The traffic congestion classification framework which contains daytime and nighttime modules is proposed in this thesis. Through analyzing the traffic surveillance videos, our frameworks are able to recognize the traffic congestion level. The information of traffic congestion is useful for drivers to avoid traffic jam and for intelligent mobile devices to plan other alternate routes immediately.
In daytime module, an initialization procedure is used to obtain the consistent information of roadway, and the traffic congestion classification based on three traffic parameters are estimated from traffic surveillance video. During initialization procedure, automatic roadway detection, bidirectional roadway analysis and virtual detector installation methods are proposed to overcome the unbalanced traffic flow and roadway-type limitations in previous works. In addition, due to the use of virtual detectors, simplified procedure of vehicle tracking for traffic parameters estimation not only significantly reduces the cost caused by other complex algorithm, but also solves the difficulty of vehicle tracking in the complicated environment.
In nighttime module, we propose a vehicle detection method based on headlights detection and grouping, and the virtual detection line is employed to evaluate the traffic congestion. Headlights are extracted by using three strong features including luminance, color variation, and shape rather than just using luminance in earlier researches. Then not only the distance but also the edge feature between two headlight candidates are utilized to reveal the correlation of a pair of headlights. Consequently, vehicles are detected from the headlights according to the correlations. By calculating the frequency that vehicles touch the virtual detection line, the traffic congestion can be classified in real time.
74
As the approaches described above, we can enhance the ability of the traffic congestion evaluation in more complicated environment, such as a large number of vehicles and vehicle occlusions resulting from too low installation of a camera.
Besides, the computational complexity is reduced to achieve the requirement of real-time response. The performance of the proposed framework is examined in videos with different surveillance scene and traffic congestion levels. We obtain the 89.2%
and 95.4% accuracies of traffic congestion classification in daytime and nighttime surveillance videos, respectively.
In the future, once the traffic congestion level is classified instantly from surveillance camera, our frameworks can provide a sequence of patterns that represents the congestion condition for further traffic jam prediction with advanced data mining knowledge. Moreover, there are no strong features at the back of vehicle, so the traffic congestion evaluation for outgoing direction needs further investigations.
75
Bibliography
[1] G. Wang, D. Xiao, and J. Gu, “Review on vehicle detection based on video for traffic surveillance,” in IEEE International Conference on Automation and Logistics, Qingdao, China, 2008, pp. 2961-2966.
[2] B. Li and Q.-mei Chen, “Framework for Freeway Auto-Surveillance from Traffic Video,” in WRI World Congress on Computer Science and Information Engineering, Los Angeles, CA, USA, 2009, vol. 6, pp. 360-365.
[3] B. Yu and A. K. Jain, “Lane boundary detection using a multiresolution Hough transform,” in International Conference on Image Processing, Santa Barbara, CA , USA, 1997, vol. 2, pp. 748-751.
[4] A. H. S. Lai and N. H. C. Yung, “Lane detection by orientation and length discrimination,” IEEE Transactions on Systems, Man, and Cybernetics, Part B:
Cybernetics, vol. 30, no. 4, pp. 539-548, Aug. 2000.
[5] B. D. Stewart, I. Reading, M. S. Thomson, T. D. Binnie, K. W. Dickinson, and C. L. Wan, “Adaptive lane finding in road traffic image analysis,” in International Conference on Road Traffic Monitoring and Control, London , UK, 1994, pp. 133-136.
[6] S. Pumrin and D. J. Dailey, “Roadside camera motion detection for automated speed measurement,” in IEEE 5th International Conference on Intelligent Transportation Systems, 2002, pp. 147- 151.
[7] W. Lee and B. Ran, “Bidirectional roadway detection for traffic surveillance using online CCTV videos,” in IEEE International Conference on Intelligent Transportation Systems Conference, Toronto, Ont., 2006, pp. 1556-1561.
[8] A. Yilmaz, O. Javed, and M. Shah, “Object Tracking: A Survey,” Journal of ACM Computing Surveys, vol. 38, no. 4, 2006.
