{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:19:34Z","timestamp":1773087574224,"version":"3.50.1"},"reference-count":50,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2017,3,17]],"date-time":"2017-03-17T00:00:00Z","timestamp":1489708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Due to the reasonably acceptable performance of state-of-the-art object detectors, tracking-by-detection is a standard strategy for visual multi-object tracking (MOT). In particular, online MOT is more demanding due to its diverse applications in time-critical situations. A main issue of realizing online MOT is how to associate noisy object detection results on a new frame with previously being tracked objects. In this work, we propose a multi-object tracker method called CRF-boosting which utilizes a hybrid data association method based on online hybrid boosting facilitated by a conditional random field (CRF) for establishing online MOT. For data association, learned CRF is used to generate reliable low-level tracklets and then these are used as the input of the hybrid boosting. To do so, while existing data association methods based on boosting algorithms have the necessity of training data having ground truth information to improve robustness, CRF-boosting ensures sufficient robustness without such information due to the synergetic cascaded learning procedure. Further, a hierarchical feature association framework is adopted to further improve MOT accuracy. From experimental results on public datasets, we could conclude that the benefit of proposed hybrid approach compared to the other competitive MOT systems is noticeable.<\/jats:p>","DOI":"10.3390\/s17030617","type":"journal-article","created":{"date-parts":[[2017,3,17]],"date-time":"2017-03-17T11:22:56Z","timestamp":1489749776000},"page":"617","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Conditional Random Field (CRF)-Boosting: Constructing a Robust Online Hybrid Boosting Multiple Object Tracker Facilitated by CRF Learning"],"prefix":"10.3390","volume":"17","author":[{"given":"Ehwa","family":"Yang","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6237-0141","authenticated-orcid":false,"given":"Jeonghwan","family":"Gwak","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moongu","family":"Jeon","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2017,3,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1109\/TPAMI.2007.1174","article-title":"Multicamera people tracking with a probabilistic occupancy map","volume":"30","author":"Fleuret","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1806","DOI":"10.1109\/TPAMI.2011.21","article-title":"Multiple object tracking using k-shortest paths optimization","volume":"33","author":"Berclaz","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201326). Histograms of oriented gradients for human detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Maji, S., Brox, T., and Malik, J. (2010, January 5\u201311). Detecting people using mutually consistent poselet activations. Proceedings of the 11th European Conference on Computer vision, Crete, Greece.","DOI":"10.1007\/978-3-642-15567-3_13"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object detection with discriminatively trained part based models","volume":"32","author":"Felzenszwalb","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Jiang, H., Fels, S., and Little, J.J. (2007, January 18\u201323). A linear programming approach for multiple object tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.383180"},{"key":"ref_7","unstructured":"Zhang, L., Li, Y., and Nevatia, R. (2008, January 24\u201326). Global data association for multi object tracking using network flows. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA."},{"key":"ref_8","unstructured":"Perera, A.G.A., Srinivas, C., Hoogs, A., Brooksby, G., and Hu, W. (2006, January 17\u201322). Multi-object tracking through simultaneous long occlusions and spilt-merge condition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New York, NY, USA."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yang, E., Gwak, J., and Jeon, M. (2016). Multi-human tracking using part-based appearance modelling and grouping-based tracklet association for visual surveillance applications. Multimedia Tools Appl.","DOI":"10.1007\/s11042-015-3219-8"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Milan, A., Schindler, K., and Roth, S. (2016). Multi-target tracking by discrete-continuous energy minimization. IEEE Trans. Pattern Anal. Mach. Intell.","DOI":"10.1109\/TPAMI.2015.2505309"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Dehghan, A., Assari, S.M., and Shah, M. (2015, January 8\u201310). GMMCP Tracker: Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299036"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Milan, A., Leal-Taixe, L., Schindler, K., and Reid, I. (2015, January 8\u201310). Joint Tracking and Segmentation of Multiple Targets. