Gait Recognition Using 3-D Human Body Shape Inference

Gait recognition, which identifies individuals based on their walking patterns, is an important biometric technique since it can be observed from a distance and does not require the subject's cooperation. Recognizing a person's gait is difficult because of the appearance variants in human silhouette sequences produced by varying viewing angles, carrying objects, and clothing. Recent research has produced a number of ways for coping with these variants. In this paper, we present the usage of inferring 3-D body shapes distilled from limited images, which are, in principle, invariant to the specified variants. Inference of 3-D shape is a difficult task, especially when only silhouettes are provided in a dataset. We provide a method for learning 3-D body inference from silhouettes by transferring knowledge from 3-D shape prior from RGB photos. We use our method on multiple existing state-of-the-art gait baselines and obtain consistent improvements for gait identification on two public datasets, CASIA-B and OUMVLP, on several variants and settings, including a new setting of novel views not seen during training.

Automated summary

Gait recognition is an important biometric technique as it can identify individuals based on walking patterns without their cooperation. However, recognizing gait is challenging due to appearance variations caused by different angles, carried objects, and clothing. This research presents the inference of 3-D body shapes from limited images to address these variations. The proposed method transfers knowledge from RGB photos to learn 3-D body inference from silhouettes and achieves consistent improvements in gait identification on multiple baselines and datasets.