Estimating skeleton-based gait abnormality index by sparse deep auto-encoder
This work addresses gait analysis for medical or rehabilitation applications, but it is incremental as it builds on existing deep learning methods with added sparsity constraints.
The paper tackles the problem of estimating gait abnormality from skeleton data by automatically extracting features using a sparse deep auto-encoder, eliminating the need for hand-crafted features, and reports promising results on a dataset of nearly 100,000 skeleton samples.
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.