{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:17:23Z","timestamp":1760217443052,"version":"build-2065373602"},"reference-count":40,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2015,7,3]],"date-time":"2015-07-03T00:00:00Z","timestamp":1435881600000},"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>CCTV-based behavior recognition systems have gained considerable attention in recent years in the transportation surveillance domain for identifying unusual patterns, such as traffic jams, accidents, dangerous driving and other abnormal behaviors. In this paper, a novel approach for traffic behavior modeling is presented for video-based road surveillance. The proposed system combines the pachinko allocation model (PAM) and support vector machine (SVM) for a hierarchical representation and identification of traffic behavior. A background subtraction technique using Gaussian mixture models (GMMs) and an object tracking mechanism based on Kalman filters are utilized to firstly construct the object trajectories. Then, the sparse features comprising the locations and directions of the moving objects are modeled by PAMinto traffic topics, namely activities and behaviors. As a key innovation, PAM captures not only the correlation among the activities, but also among the behaviors based on the arbitrary directed acyclic graph (DAG). The SVM classifier is then utilized on top to train and recognize the traffic activity and behavior. The proposed model shows more flexibility and greater expressive power than the commonly-used latent Dirichlet allocation (LDA) approach, leading to a higher recognition accuracy in the behavior classification.<\/jats:p>","DOI":"10.3390\/s150716040","type":"journal-article","created":{"date-parts":[[2015,7,3]],"date-time":"2015-07-03T16:19:37Z","timestamp":1435940377000},"page":"16040-16059","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Traffic Behavior Recognition Using the Pachinko Allocation Model"],"prefix":"10.3390","volume":"15","author":[{"given":"Thien","family":"Huynh-The","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446-701, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oresti","family":"Banos","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446-701, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ba-Vui","family":"Le","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446-701, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinh-Mao","family":"Bui","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446-701, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongik","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department of Multimedia Science, Sookmyung's Women University, Seoul 140-742, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungyoung","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kyung Hee University, Suwon 446-701, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2015,7,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/TSMCC.2004.829274","article-title":"A survey on visual surveillance of object motion and behaviors","volume":"34","author":"Hu","year":"2004","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"10873","DOI":"10.1016\/j.eswa.2012.03.005","article-title":"A review on vision techniques applied to human behaviour analysis for ambientassisted living","volume":"39","author":"Chaaraoui","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1016\/j.cviu.2011.10.001","article-title":"A suspicious behaviour detection using a context space model for smart surveillance systems","volume":"116","author":"Wiliem","year":"2012","journal-title":"Comput. Vis. Image Und."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1109\/TASE.2008.2004965","article-title":"Detecting human behavior models from multimodal observation in a smart home","volume":"6","author":"Brdiczka","year":"2009","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s11263-006-4329-6","article-title":"Beyond tracking: Modelling activity and understanding behaviour","volume":"67","author":"Xiang","year":"2006","journal-title":"Int. J. Comput. Vis."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kermani, E., and Asemani, D. (2014). A robust adaptive algorithm of moving object detection for video surveillance. EURASIP J. Image Video Process, 2014.","DOI":"10.1186\/1687-5281-2014-27"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2309","DOI":"10.1016\/j.patcog.2007.11.024","article-title":"Activity based surveillance video content modelling","volume":"41","author":"Xiang","year":"2007","journal-title":"Pattern Recognit."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Deepak, N.A., Hariharan, R., and Sinha, U.N. (2013, January 27\u201328). Cluster based human action recognition using latent dirichlet allocation. Bengaluru, India.","DOI":"10.1109\/CCUBE.2013.6718561"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1049\/iet-cvi.2012.0121","article-title":"Body posture graph: A new graph-based posture descriptor for human behavior recognition","volume":"7","author":"Modarres","year":"2013","journal-title":"IET Comput. Vis."},{"key":"ref_10","unstructured":"Zhang, F., Guo, L., Lu, H., Gui, S., and Li, J. (2012, January 16\u201318). Star Skeleton for Human Behavior Recongition. Shanghai, China."