{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T10:46:44Z","timestamp":1742640404444,"version":"3.37.3"},"reference-count":30,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2018,10,17]],"date-time":"2018-10-17T00:00:00Z","timestamp":1539734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Key Research and Development Program of China","award":["2018YFB0105003"]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1762264, 51875255, U1664258, U1764257, 61601203, 61773184"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2016149"]},{"name":"Key Project for the Development of Strategic Emerging Industries of Jiangsu Province","award":["2016-1094, 2015-1084"]},{"name":"Key Research and Development Program of Zhenjiang City","award":["GY2017006"]},{"name":"Overseas Training Program for Universities of Jiangsu Province","award":["(No Number)"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"Visual-based vehicle detection has been studied extensively, however there are great challenges in certain settings. To solve this problem, this paper proposes a probabilistic framework combining a scene model with a pattern recognition method for vehicle detection by a stationary camera. A semisupervised viewpoint inference method is proposed in which five viewpoints are defined. For a specific monitoring scene, the vehicle motion pattern corresponding to road structures is obtained by using trajectory clustering through an offline procedure. Then, the possible vehicle location and the probability distribution around the viewpoint in a fixed location are calculated. For each viewpoint, the vehicle model described by a deformable part model (DPM) and a conditional random field (CRF) is learned. Scores of root and parts and their spatial configuration generated by the DPM are used to learn the CRF model. The occlusion states of vehicles are defined based on the visibility of their parts and considered as latent variables in the CRF. In the online procedure, the output of the CRF, which is considered as an adjusted vehicle detection result compared with the DPM, is combined with the probability of the apparent viewpoint in a location to give the final vehicle detection result. Quantitative experiments under a variety of traffic conditions have been contrasted to test our method. The experimental results illustrate that our method performs well and is able to deal with various vehicle viewpoints and shapes effectively. In particular, our approach performs well in complex traffic conditions with vehicle occlusion.<\/jats:p>","DOI":"10.3390\/s18103505","type":"journal-article","created":{"date-parts":[[2018,10,17]],"date-time":"2018-10-17T14:22:54Z","timestamp":1539786174000},"page":"3505","source":"Crossref","is-referenced-by-count":7,"title":["Vehicle Detection by Fusing Part Model Learning and Semantic Scene Information for Complex Urban Surveillance"],"prefix":"10.3390","volume":"18","author":[{"given":"Yingfeng","family":"Cai","sequence":"first","affiliation":[{"name":"Automotive Engineering Research Institution, Jiangsu University, Zhenjiang 212013, China"}]},{"given":"Ze","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9136-8091","authenticated-orcid":false,"given":"Hai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China"}]},{"given":"Xiaobo","family":"Chen","sequence":"additional","affiliation":[{"name":"Automotive Engineering Research Institution, Jiangsu University, Zhenjiang 212013, China"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Automotive Engineering Research Institution, Jiangsu University, Zhenjiang 212013, China"}]}],"member":"1968","published-online":{"date-parts":[[2018,10,17]]},"reference":[{"key":"ref_1","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_2","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_3","doi-asserted-by":"crossref","unstructured":"Leon, L.C., and Hirata, R. (2012, January 22\u201325). Vehicle detection using mixture of deformable parts models: Static and dynamic camera. Proceedings of the 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images, Ouro Preto, Brazil.","DOI":"10.1109\/SIBGRAPI.2012.40"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1109\/TSMCB.2005.846652","article-title":"Learning semantic scene models from observing activity in visual surveillance","volume":"35","author":"Makris","year":"2005","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Niknejad, H.T., Kawano, T., Oishi, Y., and Mita, S. (2013, January 23\u201326). Occlusion handling using discriminative model of trained part templates and conditional random field. Proceedings of the 2013 IEEE Intelligent Vehicles Symposium (IV), Gold Coast City, Australia.","DOI":"10.1109\/IVS.2013.6629557"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/TITS.2007.911357","article-title":"Real-time incremental segmentation and tracking of vehicles at low camera angles using stable features","volume":"9","author":"Kanhere","year":"2008","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/TITS.2007.902647","article-title":"A method for vehicle count in the presence of multiple-vehicle occlusions in traffic images","volume":"8","author":"Pang","year":"2007","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2453","DOI":"10.1109\/TVT.2013.2242910","article-title":"A fast evolutionary algorithm for real-time vehicle detection","volume":"62","author":"Nguyen","year":"2013","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1109\/TITS.2008.915647","article-title":"Multilevel framework to detect and handle vehicle occlusion","volume":"9","author":"Zhang","year":"2008","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_10","unstructured":"Shu, G., Dehghan, A., Oreifej, O., Hand, E., and Shah, M. (2012, January 16\u201322). Part-based multiple-person tracking with partial occlusion handling. Proceedings of the 2012 IEEE Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.neunet.2018.02.005","article-title":"Salient object detection based on multi-scale contrast","volume":"101","author":"Wang","year":"2018","journal-title":"Neural Netw."