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299178"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chari, V., Lacoste-Julien, S., Laptev, I., and Sivic, J. (2015, January 8\u201310). On Pairwise Costs for Network Flow Multi-Object Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299193"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Tang, S., Andres, B., Andriluka, M., and Schiele, B. (2015, January 8\u201310). Subgraph Decomposition for Multi-Target Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299138"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Dehghan, A., Tian, Y., Torr, P.H.S., and Shah, M. (2015, January 8\u201310). Target Identity-aware Network Flow for Online Multiple Target Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298718"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Xu, Y., Liu, X., Liu, Y., and Zhu, S. (2016, January 27\u201330). Multi-view People Tracking via Hierarchical Trajectory Composition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Lasvegas, NV, USA.","DOI":"10.1109\/CVPR.2016.461"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yu, S., Meng, D., Zuo, W., and Hauptmann, A. (2016, January 27\u201330). The Solution Path Algorithm for Identity-Aware Multi-Object Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Lasvegas, NV, USA.","DOI":"10.1109\/CVPR.2016.420"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Milan, A., Rezatofighi, S.H., Dick, A., Schindler, K., and Reid, I. (2016). Online Multi-target Tracking using Recurrent Neural Networks. IEEE Conf. Comput. Vis. Pattern Recognit.","DOI":"10.1609\/aaai.v31i1.11194"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Alahi, A., and Savarese, S. (2015, January 10\u201318). Learning to Track: Online Multi-Object Tracking by Decision Making. Proceedings of the International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.534"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1983","DOI":"10.1109\/TPAMI.2015.2509979","article-title":"Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking","volume":"38","author":"Wen","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_21","unstructured":"Lafferty, J., McCallum, A., and Pereira, F.C.N. (July, January 28). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proceedings of the International Conference on Machine Learning, Williamstown, MA, USA."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kuo, C.H., and Nevatia, R. (2011, January 20\u201325). How does person identity recognition help multi-person tracking?. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995384"},{"key":"ref_23","first-page":"933","article-title":"An efficient boosting algorithm for combining preferences","volume":"4","author":"Freund","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., and Nevatia, R. (2009, January 20\u201325). Learning to Associate: Hybrid Boosted Multi-Target Tracker for Crowded Scene. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206735"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Milan, A., Schindler, K., and Roth, S. (2013, January 23\u201328). Detection- and trajectory-level exclusion in multiple object tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.472"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.1016\/j.cviu.2012.08.008","article-title":"Multi-target tracking on confidence maps: An application to people tracking","volume":"117","author":"Poiesi","year":"2013","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Bae, S., and Yoon, K. (2014, January 24\u201327). Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.159"},{"key":"ref_28","unstructured":"Bak, S., Chau, D., Badie, J., Corvee, E., Bremond, F., and Thonnat, M. (October, January 30). Multi-target tracking by Discriminative analysis on Riemannian Manifold. Proceedings of the IEEE International Conference on Image Processing, Orlando, FL, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.cviu.2016.07.006","article-title":"An on-line variational Bayesian model for multi-person tracking from cluttered scenes","volume":"153","author":"Ba","year":"2016","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.cviu.2016.05.012","article-title":"High-order framewise smoothness-constrained globally-optimal tracking","volume":"153","author":"Ukita","year":"2016","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/TPAMI.2013.103","article-title":"Continuous energy minimization for multitarget tracking","volume":"36","author":"Milan","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1007\/s11263-010-0381-3","article-title":"Incremental linear discriminant analysis using sufficient spanning sets and its applications","volume":"91","author":"Kim","year":"2011","journal-title":"Int. J. Comput. Vis."