Abstract
Quality assurance in research helps to ensure reliability and comparable results within a study. This includes reliable measurement equipment and data-processing. The Azure Kinect DK is a popular sensor used in studies with human subjects that tracks numerous joint positions with the Azure Kinect Body Tracking SDK. Prior experiments in literature indicate that light might influence the results of the body tracking. As similar light conditions are not always given in study protocols, the impact needs to be analyzed to ensure comparable results. We ran two experiments, one with four different light conditions and one with repeated measures of similar light conditions, and compared the results by calculating the random error of depth measurement, the mean distance error of the detected joint positions, and the distance between left and right ankle. The results showed that recordings with similar light conditions produce comparable results, with a maximum difference in the median value of mean distance error of 0.06 mm, while different light conditions result in inconsistent outcomes with a difference in the median value of mean distance error of up to 0.35 mm. Therefore, light might have an influence on the Azure Kinect and its body tracking. Especially additional infrared light appears to have a negative impact on the results. Therefore, we recommend recording various videos in a study under similar light conditions whenever possible, and avoiding additional sources of infrared light.
Funder
Bundesministerium für Bildung und Forschung
Deutsche Forschungsgemeinschaft
Volkswagen Foundation
Publisher
Public Library of Science (PLoS)
Reference25 articles.
1. Sentinel fall presenting to the emergency department (SeFallED) - protocol of a complex study including long-term observation of functional trajectories after a fall, exploration of specific fall risk factors, and patients’ views on falls prevention;T Stuckenschneider;BMC geriatrics,2022
2. A systematic review of the applications of markerless motion capture (MMC) technology for clinical measurement in rehabilitation;WW Lam;Journal of NeuroEngineering and Rehabilitation,2023
3. Ma Y, Sheng B, Hart R, Zhang Y. The validity of a dual Azure Kinect-based motion capture system for gait analysis: a preliminary study. In: 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC); 2020. p. 1201–1206.
4. Agreement between Azure Kinect and Marker-Based Motion Analysis during Functional Movements: A Feasibility Study;S Jo;Sensors,2022
5. Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard: A Pilot Study;JA Albert;Sensors,2020
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献