Occlusion Vehicle Segmentation Algorithm in Crowded Scene for Traffic Surveillance System
Traffic surveillance system (TSS) is an essential tool to extract necessary information (count, type, speed, etc.) from cameras for further analysis. In this issue, vehicle detection is considered one of the most important studies as it is a vital process from which modules such as vehicle tracking and classification can be built upon. However, detecting moving vehicles in urban areas is difficult because the inter-vehicle space is significantly reduced, which increases the occlusion among vehicles. This issue is more challenging in developing countries where the roads are crowded with 2-wheeled motorbikes in rush hours. This paper proposes a method to improve the occlusion vehicle detection from static surveillance cameras. The main contribution is an overlapping vehicle segmentation algorithm in which undefined blobs of occluded vehicles are examined to extract the vehicles individually based on the geometry and the ellipticity characteristics of objects’ shapes. Experiments on real-world data have shown promising results with a detection rate of 84.10% in daytime scenes.
KeywordsOcclusion detection Blob splitting Vehicle segmentation Traffic surveillance system
This research is funded by International University—Vietnam National University Ho Chi Minh City (VNU-HCM) under Grant Number SV2016-IT-05.
- 1.R. Mobus and U. Kolbe: Multi-target multi-object tracking, sensor fusion of radar and infrared. IEEE Intelligent Vehicles Symposium, pp. 732–737 (2004)Google Scholar
- 2.U. Meis, W. Ritter and H. Neumann: Detection and classification of obstacles in night vision traffic scenes based on infrared imagery. Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems, 2, 1140–1144 (2003)Google Scholar
- 3.Duong Nguyen-Ngoc Tran, Tien Phuoc Nguyen, Tai Nhu Do, and Synh Viet-Uyen Ha: Subsequent Processing of Background Modeling for Traffic Surveillance System. International Journal of Computer Theory and Engineering, vol. 8, no. 3, pp. 235–239 (2016)Google Scholar
- 4.Synh Ha, Huy Hung Nguyen, Tu Kha Huynh and Phong Ho-Thanh: Lane detection in intelligent traffic system using probabilistic model. 16th Asia Pacific Ind. Eng. Manag. Syst. Conf. (APIEMS 2015), 1856–1863 (2015)Google Scholar
- 5.Ha, S.V.-U., Pham, L.H., Phan, H.N., Ho-Thanh, P.: A robust algorithm for vehicle detection and classification in intelligent traffic system. 16th Asia Pacific Ind. Eng. Manag. Syst. Conf. (APIEMS 2015), 1832–1838 (2015)Google Scholar
- 6.Ha, S.V.-U., Pham, L.H., Tran, H.M., Ho-Thanh, P.: Improved vehicles detection & classification algorithm for traffic surveillance system. J. Inf. Assur. Secur., 9, 268–277 (2014)Google Scholar
- 7.Nguyen, T.P., Tran, D.N.-N., Huynh, T.K., Ha, S.V.-U.: Disorder detection approach to background modeling in traffic surveillance system. J. Sci. Technol. Vietnamese Acad. Sci. Technol., 52, 140–149 (2014)Google Scholar
- 8.L. H. Pham, T. T. Duong, H. M. Tran and S. V. U. Ha: Vision-based approach for urban vehicle detection & classification. 2013 Third World Congress on Information and Communication Technologies (WICT 2013), pp. 305–310, Hanoi (2013)Google Scholar
- 9.Andrew W. Fitzgibbon and Robert B. Fisher: A buyer’s guide to conic fitting. In Proceedings of the 6th British conference on Machine vision (BMVC ’95), David Pycock (Ed.). BMVA Press, Surrey, vol. 2, pp. 513–522, UK (1995)Google Scholar
- 10.Thomas M. Mitchell: Decision Tree Learning. In: Machine Learning (1 ed.), pp. 52–80. McGraw-Hill, Inc., New York, NY, USA (1997)Google Scholar
- 11.Jack Sklansky: Finding the convex hull of a simple polygon. Pattern Recognition Letters, vol. 1, pp. 79-83, ISSN 0167–8655 (1982)Google Scholar