Interpretable Gait Recognition by Granger Causality

TL;DR

This paper introduces an interpretable gait recognition method using graphical Granger causal inference to model joint interactions in human gait, providing a discriminative and visually interpretable feature representation.

Contribution

It proposes a novel GGM-based approach for gait recognition that captures joint interactions as causal graphs, enhancing interpretability and classification performance.

Findings

GGM effectively detects discriminative joint interactions.

Total norm and Ky-Fan 1-norm are optimal distance metrics for GGM.

GGM outperforms related interpretable models in classification accuracy.

Abstract

Which joint interactions in the human gait cycle can be used as biometric characteristics? Most current methods on gait recognition suffer from the lack of interpretability. We propose an interpretable feature representation of gait sequences by the graphical Granger causal inference. Gait sequence of a person in the standardized motion capture format, constituting a set of 3D joint spatial trajectories, is envisaged as a causal system of joints interacting in time. We apply the graphical Granger model (GGM) to obtain the so-called Granger causal graph among joints as a discriminative and visually interpretable representation of a person's gait. We evaluate eleven distance functions in the GGM feature space by established classification and class-separability evaluation metrics. Our experiments indicate that, depending on the metric, the most appropriate distance functions for the GGM are the total norm distance and the Ky-Fan 1-norm distance. Experiments also show that the GGM is able to detect the most discriminative joint interactions and that it outperforms five related interpretable models in correct classification rate and in Davies-Bouldin index. The proposed GGM model can serve as a complementary tool for gait analysis in kinesiology or for gait recognition in video surveillance.