WildGait: Learning Gait Representations from Raw Surveillance Streams
This addresses gait recognition for unconstrained environments like surveillance, offering a non-invasive biometric solution with privacy benefits, though it is incremental as it builds on existing pose-based methods.
The paper tackles the problem of gait recognition in real-world surveillance scenarios where multiple people pass a camera only once, by proposing WildGait, a weakly supervised learning framework that uses motion information from automatically annotated skeleton sequences; results show it surpasses current state-of-the-art pose-based methods with fine-tuning.
The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition require cooperative gait scenarios, in which a single person is walking multiple times in a straight line in front of a camera. We aim to address the challenges of real-world scenarios in which camera feeds capture multiple people, who in most cases pass in front of the camera only once. We address privacy concerns by using only motion information of walking individuals, with no identifiable appearance-based information. As such, we propose a novel weakly supervised learning framework, WildGait, which consists of training a Spatio-Temporal Graph Convolutional Network on a large number of automatically annotated skeleton sequences obtained from raw, real-world, surveillance streams to learn useful gait signatures. We collected the training data and compiled the largest dataset of walking skeletons called Uncooperative Wild Gait, containing over 38k tracklets of anonymized walking 2D skeletons. We release the dataset for public use. Our results show that, with fine-tuning, we surpass the current state-of-the-art pose-based gait recognition solutions. Our proposed method is reliable in training gait recognition methods in unconstrained environments, especially in settings with scarce amounts of annotated data.