Comparison of Visual Trackers for Biomechanical Analysis of Running

TL;DR

This paper evaluates six human pose trackers for biomechanical analysis of sprinting, comparing their accuracy against expert annotations and proposing a post-processing method to improve joint angle estimations.

Contribution

It introduces a comprehensive framework for assessing pose trackers in sprint biomechanics and proposes a post-processing module to enhance accuracy of joint angle measurements.

Findings

Joint-based models achieve RMSE from 11.41° to 4.37°

Post-processing reduces errors to 6.99° and 3.88°

Pose tracking is promising for biomechanical analysis but needs further accuracy improvements.

Abstract

Human pose estimation has witnessed significant advancements in recent years, mainly due to the integration of deep learning models, the availability of a vast amount of data, and large computational resources. These developments have led to highly accurate body tracking systems, which have direct applications in sports analysis and performance evaluation. This work analyzes the performance of six trackers: two point trackers and four joint trackers for biomechanical analysis in sprints. The proposed framework compares the results obtained from these pose trackers with the manual annotations of biomechanical experts for more than 5870 frames. The experimental framework employs forty sprints from five professional runners, focusing on three key angles in sprint biomechanics: trunk inclination, hip flex extension, and knee flex extension. We propose a post-processing module for outlier detection and fusion prediction in the joint angles. The experimental results demonstrate that using joint-based models yields root mean squared errors ranging from 11.41{\deg} to 4.37{\deg}. When integrated with the post-processing modules, these errors can be reduced to 6.99{\deg} and 3.88{\deg}, respectively. The experimental findings suggest that human pose tracking approaches can be valuable resources for the biomechanical analysis of running. However, there is still room for improvement in applications where high accuracy is required.