Assessment of kinematic cmj data using a deep learning algorithm-based markerless motion capture system

(Bewertung kinematischer cmj-Daten mit einem auf einem tiefen Lernalgorithmus basierenden markerlosen Bewegungserfassungssystem)

The purpose of this study was to compare the performance of a video-based markerless motion capture system to a conventional marker-based approach during a counter movement jump (CMJ). Twenty-three healthy participants performed CMJ while data was collected simultaneously via a marker-based (Oqus) and a 2D video-based motion capture system (Miqus, both: Qualisys). The video data was further processed to 3D-data using Theia3D (Theia Markerless Inc.). Excellent agreement between systems with ICCs >0.99 exists for jump height (mean average error of -0.27 cm) and sagittal ankle and knee plane angles (RMSD < 5°). The hip joint showed an average RMSD of 21° with a strong correlation of 0.80. As such the markerless system is capable of detecting jump height, sagittal ankle and knee joint angles and 3D joint positions of a CMJ to a high accuracy
© Copyright 2021 ISBS Proceedings Archive (Michigan). Northern Michigan University. Veröffentlicht von International Society of Biomechanics in Sports. Alle Rechte vorbehalten.

Bibliographische Detailangaben
Schlagworte:
Notationen:Trainingswissenschaft Naturwissenschaften und Technik Ausdauersportarten
Tagging:markerless reaktiver Sprung deep learning
Veröffentlicht in:ISBS Proceedings Archive (Michigan)
Sprache:Englisch
Veröffentlicht: Canberra International Society of Biomechanics in Sports 2021
Online-Zugang:https://commons.nmu.edu/isbs/vol39/iss1/61
Jahrgang:39
Heft:1
Seiten:Article 61
Dokumentenarten:Kongressband, Tagungsbericht
Level:hoch