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1016\/j.patcog.2008.10.033","article-title":"A stochastic graph grammar for compositional object representation and recognition","volume":"42","author":"Lin","year":"2009","journal-title":"Pattern Recognit."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1109\/TITS.2011.2182649","article-title":"Integrating appearance and edge features for sedan vehicle detection in the blind-spot area","volume":"13","author":"Lin","year":"2012","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1109\/TITS.2013.2283302","article-title":"Rear-view vehicle detection and tracking by combining multiple parts for complex urban surveillance","volume":"15","author":"Tian","year":"2014","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/TITS.2007.908572","article-title":"Automatic vehicle detection using local features-A statistical approach","volume":"9","author":"Wang","year":"2008","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1109\/TITS.2013.2250501","article-title":"Vehicle detection based on the and-or graph for congested traffic conditions","volume":"14","author":"Li","year":"2013","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.trc.2014.10.009","article-title":"Vehicle detection based on and-or graph and hybrid image templates for complex urban traffic conditions","volume":"51","author":"Li","year":"2015","journal-title":"Transp. Res. Part C: Emerg. Technol."},{"key":"ref_18","first-page":"5013","article-title":"Saliency-based pedestrian detection in far infrared images","volume":"5","author":"Cai","year":"2017","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1109\/TITS.2012.2187894","article-title":"On-road multivehicle tracking using deformable object model and particle filter with improved likelihood estimation","volume":"13","author":"Niknejad","year":"2012","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Enzweiler, M., Eigenstetter, A., Schiele, B., and Gavrila, D.M. (2010, January 13\u201318). Multi-cue pedestrian classification with partial occlusion handling. Proceedings of the 2010 IEEE Conference on Computer vision and pattern recognition (CVPR), San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5540111"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/s11263-010-0346-6","article-title":"A numerical study of the bottom-up and top-down inference processes in and-or graphs","volume":"93","author":"Wu","year":"2011","journal-title":"Int. J. Comput. Vision"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Azizpour, H., and Laptev, I. (2012, January 7\u201313). Object detection using strongly-supervised deformable part models. Proceedings of the European Conference on Computer Vision, Florence, Italy.","DOI":"10.1007\/978-3-642-33718-5_60"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1109\/TPAMI.2013.221","article-title":"Preserving structure in model-free tracking","volume":"36","author":"Zhang","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1109\/TITS.2015.2466109","article-title":"Probabilistic Inference for Occluded and Multiview On-road Vehicle Detection","volume":"17","author":"Wang","year":"2016","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Pepikj, B., Stark, M., Gehler, P., and Schiele, B. (2013, January 23\u201328). Occlusion patterns for object class detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.422"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"9277","DOI":"10.1007\/s11042-015-3141-0","article-title":"Occluded vehicle detection with local connected deep model","volume":"75","author":"Wang","year":"2016","journal-title":"Multimedia Tools Appl."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1049\/iet-its.2014.0238","article-title":"Trajectory-based anomalous behaviour detection for intelligent traffic surveillance","volume":"9","author":"Cai","year":"2015","journal-title":"IET Intel. Transport Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/MSP.2005.1406476","article-title":"Smart video surveillance: exploring the concept of multiscale spatiotemporal tracking","volume":"22","author":"Hampapur","year":"2005","journal-title":"IEEE Signal Process Mag."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.patcog.2013.07.017","article-title":"The C-loss function for pattern classification","volume":"47","author":"Singh","year":"2014","journal-title":"Pattern Recognit."},{"key":"ref_30","unstructured":"Griffin, G., Holub, A., and Perona, P. (2007). Caltech-256 object category dataset. , California Institute of Technology, Pasadena, CA, USA, Unpublished work."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/10\/3505\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T01:24:11Z","timestamp":1736213051000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/10\/3505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,17]]},"references-count":30,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2018,10]]}},"alternative-id":["s18103505"],"URL":"https:\/\/doi.org\/10.3390\/s18103505","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2018,10,17]]}}}