Abstract

Several deep learning-based pose estimation methods (OpenPose, AlphaPose and DeepLabCut) were bench-marked against full-body marker-based motion capture. Joint centre locations between systems were evaluated during walking, running and jumping.
Original languageEnglish
Publication statusPublished - Jul 2021
EventCongress of the International Society of Biomechanics -
Duration: 25 Jul 202129 Jul 2021
Conference number: XXVIII

Conference

ConferenceCongress of the International Society of Biomechanics
Abbreviated titleISB
Period25/07/2129/07/21

Fingerprint

Dive into the research topics of 'The Performance of Open-Source Pose Estimation Algorithms During Walking, Running and Jumping'. Together they form a unique fingerprint.

Cite this