International Journal of Engineering Research in Electronics and Communication Engineering

Traffic Load Computation on Cluttered Road Scenes

Author : V.S.Harilakshmi ¹ P.Arockia Jansi Rani ²

Date of Publication :20th April 2018

Abstract: Automatic traffic load computation is an important aspect of todayâ€™s Intelligent Transportation Systems (ITSs). Computation of traffic load helps in better management of flow of traffic and thus can help in planning transportation infrastructure and related policy. Large urban areas are subjected to face a major problem of traffic congestion because of the increase in number of vehicles. Different techniques have been proposed to estimate the traffic load to combat traffic congestion. Most of the works detect the edge of vehicles and count the number of vehicles in the frame. The method of counting number of vehicles may give faulty results and inefficient in case of extremely overlapping vehicles in congested road. This paper proposes the method of calculating the traffic load levels based on the application of image processing techniques on the background segmented road patch. Traffic load levels are then estimated based on the careful investigation and mapping of the feature values. Proposed load computation algorithm based on segmentation of cluttered road scenes shows superior results when compared to the existing load computation algorithms. We measure the vehicle detection rate. This technique, based on video processing of traffic frames, result in about 71.65%, 81.13% and 84.19% of overall vehicle detection on cluttered roads. The technique proposed in this paper works well on cluttered roads at various weather conditions. The proposed load computation technique can be applied to better understand traffic patterns in unlaned, chaotic roads of developing countries

Reference :

1. Zhaoxiang Zhang, Yuqing Hou, Yunhong Wang, and Jie Qin. "A traffic flow detection system combining optical flow and shadow removal." In Intelligent Visual Surveillance (IVS), 2011 Third Chinese Conference on, pp. 45-48. IEEE, 2011.
2. S. Cheung, S. Coleri, B. Dundar, S. Ganesh, C. Tan, and P. Varaiya, "Traffic measurement and vehicle classification with a single magnetic sensor", Paper ucb-its pwp-2004-7, CA Partners for Advanced Transit & Highways, 2004.
3. I.Sikiric, K. Brkic, J. Krapac, S. Segvic, "Image Represetations on a Budget: Traffic Scene Classification in a restricted bandwidth scenario", IEEE Intelligent Vehicle Symposium, pp. 845-851, 2014.
4. Y.K. Jung, K.W. Lee, Y.S. Ho, "Content based event retrieval using semantic secene interpretation for automated traffic surveillance", IEEE Trans. on Int. Trans. Sys., vol. 2, no. 3, pp. 151-163, 2001.
5. J. Lee, A. Bovik, "Estimation and Analysis of Urban Traffic Flow", IEEE Int. Conf. On Img. Proc. (ICIP-2009), pp. 1157-1160, 2009.
6. R. E. Anderson, A. Poon, C. Lustig, W. Brunette, G. Borriello, and B. E. Kolko. Building a transportation information system using only GPS and basic SMS infrastructure. In ICTD, 2009.
7. J. Biagioni, T. Gerlich, T. Merrifield, and J. Eriksson. EasyTracker: automatic transit tracking, mapping, and arrival time prediction using smartphones. In SenSys, 2011.
8. Chomtip Pornpanomchai, Thitinut Liamsanguan, Vissakorn Vannakosit. "Vehicle Detection and Counting From a Video Frame." Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, Hong Kong, 30- 31 Aug. 2008.
9. H.S. Mohana M. Ashwathakumar G. Shivakumar. "Vehicle Detection and Counting by Using Real Time Traffic Flux through Differential Technique and Performance Evaluation." International Conference on Advanced Computer Control. Page(s): 791 – 795, 2009.