{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:41:56Z","timestamp":1784227316908,"version":"3.55.0"},"reference-count":24,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2019,10,22]],"date-time":"2019-10-22T00:00:00Z","timestamp":1571702400000},"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>Automatic vehicle detection and counting are considered vital in improving traffic control and management. This work presents an effective algorithm for vehicle detection and counting in complex traffic scenes by combining both convolution neural network (CNN) and the optical flow feature tracking-based methods. In this algorithm, both the detection and tracking procedures have been linked together to get robust feature points that are updated regularly every fixed number of frames. The proposed algorithm detects moving vehicles based on a background subtraction method using CNN. Then, the vehicle\u2019s robust features are refined and clustered by motion feature points analysis using a combined technique between KLT tracker and K-means clustering. Finally, an efficient strategy is presented using the detected and tracked points information to assign each vehicle label with its corresponding one in the vehicle\u2019s trajectories and truly counted it. The proposed method is evaluated on videos representing challenging environments, and the experimental results showed an average detection and counting precision of 96.3% and 96.8%, respectively, which outperforms other existing approaches.<\/jats:p>","DOI":"10.3390\/s19204588","type":"journal-article","created":{"date-parts":[[2019,10,23]],"date-time":"2019-10-23T11:46:59Z","timestamp":1571831219000},"page":"4588","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":62,"title":["Robust Vehicle Detection and Counting Algorithm Employing a Convolution Neural Network and Optical Flow"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0130-9088","authenticated-orcid":false,"given":"Ahmed","family":"Gomaa","sequence":"first","affiliation":[{"name":"School of Electronics, Communication and Computer Engineering (ECCE), Egypt-Japan University of Science and Technology, Alexandria 21934, Egypt"},{"name":"Graduate School of Information Science and Electrical Engineering, Kyushu University, 744, Motooka, Nishi-ku, Fukuoka 819-0395, Japan"},{"name":"National Research Institute of Astronomy and Geophysics (NRIAG), Helwan 11731, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moataz M.","family":"Abdelwahab","sequence":"additional","affiliation":[{"name":"School of Electronics, Communication and Computer Engineering (ECCE), Egypt-Japan University of Science and Technology, Alexandria 21934, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Abo-Zahhad","sequence":"additional","affiliation":[{"name":"School of Electronics, Communication and Computer Engineering (ECCE), Egypt-Japan University of Science and Technology, Alexandria 21934, Egypt"},{"name":"Electrical and Electronics Engineering Department, Faculty of Engineering, Assiut University, Assiut 71511, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsubasa","family":"Minematsu","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Electrical Engineering, Kyushu University, 744, Motooka, Nishi-ku, Fukuoka 819-0395, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rin-ichiro","family":"Taniguchi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Electrical Engineering, Kyushu University, 744, Motooka, Nishi-ku, Fukuoka 819-0395, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,10,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.imavis.2017.09.008","article-title":"Vehicle detection in intelligent transportation systems and its applications under varying environments: A review","volume":"69","author":"Yang","year":"2018","journal-title":"Image Vis. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Lou, L., Zhang, J., Xiong, Y., and Jin, Y. (2019). A Novel Vehicle Detection Method Based on the Fusion of Radio Received Signal Strength and Geomagnetism. Sensors, 19.","DOI":"10.3390\/s19010058"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yu, Z., and Zhu, L. (2018). Foreground detection with deeply learned multi-scale spatial-temporal features. Sensors, 18.","DOI":"10.3390\/s18124269"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yu, T., Yang, J., and Lu, W. (2019). Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background. Algorithms, 12.","DOI":"10.3390\/a12070128"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1109\/TITS.2011.2174358","article-title":"Adaptive multicue background subtraction for robust vehicle counting and classification","volume":"13","author":"Unzueta","year":"2011","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.patcog.2008.07.015","article-title":"Front-view vehicle detection by Markov chain Monte Carlo method","volume":"42","author":"Jia","year":"2009","journal-title":"Pattern Recognit."