Effect of a confidence-based weighted 3D point reconstruction for markerless motion capture with a reduced number of cameras

ABSTRACT

Markerless motion capture has been made available by the development of pose estimation algorithms that provide both an estimate of the location of body keypoints in two-dimensional images and its associated confidence. It seems relevant to use this additional information for three-dimensional (3D) point reconstruction. Yet, it has been little described, nor has its influence on 3D point reconstruction. Eight participants performed a manual material handling task, which was recorded by 10 video cameras. Each video was processed using OpenPose. Different 3D point reconstruction methods were compared: direct linear transform (DLT) and weighted DLT (wDLT), with 10 cameras and with a subset of 4 cameras. For each keypoint, confidence and position deviation from the 3D reconstructed point with 10 cameras projected in the image reference frame were assessed. Results suggest that using confidence information reduces both average and maximum 3D distance between 3D points reconstructed with 4 and 10 cameras.

KEYWORDS:

• Biomechanics
• direct linear transform
• confidence
• OpenPose

Disclosure statement

No potential conflict of interest was reported by the author(s).

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/21681163.2023.2292067.

Additional information

Notes on contributors

A. Chaumeil

Anaïs Chaumeil is a PhD student at Laboratory of Biomechanics and Impact Mechanics, University Gustave Eiffel, Lyon, France. Her main research interests include movement analysis and markerless motion capture.

A. Muller

Antoine Muller is an Associate Professor at Laboratory of Biomechanics and Impact Mechanics, University Lyon 1, University Gustave Eiffel, Lyon, France. His main research concerns the development of numerical tools for in situ motion analysis, with a specific focus on video-based analysis.

R. Dumas

Raphaël Dumas is a Senior Researcher at Laboratory of Biomechanics and Impact Mechanics, University Gustave Eiffel, Lyon, France. His research interest is in three-dimensional multi-body modelling of the human musculoskeletal system applied to joint pathologies, postural and gait impairments.

T. Robert

Thomas Robert received a Ph.D. degree in biomechanics from the National Institute of Applied Sciences of Lyon, France, in 2006. He is a Researcher with the Laboratory of Biomechanics and Impact Mechanics (LBMC), University Gustave Eiffel, Lyon, France. His interests include the analysis and simulation of human movement, balance maintenance and falls.