{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:45:01Z","timestamp":1760147101379,"version":"build-2065373602"},"reference-count":21,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"German Federal Ministry of Education and Research","doi-asserted-by":"publisher","award":["16SV8580","11-76251-12-10\/19 ZN3491"],"award-info":[{"award-number":["16SV8580","11-76251-12-10\/19 ZN3491"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011937","name":"Lower Saxony Ministry of Science and Culture","doi-asserted-by":"publisher","award":["16SV8580","11-76251-12-10\/19 ZN3491"],"award-info":[{"award-number":["16SV8580","11-76251-12-10\/19 ZN3491"]}],"id":[{"id":"10.13039\/100011937","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The Azure Kinect DK is an RGB-D-camera popular in research and studies with humans. For good scientific practice, it is relevant that Azure Kinect yields consistent and reproducible results. We noticed the yielded results were inconsistent. Therefore, we examined 100 body tracking runs per processing mode provided by the Azure Kinect Body Tracking SDK on two different computers using a prerecorded video. We compared those runs with respect to spatiotemporal progression (spatial distribution of joint positions per processing mode and run), derived parameters (bone length), and differences between the computers. We found a previously undocumented converging behavior of joint positions at the start of the body tracking. Euclidean distances of joint positions varied clinically relevantly with up to 87 mm between runs for CUDA and TensorRT; CPU and DirectML had no differences on the same computer. Additionally, we found noticeable differences between two computers. Therefore, we recommend choosing the processing mode carefully, reporting the processing mode, and performing all analyses on the same computer to ensure reproducible results when using Azure Kinect and its body tracking in research. Consequently, results from previous studies with Azure Kinect should be reevaluated, and until then, their findings should be interpreted with caution.<\/jats:p>","DOI":"10.3390\/s23020878","type":"journal-article","created":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T04:29:38Z","timestamp":1673497778000},"page":"878","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["How the Processing Mode Influences Azure Kinect Body Tracking Results"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6129-0940","authenticated-orcid":false,"given":"Linda","family":"B\u00fcker","sequence":"first","affiliation":[{"name":"Assistance Systems and Medical Device Technology, Department for Health Services Research, School of Medicine and Health Sciences, Carl von Ossietzky University, Ammerl\u00e4nder Heerstra\u00dfe 114-118, 26129 Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7770-9884","authenticated-orcid":false,"given":"Vincent","family":"Quinten","sequence":"additional","affiliation":[{"name":"Assistance Systems and Medical Device Technology, Department for Health Services Research, School of Medicine and Health Sciences, Carl von Ossietzky University, Ammerl\u00e4nder Heerstra\u00dfe 114-118, 26129 Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6367-5342","authenticated-orcid":false,"given":"Michel","family":"Hackbarth","sequence":"additional","affiliation":[{"name":"Geriatric Medicine, Department for Health Services Research, School of Medicine and Health Sciences, Carl von Ossietzky University, Ammerl\u00e4nder Heerstra\u00dfe 114-118, 26129 Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1686-6752","authenticated-orcid":false,"given":"Sandra","family":"Hellmers","sequence":"additional","affiliation":[{"name":"Assistance Systems and Medical Device Technology, Department for Health Services Research, School of Medicine and Health Sciences, Carl von Ossietzky University, Ammerl\u00e4nder Heerstra\u00dfe 114-118, 26129 Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9793-3832","authenticated-orcid":false,"given":"Rebecca","family":"Diekmann","sequence":"additional","affiliation":[{"name":"Assistance Systems and Medical Device Technology, Department for Health Services Research, School of Medicine and Health Sciences, Carl von Ossietzky University, Ammerl\u00e4nder Heerstra\u00dfe 114-118, 26129 Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8846-2282","authenticated-orcid":false,"given":"Andreas","family":"Hein","sequence":"additional","affiliation":[{"name":"Assistance Systems and Medical Device Technology, Department for Health Services Research, School of Medicine and Health Sciences, Carl von Ossietzky University, Ammerl\u00e4nder Heerstra\u00dfe 114-118, 26129 Oldenburg, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.gaitpost.2022.05.021","article-title":"Comparison of Azure Kinect overground gait spatiotemporal parameters to marker based optical motion capture","volume":"96","author":"Guess","year":"2022","journal-title":"Gait Posture"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ferraris, C., Amprimo, G., Masi, G., Vismara, L., Cremascoli, R., Sinagra, S., Pettiti, G., Mauro, A., and Priano, L. (2022). Evaluation of Arm Swing Features and Asymmetry during Gait in Parkinson\u2019s Disease Using the Azure Kinect Sensor. Sensors, 