Assessing Performance of Aerobic Routines using Background Subtraction and Intersected Image Region

TL;DR

This paper introduces a simple image similarity measure using intersected image regions within an AR app to assess aerobic routine performance, achieving over 93% accuracy with limited data.

Contribution

It presents a novel, real-time pose assessment method using background subtraction and intersected regions in an AR setting, enhancing performance evaluation accuracy.

Findings

Pose matching accuracy of 93.67% on limited dataset

Effective real-time feedback for aerobic routines

Implementation within an AR desktop application

Abstract

It is recommended for a novice to engage a trained and experience person, i.e., a coach before starting an unfamiliar aerobic or weight routine. The coach's task is to provide real-time feedbacks to ensure that the routine is performed in a correct manner. This greatly reduces the risk of injury and maximise physical gains. We present a simple image similarity measure based on intersected image region to assess a subject's performance of an aerobic routine. The method is implemented inside an Augmented Reality (AR) desktop app that employs a single RGB camera to capture still images of the subject as he or she progresses through the routine. The background-subtracted body pose image is compared against the exemplar body pose image (i.e., AR template) at specific intervals. Based on a limited dataset, our pose matching function is reported to have an accuracy of 93.67%.