Vehicle Tracking Algorithm Based on Modified GVFSnake Model
ZHANG Hui1, DONG YuNing1,2,3, XIA Yang1
1.College of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003 2.State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093 3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080
Abstract A vehicle tracking algorithm based on modified Gradient Vector Flow (GVF)Snake model is proposed. In this algorithm, the original contours of vehicles are automatically acquired by using the framedifference method. The outline of vehicles can be obtained accurately from video stream by means of the modified GVFSnake model. To Compute fast, the modified GVFSnake model adopts the greedy algorithm to control the points according to the distances among them so as to adapt to the change of vehicle targets. Thus, the forecast algorithm is applied to track vehicles. Experimental results testify the effectiveness of the proposed algorithm.
[1] Gupte S, Masoud O, Martin R F K, et al. Detection and Classification of Vehicles. IEEE Trans on Intelligent Transportation Systems, 2002, 3(1): 3747 [2] Jiang Gangyi, Yu Mei, Wang Shengnan, et al. New Approach to Vehicle Tracking Based on Region Processing // Proc of the International Conference on Machine Learning and Cybernetics. Guangzhou, China, 2005, Ⅷ: 50285033 [3] Kai S, Bebis G, Haisong G, et al. Vehicle Tracking Using OnLine Fusion of Color and Shape Features // Proc of the 7th IEEE International Conference on Intelligent Transportation Systems. Parma, Italy, 2004: 731736 [4] Xie Lei, Zhu Guangxi, Wang Yuqi, et al. RealTime Vehicles Tracking Based on Kalman Filter in a VideoBased ITS // Proc of the International Conference on Communications, Circuits and Systems. Hong Kong, China, 2005, Ⅱ: 883886 [5] Tan T N, Baker K D. Efficient Image Gradient Based Vehicle Localization. IEEE Trans on Image Processing, 2000, 9(8): 13431356 [6] Kim Z, Malik J. Fast Vehicle Detection with Probabilistic Feature Grouping and Its Application to Vehicle Tracking // Proc of 9th IEEE International Conference on Computer Vision. Beijing, China, 2003, Ⅰ: 524 531 [7] Chateau T, Lapreste J T. Real Time Tracking with Occlusion and Illumination Variations // Proc of the 17th International Conference on Pattern Recognition. Cambridge, UK, 2004, Ⅳ: 763766 [8] Paragios N, Deriche R. Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(3): 266280 [9] Peterfreund N. Robust Tracking of Position and Velocity with Kalman Snakes. IEEE Trans on Pattern Analysis and Machine Intelligence, 1999, 21(6): 564569 [10] Won K, Lee C Y, Lee J J. Tracking Moving Object Using Snake’s Jump Based on Image Flow. Mechatronics, 2001, 11(1): 199226 [11] Rostampour A R, Reeves A P, Mitchell O R. Use of Temporal Variance for Moving Object Extraction // Proc of the 7th Annual International Phoenix Conference on Computers and Communications. Scottsdale, USA, 1988: 480484 [12] Kass M, Withkin A, Terzopoulos D. Snakes: Active Contour Models. International Journal of Computer Vision, 1987, 1(4): 321331 [13] Xu C Y, Prince J L. Snakes, Shapes, and Gradient Vector Flow. IEEE Trans on Image Processing, 1998, 7(3): 359369 [14] Zhang Yong, Ou Zongying, Hou Jianhua. Boundary ContourTracing Based on Active Contour Model in Medical Imagings. Chinese Journal of Scientific Instrument, 2002, 23(Z1): 173174 (in Chinese) (张 勇,欧宗瑛,侯建华.基于主动轮廓模型的医学图像边界跟踪.仪器仪表学报, 2002, 23(Z1): 173174) [15] Stauffer C, Grimson W E L. Adaptive Background Mixture Models for RealTime Tracking // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Colorado, USA, 1999, Ⅱ: 246252 [16] Williams D J, Shah M. A Fast Algorithm for Active Contours and Curvature Estimation. CVGIP: Image Understanding, 1992, 55(1): 1426 [17] Chen Jian, Qi Feihu, Cen Feng. 3D Image Segment Method with Forecast Capability. Journal of Infrared and Millimeter Waves, 2001, 20(3): 194198 (in Chinese) (陈 剑,戚飞虎,岑 峰.一种具有预测能力的三维图像分割方法. 红外与毫米波学报, 2001, 20(3): 194198)
2007, Vol. 20 
