{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:50:19Z","timestamp":1771613419849,"version":"3.50.1"},"reference-count":56,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2014,7,7]],"date-time":"2014-07-07T00:00:00Z","timestamp":1404691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Hand tracking in video is an increasingly popular research field due to the rise of novel human-computer interaction methods. However, robust and real-time hand tracking in unconstrained environments remains a challenging task due to the high number of degrees of freedom and the non-rigid character of the human hand. In this paper, we propose an unsupervised method to automatically learn the context in which a hand is embedded. This context includes the arm and any other object that coherently moves along with the hand. We introduce two novel methods to incorporate this context information into a probabilistic tracking framework, and introduce a simple yet effective solution to estimate the position of the arm. Finally, we show that our method greatly increases robustness against occlusion and cluttered background, without degrading tracking performance if no contextual information is available. The proposed real-time algorithm is shown to outperform the current state-of-the-art by evaluating it on three publicly available video datasets. Furthermore, a novel dataset is created and made publicly available for the research community.<\/jats:p>","DOI":"10.3390\/s140712023","type":"journal-article","created":{"date-parts":[[2014,7,7]],"date-time":"2014-07-07T11:00:56Z","timestamp":1404730856000},"page":"12023-12058","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Robust Arm and Hand Tracking by Unsupervised Context Learning"],"prefix":"10.3390","volume":"14","author":[{"given":"Vincent","family":"Spruyt","sequence":"first","affiliation":[{"name":"Cosys lab, Antwerp University, Paardenmarkt 92, 2000 Antwerp, Belgium"},{"name":"Image Processing and Interpretation, iMinds, Ghent University, St-Pietersnieuwstraat 41, 9000 Ghent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Ledda","sequence":"additional","affiliation":[{"name":"Cosys lab, Antwerp University, Paardenmarkt 92, 2000 Antwerp, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wilfried","family":"Philips","sequence":"additional","affiliation":[{"name":"Image Processing and Interpretation, iMinds, Ghent University, St-Pietersnieuwstraat 41, 9000 Ghent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2014,7,7]]},"reference":[{"key":"ref_1","unstructured":"ElKoura, G., and Singh, K. (2003, January 26\u201327). Handrix: Animating the human hand. Aire-la-Ville, Switzerland."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1889\/JSID20.4.180","article-title":"Tracking, recognition, and distance detection of hand gestures for a 3-D interactive display","volume":"20","author":"Huang","year":"2012","journal-title":"J. Soc. Inform. Display"},{"key":"ref_3","unstructured":"K\u00f6lsch, M., and Turk, M. (2004, January 17\u201319). Robust Hand Detection. Seoul, Korea."},{"key":"ref_4","unstructured":"Ong, E.J., and Bowden, R. (2004, January 17\u201319). A boosted classifier tree for hand shape detection. Seoul, Korea."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Stenger, B. (2006, January 13\u201316). Template-Based hand pose recognition using multiple cues. Hyderabad, India.","DOI":"10.1007\/11612704_55"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Asaari, M., and Suandi, S. (2010, January 29). Hand gesture tracking system using Adaptive Kalman Filter. Cairo, Egypt.","DOI":"10.1109\/ISDA.2010.5687273"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Bao, P.T., Binh, N.T., and Khoa, T.D. (2009, January 14\u201316). A New Approach to Hand Tracking and Gesture Recognition by a New Feature Type and HMM. Tianjin, China.","DOI":"10.1109\/FSKD.2009.276"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Donoser, M., and Bischof, H. (2008, January 8\u201311). Real time appearance based hand tracking. Tampa, FL, USA.","DOI":"10.1109\/ICPR.2008.4761485"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1007\/978-3-642-17691-3_27","article-title":"An Appearance-Based Prior for Hand Tracking","volume":"6475","year":"2010","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1958","DOI":"10.1016\/j.patcog.2006.12.012","article-title":"Real-time hand tracking using a mean shift embedded particle filter","volume":"40","author":"Shan","year":"2007","journal-title":"Pattern Recogn."},{"key":"ref_11","first-page":"1","article-title":"Dynamic approach for real-time skin detection","volume":"7","author":"Bilal","year":"2012","journal-title":"J. Real-Time Image Process."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Dawod, A., Abdullah, J., and Alam, M. (2010, January 5\u20138). Adaptive skin color model for hand segmentation. Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICCAIE.2010.5735129"},{"key":"ref_13","unstructured":"Soriano, M., Martinkauppi, B., Huovinen, S., and Laaksonen, M. (2000, January 3\u20137). Skin detection in video under changing illumination conditions. Barcelona, Spain."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Spruyt, V., Ledda, A., and Geerts, S. (2010, January 26\u201329). Real-time multi-colourspace hand segmentation. Hong Kong, China.","DOI":"10.1109\/ICIP.2010.5653220"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Spruyt, V., Ledda, A., and Philips, W. (2012, January 30). Real-time hand tracking by invariant hough forest detection. Orlando, FL, USA.","DOI":"10.1109\/ICIP.2012.6466817"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Spruyt, V., Ledda, A., and Philips, W. (2013, January 15\u201318). Real-time, long-term hand tracking with unsupervised initialization. Melbourne, Australia.","DOI":"10.1109\/ICIP.2013.6738769"},{"key":"ref_17","unstructured":"Stefanov, N., Galata, A., and Hubbold, R. (2005, January 21\u201323). Real-Time Hand Tracking With Variable-Length Markov Models of Behaviour. San Diego, CA, USA."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Metaxas, D., Tsechpenakis, G., Li, Z., Huang, Y., and Kanaujia, A. (2006, January 28\u201331). Dynamically Adaptive Tracking of Gestures and Facial Expressions. Reading, UK.","DOI":"10.1007\/11758532_73"},{"key":"ref_19","unstructured":"Goncalves, L., di Bernardo, E., Ursella, E., and Perona, P. (1995, January 20\u201323). Monocular tracking of the human arm in 3D. Cambridge, MA, USA."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Arpit Mittal, A.Z., and Torr, P. (2011, January 2). Hand detection using multiple proposals. Dundee, UK.","DOI":"10.5244\/C.25.75"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1023\/A:1023052124951","article-title":"Contextual Priming for Object Detection","volume":"53","author":"Torralba","year":"2003","journal-title":"Int. J. Comput. Vision"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kalal, Z., Matas, J., and Mikolajczyk, K. (2010, January 13\u201318). P-N learning: Bootstrapping binary classifiers by structural constraints. San Francisco CA, USA.","DOI":"10.1109\/CVPR.2010.5540231"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1109\/TPAMI.2011.239","article-title":"Tracking-Learning-Detection","volume":"34","author":"Kalal","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cerman, L., Matas, J., and Hlav\u00e1\u010d, V. (2009, January 15\u201318). Sputnik Tracker: Having a Companion Improves Robustness of the Tracker. Oslo, Norway.","DOI":"10.1007\/978-3-642-02230-2_30"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Grabner, H., Matas, J., Van Gool, L., and Cattin, P. (2010, January 13\u201318). Tracking the invisible: Learning where the object might be. San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5539819"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Spruyt, V., Ledda, A., and Philips, W. (2013, January 15\u201319). Sparse optical flow regularization for real-time visual tracking. San Jose, CA, USA.","DOI":"10.1109\/ICME.2013.6607495"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Lovegrove, S.J., and Davison, A.J. (2011, January 3\u201316). DTAM: Dense tracking and mapping in real-time. Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Sundaram, N., Brox, T., and Keutzer, K. (2010, January 11). Dense point trajectories by GPU-accelerated large displacement optical flow. Crete, Greece.","DOI":"10.1007\/978-3-642-15549-9_32"},{"key":"ref_29","first-page":"886","article-title":"Histograms of Oriented Gradients for Human Detection","volume":"1","author":"Dalal","year":"2005","journal-title":"Comput. Vision Pattern Recognit."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive Image Features from Scale-Invariant Keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vision"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., and Gool, L.V. (2006, January 7\u201313). Surf: Speeded up robust features. Graz, Austria.","DOI":"10.1007\/11744023_32"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, H., Ullah, M.M., Kl\u00e4ser, A., Laptev, I., and Schmid, C. (2009, January 7\u201310). Evaluation of local spatio-temporal features for action recognition. London, UK.","DOI":"10.5244\/C.23.124"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","article-title":"Robust Real-time Object Detection","volume":"57","author":"Viola","year":"2004","journal-title":"Int. J. Comput. Vision"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/0031-3203(95)00067-4","article-title":"A comparative study of texture measures with classification based on featured distributions","volume":"29","author":"Ojala","year":"1996","journal-title":"J. Pattern Recognit."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/j.patcog.2008.08.014","article-title":"Description of interest regions with local binary patterns","volume":"42","author":"Schmid","year":"2009","journal-title":"J. Pattern Recognit."