Comparison of Visual Trackers for Biomechanical Analysis of Running

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gomez, Luis F., Garrido-Lopez, Gonzalo, Fierrez, Julian, Morales, Aythami, Tolosana, Ruben, Rueda, Javier, Navarro, Enrique
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918012948316160
author Gomez, Luis F.
Garrido-Lopez, Gonzalo
Fierrez, Julian
Morales, Aythami
Tolosana, Ruben
Rueda, Javier
Navarro, Enrique
author_facet Gomez, Luis F.
Garrido-Lopez, Gonzalo
Fierrez, Julian
Morales, Aythami
Tolosana, Ruben
Rueda, Javier
Navarro, Enrique
contents 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° to 4.37°. When integrated with the post-processing modules, these errors can be reduced to 6.99° and 3.88°, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04713
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comparison of Visual Trackers for Biomechanical Analysis of Running
Gomez, Luis F.
Garrido-Lopez, Gonzalo
Fierrez, Julian
Morales, Aythami
Tolosana, Ruben
Rueda, Javier
Navarro, Enrique
Computer Vision and Pattern Recognition
Machine Learning
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° to 4.37°. When integrated with the post-processing modules, these errors can be reduced to 6.99° and 3.88°, 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.
title Comparison of Visual Trackers for Biomechanical Analysis of Running
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.04713