Estimating skeleton-based gait abnormality index by sparse deep auto-encoder

TL;DR

This paper introduces a novel deep auto-encoder approach with sparsity constraints to automatically extract features from skeletal data for estimating gait abnormality, demonstrating promising results on a large dataset.

Contribution

It presents a new method that automatically learns gait features from skeletal data using a sparse deep auto-encoder, eliminating the need for handcrafted features.

Findings

Achieved promising results on a large skeleton dataset.

Automatically learned interpretable gait features.

Effective estimation of gait abnormality index.

Abstract

This paper proposes an approach estimating a gait abnormality index based on skeletal information provided by a depth camera. Differently from related works where the extraction of hand-crafted features is required to describe gait characteristics, our method automatically performs that stage with the support of a deep auto-encoder. In order to get visually interpretable features, we embedded a constraint of sparsity into the model. Similarly to most gait-related studies, the temporal factor is also considered as a post-processing in our system. This method provided promising results when experimenting on a dataset containing nearly one hundred thousand skeleton samples.