-B and our newly built TTG-200 indicate that GaitEdge significantly outperforms the previous methods and provides a more practical end-to-end paradigm. All the source code are available at https://github.com/ShiqiYu/OpenGait.