Gait Recognition Using 3-D Human Body Shape Inference

TL;DR

This paper introduces a novel gait recognition method that infers 3-D human body shapes from silhouettes, improving identification accuracy across various viewing angles and conditions by leveraging 3-D shape priors.

Contribution

It proposes a new approach to infer 3-D body shapes from silhouettes, enhancing gait recognition robustness against appearance variants and unseen viewpoints.

Findings

Consistent improvement on CASIA-B and OUMVLP datasets.

Effective in handling different viewing angles and clothing variations.

Enhances existing gait recognition baselines.

Abstract

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.