[9] M. Piccardi, “Background subtraction techniques: a review,” in IEEE International Conference on Systems, Man and Cybernetics, 2004, vol. 4, pp.
3099- 3104.
[10] B. P. L. Lo and S. A. Velastin, “Automatic congestion detection system for underground platforms,” in Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, Hong Kong , China, 2001, pp. 158-161.
[11] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, “Detecting Moving Objects, Ghosts, and Shadows in Video Streams,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 10, pp. 1337-1342, 2003.
[12] B. Chen, Y. Lei, and W. Li, “A novel background model for real-time vehicle detection,” in 7th International Conference on Signal Processing, 2004, vol. 2,
76
pp. 1276- 1279.
[13] C. Wren, A. Azarbayejani, T. Darrell, and A. Pentland, “Real-time tracking of the human body,” in IEEE International Conference on Automatic Face and Gesture Recognition, 1996, pp. 51-56.
[14] C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, CO , USA, 1999, vol. 2.
[15] A. Elgammal, D. Harwood, and L. Davis, “Non-parametric model for background subtraction,” in Proceedings of the 6th European Conference on Computer Vision-Part II, 2000, pp. 751-767.
[16] S. Zhang, H. Yao, and S. Liu, “Spatial-temporal nonparametric background subtraction in dynamic scenes,” in IEEE International Conference on Multimedia and Expo, New York, NY, USA, 2009, pp. 518-521.
[17] O. Javed and M. Shah, “Tracking and Object Classification for Automated Surveillance,” in Proceedings of the 7th European Conference on Computer Vision-Part IV, London, UK, 2002, pp. 343-357.
[18] J. M. Wang, Y. C. Chung, C. L. Chang, and S. W. Chen, “Shadow detection and removal for traffic images,” in IEEE International Conference on Networking, Sensing and Control, 2004, vol. 1, pp. 649-654.
[19] X. Song, Y. Ding, J. Gen, and Y. Chen, “Shadow Removal of Vehicles in a Video System Based on RGB Chroma Model,” in International Conference on Computer Science and Software Engineering, Wuhan, China, 2008, pp. 977-980.
[20] H. Liu, J. Li, Q. Liu, and Y. Qian, “Shadow Elimination in Traffic Video Segmentation,” in IAPR Conference on Machine Vision Applications, Tokyo, 2007.
[21] A. Yoneyama, C.-H. Yeh, and C. C. J. Kuo, “Robust Vehicle and Traffic Information Extraction for Highway Surveillance,” EURASIP Journal on Advances in Signal Processing, no. 14, pp. 2305-2321, 2005.
[22] S.-Y. Chien, Y.-W. Huang, B.-Y. Hsieh, S.-Y. Ma, and L.-G. Chen, “Fast video segmentation algorithm with shadow cancellation, global motion compensation, and adaptive threshold techniques,” IEEE Transactions on Multimedia, vol. 6, no.
5, pp. 732-748, Oct. 2004.
[23] J.-W. Hsieh, S.-H. Yu, Y.-S. Chen, and W.-F. Hu, “A Shadow Elimination Method for Vehicle Analysis,” in International Conference on Pattern Recognition, Washington, DC, USA, 2004, pp. 372-375.
[24] L. Xie, G. Zhu, Y. Wang, H. Xu, and Z. Zhang, “Robust vehicle extraction in video-based intelligent transportation systems,” in Visual Communications and Image Processing, 2005.
77
[25] T. J. Broida and R. Chellappa, “Estimation of object motion parameters from noisy images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, pp. 90–99, Jan. 1986.
[26] G. Kitagawa, “Non-Gaussian State-Space Modeling of Nonstationary Time Series,” Journal of the American Statistical Association, vol. 82, no. 400, pp.
1032-1041, Dec. 1987.
[27] X. Chen and C. Zhang, “An Interactive Semantic Video Mining and Retrieval Platform–Application in Transportation Surveillance Video for Incident Detection,” in Proceedings of the Sixth International Conference on Data Mining, Washington, DC, USA, 2006, pp. 129–138.