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1109\/TIP.2007.891147","article-title":"Vehicle detection using normalized color and edge map","volume":"16","author":"Tsai","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"19654","DOI":"10.1109\/ACCESS.2018.2825229","article-title":"Road Object Detection Using a Disparity-Based Fusion Model","volume":"6","author":"Chen","year":"2018","journal-title":"IEEE Access"},{"key":"ref_9","unstructured":"Stauffer, C., and Grimson, W.E.L. (1999, January 23\u201325). Adaptive background mixture models for real-time tracking. Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), Fort Collins, CO, USA."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1049\/iet-its.2015.0157","article-title":"Vehicle detection, counting and classification in various conditions","volume":"10","author":"Kamkar","year":"2016","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Maddalena, L., and Petrosino, A. (2018). Background subtraction for moving object detection in rgbd data: A survey. J. Imaging, 4.","DOI":"10.3390\/jimaging4050071"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.cviu.2016.02.009","article-title":"COROLA: A sequential solution to moving object detection using low-rank approximation","volume":"146","author":"Shakeri","year":"2016","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1049\/iet-its.2017.0047","article-title":"Real-time vehicle detection and counting in complex traffic scenes using background subtraction model with low-rank decomposition","volume":"12","author":"Yang","year":"2017","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Quesada, J., and Rodriguez, P. (2016, January 25\u201328). Automatic vehicle counting method based on principal component pursuit background modeling. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.","DOI":"10.1109\/ICIP.2016.7533075"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1049\/el.2018.6719","article-title":"Fast approach for efficient vehicle counting","volume":"55","author":"Abdelwahab","year":"2018","journal-title":"Electron. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Braham, M., and Van Droogenbroeck, M. (2016, January 23\u201325). Deep background subtraction with scene-specific convolutional neural networks. Proceedings of the 2016 IEEE International Conference on Systems, Signals and Image Processing (IWSSIP), Bratislava, Slovakia.","DOI":"10.1109\/IWSSIP.2016.7502717"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Minematsu, T., Shimada, A., Uchiyama, H., and Taniguchi, R.I. (2018). Analytics of deep neural network-based background subtraction. J. Imaging, 4.","DOI":"10.3390\/jimaging4060078"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"890","DOI":"10.1109\/TITS.2016.2595526","article-title":"Real-time bidirectional traffic flow parameter estimation from aerial videos","volume":"18","author":"Ke","year":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_19","first-page":"4","article-title":"Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm","volume":"5","author":"Bouguet","year":"2001","journal-title":"Intel Corp."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"59143","DOI":"10.1109\/ACCESS.2019.2914961","article-title":"A Comprehensive Survey of Video Datasets for Background Subtraction","volume":"7","author":"Kalsotra","year":"2019","journal-title":"IEEE Access"},{"key":"ref_21","unstructured":"Sheorey, S., Keshavamurthy, S., Yu, H., Nguyen, H., and Taylor, C.N. (2014). Uncertainty estimation for KLT tracking. Asian Conference on Computer Vision, Springer."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1109\/TPAMI.2008.57","article-title":"Framework for performance evaluation of face, text, and vehicle detection and tracking in video: Data, metrics, and protocol","volume":"31","author":"Kasturi","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Guerrero-G\u00f3mez-Olmedo, R., L\u00f3pez-Sastre, R.J., Maldonado-Basc\u00f3n, S., and Fern\u00e1ndez-Caballero, A. (2013). Vehicle tracking by simultaneous detection and viewpoint estimation. International Work-Conference on the Interplay Between Natural and Artificial Computation, Springer.","DOI":"10.1007\/978-3-642-38622-0_32"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, Y., Jodoin, P.M., Porikli, F., Konrad, J., Benezeth, Y., and Ishwar, P. (2014, January 24\u201327). CDnet 2014: An expanded change detection benchmark dataset. Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA.","DOI":"10.1109\/CVPRW.2014.126"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/20\/4588\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:28:21Z","timestamp":1760189301000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/20\/4588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,22]]},"references-count":24,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2019,10]]}},"alternative-id":["s19204588"],"URL":"https:\/\/doi.org\/10.3390\/s19204588","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,22]]}}}