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chakraborty, B., Rudovic, O., and Gonzalez, J. (2008, January 17\u201319). View-Invariant Human-Body Detection with Extension to Human Action Recognition using Component-Wise HMM of Body Parts. Amsterdam, The Netherlands.","DOI":"10.1109\/AFGR.2008.4813302"},{"key":"ref_12","unstructured":"Duong, T., Bui, H., Phung, D., and Venkatesh, S. (2005, January 20\u201325). Activity recognition and abnormality detection with the switching hidden semi-markov model. San Diego, CA, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, C., Han, Z., Ye, Q., and Jiao, J. (2011, January 12\u201315). Abnormal behavior detection via Sparse reconstruction analysis of trajectory. Hefei, China.","DOI":"10.1109\/ICIG.2011.104"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1109\/34.868684","article-title":"A bayesian computer vision system for modeling human interactions","volume":"22","author":"Oliver","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1109\/34.868685","article-title":"Discovery and segmentation of activities in video","volume":"22","author":"Brand","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/MCI.2012.2228597","article-title":"Video behavior analysis using topic models and rough sets (applications notes)","volume":"8","author":"Zhao","year":"2013","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liang, G., Lee, K.K., and Xu, Y. (2007, January 8\u201311). Abnormal behavior detection by multi-svm-based bayesian network. Seogwipo-si, Korea.","DOI":"10.1109\/ICIA.2007.4295746"},{"key":"ref_18","first-page":"7157","article-title":"Detection of abnormal events via Optical flow feature analysis","volume":"15","author":"Wang","year":"2015","journal-title":"Sensors"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/TITS.2009.2030963","article-title":"Understanding Transit Scenes: A Survey on Human Behavior-Recognition Algorithms","volume":"11","author":"Candamo","year":"2009","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1109\/TPAMI.2007.70731","article-title":"Video behavior profiling for anomaly detection","volume":"30","author":"Xiang","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1109\/TPAMI.2011.246","article-title":"Incremental activity modeling in multiple disjoint cameras","volume":"34","author":"Loy","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1109\/TCSVT.2012.2226526","article-title":"Detecting group activities with multi-camera context","volume":"23","author":"Zha","year":"2013","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.engappai.2013.12.010","article-title":"A method of abnormal habits recognition in intelligent space","volume":"29","author":"Huang","year":"2014","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1109\/34.946990","article-title":"Event Detection and Analysis from Video Streams","volume":"23","author":"Medioni","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","unstructured":"Zeng, Y., and Xiang, K. (February, January 30). Applying behavior recognition in road detection using vehicle sensor networks. Maui, HI, USA."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/j.imavis.2014.02.005","article-title":"A unified approach to the recognition of complex actions from sequences of zone-crossings","volume":"32","author":"Sanrom","year":"2014","journal-title":"Img. Vis. Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/TPAMI.2010.60","article-title":"An extended grammar system for learning and recognizing complex visual events","volume":"33","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/j.trc.2014.04.003","article-title":"Urban activity pattern classification using topic models from only geo-location data","volume":"33","author":"Hasan","year":"2014","journal-title":"Trans. Res. Part C"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Haines, T., and Xiang, T. (2011, January 6\u201313). Delta-dual hierarchical dirichlet processes: A pragmatic abnormal behaviour detector. Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126497"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-011-0510-7","article-title":"Video behavior mining using a dynamic topic model","volume":"98","author":"Hospedales","year":"2011","journal-title":"Int. J. Comput. Vis."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/TPAMI.2008.87","article-title":"Unsupervised activity perception in crowded and complicated scenes using hierarchical bayesian models","volume":"31","author":"Wang","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Huynh-The, T., Le, B., Lee, S., Yoon, Y., and Le-Tien, T. (2014). Using weighted dynamic range for histogram equalization to inprove the image contrast. EURASIP J. Image Video Process, 2014.","DOI":"10.1186\/1687-5281-2014-44"},{"key":"ref_33","unstructured":"Zhou, H., Zhang, Z., Gao, Y., and Yu, P. (2010, January 20\u201322). Video background subtracion using improved adaptive-k gaussian mixture model. Chengdu, China."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1709","DOI":"10.1109\/TIP.2010.2101613","article-title":"ViBe: A Universal Background Subtraction Algorithm for Video Sequences","volume":"20","author":"Barnich","year":"2011","journal-title":"IEEE Trans. Image Process"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Li, W., and McCallum, A. (2006, January 25\u201329). Pachinko allocation dag-structured mixture models of topic correlations. Pittsburgh, PA, USA.","DOI":"10.1145\/1143844.1143917"},{"key":"ref_36","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"17","author":"Blei","year":"2003","journal-title":"J. Mach. Learn Res."},{"key":"ref_37","unstructured":"Li, W., and McCallum, A. (2008). Pachinko allocation: Scalable mixture models of topic correlations. J. Mach. Learn. Res., in press."},{"key":"ref_38","first-page":"47","article-title":"Support vector machines with binary tree architecture for multi-class classification","volume":"2","author":"Cheong","year":"2004","journal-title":"Neural Info. Process.-Lett. Rev."},{"key":"ref_39","unstructured":"QMUL Junction Dataset Available online: http:\/\/www.eecs.qmul.ac.uk\/\u223cccloy\/downloads_qmul_junction.html."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1109\/TPAMI.2011.81","article-title":"Identifying rare and subtle behaviors: A weakly supervised joint topic model","volume":"33","author":"Hospedales","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/15\/7\/16040\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T20:48:44Z","timestamp":1760215724000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/15\/7\/16040"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,3]]},"references-count":40,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2015,7]]}},"alternative-id":["s150716040"],"URL":"https:\/\/doi.org\/10.3390\/s150716040","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2015,7,3]]}}}