},{"key":"ref_36","unstructured":"Jones, M., and Rehg, J. (1999, January 23\u201325). Statistical color models with application to skin detection. Ft. Collins, CO, USA."},{"key":"ref_37","unstructured":"Valentini, G. (2003). [Ensemble Methods Based on Bias-Variance Analysis. Ph.D. Thesis, Dipartimento di Informatica e Scienze dell]."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"J. Mach. Learning"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Saffari, A., Leistner, C., Santner, J., Godec, M., and Bischof, H. (2009, January 27). On-Line Random Forests. Kyoto, Japan.","DOI":"10.1109\/ICCVW.2009.5457447"},{"key":"ref_40","first-page":"15","article-title":"Fast Template Matching","volume":"Volume 95","author":"Lewis","year":"1995","journal-title":"Vision Interface 1984"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Belgacem, S., Chatelain, C., Ben-Hamadou, A., and Paquet, T. (2012, January 24\u201326). Hand tracking using optical-flow embedded particle filter in sign language scenes. Warsaw, Poland.","DOI":"10.1007\/978-3-642-33564-8_35"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1007\/978-3-642-15986-2_16","article-title":"Tracking People in Broadcast Sports","volume":"6376","author":"Yao","year":"2010","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Isard, M., and Blake, A. (1998, January 2\u20136). ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework, Freiburg, Germany.","DOI":"10.1007\/BFb0055711"},{"key":"ref_44","unstructured":"Van der Merwe, R., de Freitas, N., Doucet, A., and Wan, E. (2000). Advances in Neural Information Processing Systems (NIPS13), MIT Press."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Julier, S. (2002, January 8\u201310). The scaled unscented transformation. Anchorage, AK, USA.","DOI":"10.1109\/ACC.2002.1025369"},{"key":"ref_46","unstructured":"Mosabbeb, E.A., Sadeghi, M., and Fathy, M. (2007, January 26\u201328). A New Approach for Vehicle Detection in Congested Traffic Scenes Based on Strong Shadow Segmentation. Lake Tahoe, NV, USA."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"MacCormick, J., and Isard, M. (2000, January 26). Partitioned Sampling, Articulated Objects, Interface-Quality Hand Tracking. Dublin, Ireland.","DOI":"10.1007\/3-540-45053-X_1"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The Pascal Visual Object Classes (VOC) Challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vision"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1007\/s11263-012-0524-9","article-title":"2d articulated human pose estimation and retrieval in (almost) unconstrained still images","volume":"99","author":"Eichner","year":"2012","journal-title":"Int. J. Comput. Vision"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Exner, D., Bruns, E., Kurz, D., Grundhofer, A., and Bimber, O. (2010, January 13\u201318). Fast and robust CAMShift tracking. San Francisco, CA, USA.","DOI":"10.1109\/CVPRW.2010.5543787"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Kwon, J., and Lee, K.M. (2009, January 20\u201325). Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive Basin Hopping Monte Carlo sampling. Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206502"},{"key":"ref_52","unstructured":"Adam, A., Rivlin, E., and Shimshoni, I. (2006, January 17\u201322). Robust Fragments-based Tracking using the Integral Histogram. New York, NY, USA."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1007\/s11263-011-0480-9","article-title":"Upper Body Detection and Tracking in Extended Signing Sequences","volume":"95","author":"Buehler","year":"2011","journal-title":"Int. J. Comput. Vision"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Karlinsky, L., Dinerstein, M., Harari, D., and Ullman, S. (2010, January 13\u201318). The chains model for detecting parts by their context. San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5540232"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Buehler, P., Everingham, M., Huttenlocher, D.P., and Zisserman, A. (2008, January 1\u20134). Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts. Leeds, UK.","DOI":"10.5244\/C.22.110"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Kumar, M., Zisserman, A., and Torr, P.H.S. (2009, January 27). Efficient discriminative learning of parts-based models. Kyoto, Japan.","DOI":"10.1109\/ICCV.2009.5459192"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/14\/7\/12023\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:13:22Z","timestamp":1760217202000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/14\/7\/12023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7,7]]},"references-count":56,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2014,7]]}},"alternative-id":["s140712023"],"URL":"https:\/\/doi.org\/10.3390\/s140712023","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,7]]}}}