[28] Y. Zou, G. Shi, H. Shi, and Y. Wang, “Image Sequences Based Traffic Incident Detection for Signaled Intersections Using HMM,” in International Conference on Hybrid Intelligent Systems, Shenyang, China, 2009, vol. 1, pp. 257-261.
[29] Y. Yue, “A Traffic-Flow Parameters Evaluation Approach Based on Urban Road Video,” International Journal of Intelligent Engineering and System, vol. 2, 2009.
[30] L. Li, L. Chen, X. Huang, and J. Huang, “A Traffic Congestion Estimation Approach from Video Using Time-Spatial Imagery,” in International Conference on Intelligent Networks and Intelligent Systems, Wuhan, China, 2008, pp. 465-469.
[31] T. B. L., C.-Y. Lin, and S. J.R., “Real-time video surveillance for traffic monitoring using virtual line analysis,” IEEE International Conference on Multimedia and Expo, vol. 2, pp. 541- 544, 2002.
[32] Liu Anan, “Video Vehicle Detection Algorithm based on Virtual-Line Group,”
in IEEE Asia Pacific Conference on Circuits and Systems, Singapore, 2006, pp.
1148-1151.
[33] J. Wu, Z. Yang, J. Wu, and A. Liu, “Virtual Line Group Based Video Vehicle Detection Algorithm Utilizing Both Luminance and Chrominance,” in IEEE Conference on Industrial Electronics and Applications, Harbin, China, 2007, pp.
2854-2858.
[34] M. S. Sayed and J. Delva, “Low Complexity Contrast Enhancement Algorithm for Nighttime Visual Surveillance,” in International Conference on Intelligent Systems Design and Applications, Cairo, 2010.
[35] Y. Cai, K. Huang, T. Tan, and Y. Wang, “Context Enhancement of Nighttime Surveillance by Image Fusion,” in International Conference on Pattern Recognition, Hong Kong, 2006, vol. 1, pp. 980-983.
[36] A. Yamasaki, T. Hidenori, S. Kaneko, T. Kanade, and H. Ohki, “Denighting:
Enhancement of nighttime images for a surveillance camera,” in International
78
Conference on Pattern Recognition, Tampa, FL, 2008, pp. 1-4.
[37] K. Huang, L. Wang, T. Tan, and S. Maybank, “A real-time object detecting and tracking system for outdoor night surveillance,” Pattern Recognition, vol. 41, no.
1, pp. 432-444, Jan. 2008.
[38] L. Wang, K. Huang, Y. Huang, and T. Tan, “Object detection and tracking for night surveillance based on salient contrast analysis,” in IEEE International Conference on Image Processing, Cairo, Egypt, 2009, pp. 1113-1116.
[39] K. Robert, “Night-Time Traffic Surveillance: A Robust Framework for Multi-vehicle Detection, Classification and Tracking,” in IEEE International Conference on Advanced Video and Signal Based Surveillance, Genova, Italy, 2009, pp. 1-6.
[40] Y.-L. Chen, B.-F. Wu, and C.-J. Fan, “Real-time vision-based multiple vehicle detection and tracking for nighttime traffic surveillance,” in IEEE International Conference on Systems, Man and Cybernetics, San Antonio, TX, 2009, pp.
3352-3358.
[41] Z.-N. and D., Mark S. Li, Fundamentals of Multimedia. Prentice-Hall of India, 2005.
[42] S. Theodoridis and K. Koutroumbas, Pattern Recognition & Matlab Intro:
Pattern Recognition, Fourth Edition, 4th ed. Academic Press, 2008.
[43] Z.-H. Lee, “Human Behavior Analysis with Shadow Cancellation and Occlusion Detection Technique,” in National Chiao Tung University Master Thesis, 2006.
[44] “Taiwan Area National Freeway Bureau,” http://www.freeway.gov.tw/, 04-Jul-2008.
[45] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol.
20, no. 3, pp. 273-297, Sep. 1995.