22.","DOI":"10.3390\/s22166282"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Alaoui, H., Moutacalli, M.T., and Adda, M. (2020, January 9\u201311). AI-Enabled High-Level Layer for Posture Recognition Using The Azure Kinect in Unity3D. Proceedings of the 2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), Genova, Italy.","DOI":"10.1109\/IPAS50080.2020.9334945"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Sekiguchi, S., Li, L., Ko, N.Y., and Choi, W. (2021, January 12\u201315). Posture Recognition System using Depth Sensor. Proceedings of the 2021 21st International Conference on Control, Automation and Systems (ICCAS), Jeju, Korea.","DOI":"10.23919\/ICCAS52745.2021.9649849"},{"key":"ref_5","unstructured":"Microsoft Inc. (2022, July 25). Azure Kinect DK Hardware Specifications. Available online: https:\/\/docs.microsoft.com\/en-us\/azure\/Kinect-dk\/hardware-specification."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kurillo, G., Hemingway, E., Cheng, M.L., and Cheng, L. (2022). Evaluating the Accuracy of the Azure Kinect and Kinect v2. Sensors, 22.","DOI":"10.3390\/s22072469"},{"key":"ref_7","unstructured":"Microsoft Inc. (2022, March 31). Azure Kinect DK Depth Camera. Available online: https:\/\/docs.microsoft.com\/en-us\/azure\/kinect-dk\/depth-camera."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"T\u00f6lgyessy, M., Dekan, M., Chovanec, L., and Hubinsk\u00fd, P. (2021). Evaluation of the Azure Kinect and Its Comparison to Kinect V1 and Kinect V2. Sensors, 21.","DOI":"10.3390\/s21020413"},{"key":"ref_9","unstructured":"Microsoft Inc. (2022, August 29). About Azure Kinect DK|Microsoft Docs. Available online: https:\/\/docs.microsoft.com\/en-us\/azure\/kinect-dk\/about-azure-kinect-dk."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Albert, J.A., Owolabi, V., Gebel, A., Brahms, C.M., Granacher, U., and Arnrich, B. (2020). 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. Sensors, 20.","DOI":"10.3390\/s20185104"},{"key":"ref_11","unstructured":"Ma, Y., Sheng, B., Hart, R., and Zhang, Y. (2020, January 7\u201310). The validity of a dual Azure Kinect-based motion capture system for gait analysis: A preliminary study. Proceedings of the 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Auckland, New Zealand."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"T\u00f6lgyessy, M., Dekan, M., and Chovanec, L. (2021). Skeleton Tracking Accuracy and Precision Evaluation of Kinect V1, Kinect V2, and the Azure Kinect. Appl. Sci., 11.","DOI":"10.3390\/app11125756"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Romeo, L., Marani, R., Malosio, M., Perri, A.G., and D\u2019Orazio, T. (2021, January 22\u201325). Performance Analysis of Body Tracking with the Microsoft Azure Kinect. Proceedings of the 2021 29th Mediterranean Conference on Control and Automation (MED), Puglia, Italy.","DOI":"10.1109\/MED51440.2021.9480177"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.gaitpost.2021.04.005","article-title":"Effects of camera viewing angles on tracking kinematic gait patterns using Azure Kinect, Kinect v2 and Orbbec Astra Pro v2","volume":"87","author":"Yeung","year":"2021","journal-title":"Gait Posture"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Cai, L., Liu, D., and Ma, Y. (2021). Placement recommendations for single kinect-based motion capture system in unilateral dynamic motion analysis. Healthcare, 9.","DOI":"10.3390\/healthcare9081076"},{"key":"ref_16","unstructured":"Microsoft Inc. (2022, September 30). Azure Kinect DK cOordinate Systems. Available online: https:\/\/learn.microsoft.com\/en-us\/azure\/kinect-dk\/coordinate-systems."},{"key":"ref_17","unstructured":"Microsoft Inc. (2022, June 30). GitHub\u2014Microsoft\/Azure-Kinect-Samples: Samples for Azure Kinect. Available online: https:\/\/github.com\/microsoft\/Azure-Kinect-Samples."},{"key":"ref_18","unstructured":"Microsoft Inc. (2022, August 29). Azure Kinect Body Tracking Joints. Available online: https:\/\/docs.microsoft.com\/en-us\/azure\/kinect-dk\/body-joints."},{"key":"ref_19","unstructured":"Vallabha, G. (2022, March 31). PLOT_GAUSSIAN_ELLIPSOID\u2013File Exchange\u2013MATLAB Central. Available online: https:\/\/de.mathworks.com\/matlabcentral\/fileexchange\/16543-plot_gaussian_ellipsoid."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, B., Shi, W., and Miao, Z. (2015). Confidence analysis of standard deviational ellipse and its extension into higher dimensional Euclidean space. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0118537"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/978-981-15-8944-7_8","article-title":"Markerless 3D Human Pose Tracking in the Wild with Fusion of Multiple Depth Cameras: Comparative Experimental Study with Kinect 2 and 3","volume":"Volume 204","author":"Colombel","year":"2021","journal-title":"Smart Innovation, Systems and Technologies"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/878\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:04:00Z","timestamp":1760119440000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,12]]},"references-count":21,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["s23020878"],"URL":"https:\/\/doi.org\/10.3390\/s23020878","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,1,12]]}}}