Biology subjects

Bilzon, J. L.

Publications and source records attributed to Bilzon, J. L..

2 recordsLinked to original sources

bioRxiv2022

The Development and Evaluation of a Fully Automated Markerless Motion Capture Workflow

This study presented a fully automated deep learning based markerless motion capture workflow and evaluated its performance against marker-based motion capture during overground running, walking and counter movement jumping. Multi-view high speed (200 Hz) image data were collected concurrently with marker-based motion capture (criterion data), permitting a direct comparison between methods. Lower limb kinematic data for 15 participants were computed using 2D pose estimation, our 3D fusion process and OpenSim based inverse kinematics modelling. Results demonstrated high levels of agreement for lower limb joint angles, with mean differences ranging between 0.1{degrees} - 10.5{degrees} for 6 DoF hip joint rotations, and 0.7{degrees} - 3.9{degrees} for knee and ankle rotations. These differences generally fall within the documented uncertainties of marker-based motion capture, suggesting that our markerless approach could be used for appropriate biomechanics applications. We used an open-source, modular and customisable workflow, allowing for integration with other popular biomechanics tools such as OpenSim. By developing open-source tools, we hope to facilitate the democratisation of markerless motion capture technology and encourage the transparent development of markerless methods. This presents exciting opportunities for biomechanics researchers and practitioners to capture large amounts of high quality, ecologically valid data both in the laboratory and in the wild.

bioengineering↗

bioRxiv2021

Human Movement Science in The Wild: Can Current Deep-Learning Based Pose Estimation Free Us from The Lab?

Human movement researchers are often restricted to laboratory environments and data capture techniques that are time and/or resource intensive. Markerless pose estimation algorithms show great potential to facilitate large scale movement studies in the wild, i.e., outside of the constraints imposed by marker-based motion capture. However, the accuracy of such algorithms has not yet been fully evaluated. We computed 3D joint centre locations using several deep-learning based pose estimation methods (OpenPose, AlphaPose, DeepLabCut) and compared to marker-based motion capture. Participants performed walking, running and jumping activities while marker-based motion capture data and multi-camera high speed images (200 Hz) were captured. The pose estimation algorithms were applied to 2D image data and 3D joint centre locations were reconstructed. Pose estimation derived joint centres demonstrated systematic differences at the hip and knee (~30 - 50 mm), most likely due to mislabeling of ground truth data in the training datasets. Where systematic differences were lower, e.g., the ankle, differences of 1 - 15 mm were observed depending on the activity. Markerless motion capture represents a highly promising emerging technology that could free movement scientists from laboratory environments. We provide recommendations relating to domain specific datasets and benchmarks, which will be vital to realising this goal.

bioengineering↗