{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:20:30Z","timestamp":1781194830368,"version":"3.54.1"},"reference-count":36,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2022,4,20]],"date-time":"2022-04-20T00:00:00Z","timestamp":1650412800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["2003762"],"award-info":[{"award-number":["2003762"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Skeleton data, which is often used in the HCI field, is a data structure that can efficiently express human poses and gestures because it consists of 3D positions of joints. The advancement of RGB-D sensors, such as Kinect sensors, enabled the easy capture of skeleton data from depth or RGB images. However, when tracking a target with a single sensor, there is an occlusion problem causing the quality of invisible joints to be randomly degraded. As a result, multiple sensors should be used to reliably track a target in all directions over a wide range. In this paper, we proposed a new method for combining multiple inaccurate skeleton data sets obtained from multiple sensors that capture a target from different angles into a single accurate skeleton data. The proposed algorithm uses density-based spatial clustering of applications with noise (DBSCAN) to prevent noise-added inaccurate joint candidates from participating in the merging process. After merging with the inlier candidates, we used Kalman filter to denoise the tremble error of the joint\u2019s movement. We evaluated the proposed algorithm\u2019s performance using the best view as the ground truth. In addition, the results of different sizes for the DBSCAN searching area were analyzed. By applying the proposed algorithm, the joint position accuracy of the merged skeleton improved as the number of sensors increased. Furthermore, highest performance was shown when the searching area of DBSCAN was 10 cm.<\/jats:p>","DOI":"10.3390\/s22093155","type":"journal-article","created":{"date-parts":[[2022,4,21]],"date-time":"2022-04-21T03:46:11Z","timestamp":1650512771000},"page":"3155","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Markerless 3D Skeleton Tracking Algorithm by Merging Multiple Inaccurate Skeleton Data from Multiple RGB-D Sensors"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8363-3054","authenticated-orcid":false,"given":"Sang-hyub","family":"Lee","sequence":"first","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8787-5608","authenticated-orcid":false,"given":"Deok-Won","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8757-2014","authenticated-orcid":false,"given":"Kooksung","family":"Jun","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5981-2375","authenticated-orcid":false,"given":"Wonjun","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6050-6594","authenticated-orcid":false,"given":"Mun Sang","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ma, M., Proffitt, R., and Skubic, M. (2018). Validation of a Kinect V2 based rehabilitation game. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0202338"},{"key":"ref_2","first-page":"993","article-title":"Skeleton-based human activity recognition for video surveillance","volume":"6","author":"Taha","year":"2015","journal-title":"Int. J. Sci. Eng. Res."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Varshney, N., Bakariya, B., Kushwaha, A.K.S., and Khare, M. (2021). Rule-based multi-view human activity recognition system in real time using skeleton data from RGB-D sensor. Soft Comput., 241.","DOI":"10.1007\/s00500-021-05649-w"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4351435","DOI":"10.1155\/2016\/4351435","article-title":"A human activity recognition system using skeleton data from RGBD sensors","volume":"2016","author":"Cippitelli","year":"2016","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_5","unstructured":"Bari, A.H., and Gavrilova, M.L. (2019). Multi-layer perceptron architecture for kinect-based gait recognition. Computer Graphics International Conference, Springer."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yao, A., Gall, J., Fanelli, G., and Van Gool, L. (September, January 29). Does human action recognition benefit from pose estimation?. Proceedings of the 22nd British Machine Vision Conference (BMVC 2011), Dundee, Scotland.","DOI":"10.5244\/C.25.67"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Schlagenhauf, F., Sreeram, S., and Singhose, W. (2018, January 12\u201315). Comparison of kinect and vicon motion capture of upper-body joint angle tracking. Proceedings of the 2018 IEEE 14th International Conference on Control and Automation (ICCA), Anchorage, AK, USA.","DOI":"10.1109\/ICCA.2018.8444349"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shaikh, M.B., and Chai, D. (2021). RGB-D Data-based Action Recognition: A Review. Sensors, 21.","DOI":"10.20944\/preprints202101.0369.v1"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.cviu.2018.04.007","article-title":"RGB-D-based human motion recognition with deep learning: A survey","volume":"171","author":"Wang","year":"2018","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.patcog.2019.05.020","article-title":"RGB-D sensing based human action and interaction analysis: A survey","volume":"94","author":"Liu","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"T\u00f6lgyessy, M., Dekan, M., Chovanec, \u013d., 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_12","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_13","doi-asserted-by":"crossref","unstructured":"Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R., Kohli, P., Shotton, J., Hodges, S., Freeman, D., and Davison, A. (2011, January 16\u201319). KinectFusion: Real-time 3D reconstruction and interaction using a moving depth camera. Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology, Santa Barbara, CA, USA.","DOI":"10.1145\/2047196.2047270"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"T\u00f6lgyessy, M., Dekan, M., and Chovanec, \u013d. (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_15","doi-asserted-by":"crossref","unstructured":"Aguileta, A.A., Brena, R.F., Mayora, O., Molino-Minero-Re, E., and Trejo, L.A. (2019). Multi-sensor fusion for activity recognition\u2014A survey. Sensors, 19.","DOI":"10.3390\/s19173808"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.inffus.2016.09.005","article-title":"Multi-sensor fusion in body sensor networks: State-of-the-art and research challenges","volume":"35","author":"Gravina","year":"2017","journal-title":"Inf. Fusion"},{"key":"ref_17","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_18","doi-asserted-by":"crossref","first-page":"181","DOI":"10.4218\/etrij.17.2816.0045","article-title":"Motion capture of the human body using multiple depth sensors","volume":"39","author":"Kim","year":"2017","journal-title":"Etri J."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Colombel, J., Daney, D., Bonnet, V., and Charpillet, F. (2021). Markerless 3D Human Pose Tracking in the Wild with fusion of Multiple Depth Cameras: Comparative Experimental Study with Kinect 2 and 3. Activity and Behavior Computing, Springer.","DOI":"10.1007\/978-981-15-8944-7_8"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, N., Chang, Y., Liu, H., Huang, L., and Zhang, H. (2018, January 25\u201327). Human pose recognition based on skeleton fusion from multiple kinects. Proceedings of the 2018 37th Chinese Control Conference (CCC), Wuhan, China.","DOI":"10.23919\/ChiCC.2018.8483016"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4249","DOI":"10.1007\/s11042-016-3759-6","article-title":"Real-time human body tracking based on data fusion from multiple RGB-D sensors","volume":"76","author":"Cabido","year":"2017","journal-title":"Multimed. Tools Appl."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wu, Y., Gao, L., Hoermann, S., and Lindeman, R.W. (2018, January 5\u20137). Towards robust 3D skeleton tracking using data fusion from multiple depth sensors. Proceedings of the 2018 10th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games), Wurzburg, Germany.","DOI":"10.1109\/VS-Games.2018.8493443"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Desai, K., Prabhakaran, B., and Raghuraman, S. (2018, January 12\u201315). Combining skeletal poses for 3D human model generation using multiple Kinects. Proceedings of the 9th ACM Multimedia Systems Conference, Amsterdam, The Netherlands.","DOI":"10.1145\/3204949.3204958"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"65","DOI":"10.5772\/62415","article-title":"Multiple kinect sensor fusion for human skeleton tracking using Kalman filtering","volume":"13","author":"Moon","year":"2016","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, H., He, X., and Liu, Y. (2020, January 14\u201316). A Human Skeleton Data Optimization Algorithm for Multi-Kinect. Proceedings of the 2020 Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC), Dalian, China.","DOI":"10.1109\/IPEC49694.2020.9115142"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/s13673-020-00256-4","article-title":"Multiple Kinect based system to monitor and analyze key performance indicators of physical training","volume":"10","author":"Ryselis","year":"2020","journal-title":"Hum. Cent. Comput. Inf. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Swain, M.J., and Ballard, D.H. (1992). Indexing via color histograms. Active Perception and Robot Vision, Springer.","DOI":"10.1007\/978-3-642-77225-2_13"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"1981","journal-title":"Commun. ACM"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gower, J.C., and Dijksterhuis, G.B. (2004). Procrustes Problems, Oxford University Press on Demand.","DOI":"10.1093\/acprof:oso\/9780198510581.001.0001"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1109\/TPAMI.1987.4767965","article-title":"Least-squares fitting of two 3-D point sets","volume":"PAMI-9","author":"Arun","year":"1987","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.patcog.2015.09.023","article-title":"Generation of fiducial marker dictionaries using mixed integer linear programming","volume":"51","year":"2016","journal-title":"Pattern Recognit."},{"key":"ref_32","unstructured":"Ester, M., Kriegel, H.-P., Sander, J., and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Kdd, 1996, AAAI."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Haller, E., Scarlat, G., Mocanu, I., and Tr\u0103sc\u0103u, M. (2013). Human activity recognition based on multiple Kinects. International Competition on Evaluating AAL Systems through Competitive Benchmarking, Springer.","DOI":"10.1007\/978-3-642-41043-7_5"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kalman","year":"1960","journal-title":"J. Basic Eng."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1109\/JSEN.2018.2876624","article-title":"Influence of a marker-based motion capture system on the performance of Microsoft Kinect v2 skeleton algorithm","volume":"19","author":"Naeemabadi","year":"2018","journal-title":"IEEE Sens. J."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Naeemabadi, M., Dinesen, B., Andersen, O.K., and Hansen, J. (2018). Investigating the impact of a motion capture system on Microsoft Kinect v2 recordings: A caution for using the technologies together. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0204052"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/9\/3155\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:57:37Z","timestamp":1760137057000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/9\/3155"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,20]]},"references-count":36,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["s22093155"],"URL":"https:\/\/doi.org\/10.3390\/s22093155","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,20]]}}}