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Yang, B., Huang, C., and Nevatia, R. (2011, January 21\u201323). Learning Affinities and Dependencies for Multi-Target Tracking using a CRF Model. Proceedings of the IEEE Computer Vision and Pattern Recognition, Colorado Springs, CO, USA.","DOI":"10.1109\/CVPR.2011.5995587"},{"key":"ref_34","unstructured":"Yang, M., Lv, F., Xu, W., and Gong, Y. (October, January 29). Detection driven adaptive multi-cue integration for multiple human tracking. Proceedings of the IEEE International Conference on Computer Vision, Kyoto, Japan."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s11263-006-0027-7","article-title":"Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors","volume":"75","author":"Wu","year":"2007","journal-title":"Int. J. Comput. Vis."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/BF01589116","article-title":"On the limited memory BFGS method for large scale optimization","volume":"45","author":"Liu","year":"1989","journal-title":"Math. Program."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Kuo, C.-H., Huang, C., and Nevatia, R. (2010, January 13\u201318). Multi-Target Tracking by On-Line Learned Discriminative Appearance Model. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5540148"},{"key":"ref_38","unstructured":"Yang, B., and Nevatia, R. (2012, January 16\u201321). An Online Learned CRF Model for Multi-Target Tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Huang, C., Wu, B., and Nevatia, R. (2008, January 12\u201318). Robust object tracking by hierarchical association of detection responses. Proceedings of the 10th European Conference on Computer vision, Marseille, France.","DOI":"10.1007\/978-3-540-88688-4_58"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ramos, F., Fox, D., and Durrant-Whyte, H. (2007, January 27\u201330). CRF-Matching: Conditional random fields for feature-based scan matching. Proceedings of the Robotics Science and Systems, Atlanta, GA, USA.","DOI":"10.15607\/RSS.2007.III.026"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Getoor, L., and Taskar, B. (2007). Introduction to Statistical Relational Learning, MIT Press.","DOI":"10.7551\/mitpress\/7432.001.0001"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"179","DOI":"10.2307\/2987782","article-title":"Statistical Analysis of Non-lattice Data","volume":"24","author":"Besag","year":"1975","journal-title":"Statistician"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Tuzel, O., Porikli, F., and Meer, P. (2006, January 7\u201313). Region covariance: A fast descriptor for detection and classification. Proceeding of the 9th European Conference on Computer Vision, Graz, Austria.","DOI":"10.1007\/11744047_45"},{"key":"ref_44","unstructured":"CAVIAR Test Case Scenarios. Available online: http:\/\/homepages.inf.ed.ac.uk\/rbf\/CAVIARDATA1\/."},{"key":"ref_45","unstructured":"PETS 2009 Benchmark Data. Available online: http:\/\/www.cvg.rdg.ac.uk\/PETS2009\/a.html."},{"key":"ref_46","unstructured":"ETH Data. Available online: https:\/\/data.vision.ee.ethz.ch\/cvl\/aess\/dataset\/."},{"key":"ref_47","unstructured":"Wu, B., and Nevatia, R. (2006, January 17\u201322). Tracking of multiple, partially occluded humans based on static body part detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New York, NY, USA."},{"key":"ref_48","unstructured":"Yang, B., and Nevatia, R. (2012, January 16\u201321). Multi-target tracking by online learning of non-linear motion patterns and robust appearance models. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA."},{"key":"ref_49","unstructured":"Kim, S., Kwak, S., Feyereusl, J., and Kim, B.H. (2012, January 5\u20139). Online Multi-Target Tracking by Large Margin Structured Learning. Proceedings of the 11th Asian Conference on Computer Vision, Daejeon, Korea."},{"key":"ref_50","unstructured":"Goto, Y., Yamauchi, Y., and Fujiyoshi, H. (February, January 30). CS-HOG: Color similarity-based hog. Proceedings of the Korea\u2013Japan Joint Workshop on Frontiers of Computer Vision, Incheon, Korea."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/3\/617\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:30:43Z","timestamp":1760207443000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/3\/617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,17]]},"references-count":50,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2017,3]]}},"alternative-id":["s17030617"],"URL":"https:\/\/doi.org\/10.3390\/s17030617","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3,17]]}}}