隨著經濟的發展及科技的進步，我們需要建立一套智慧型運輸系統來改善交通狀況，滿足駕駛人的行車需求。其中，車輛偵測是智慧型運輸系統中關鍵的步驟之一。成功的偵測車輛可以幫助我們得到其他交通參數，例如：車流量、車速等。與使用主動式感測器(例如：雷射雷達等)的車輛偵測方法相比較，使用光學感測器結合影像處理技術的偵測方法有以下的優點：成本低、偵測速度快等。所以本研究嘗試發展一套車輛偵測的影像處理技術，作為日後智慧型運輸系統發展的基礎。
由於光線狀況、視角、車輛顏色、大小、軸向、形狀和姿勢等的不同，使得發展一套完整而有效的車輛偵測系統充滿了挑戰。典型的交通場景監控系統通常使用移動特徵來偵測車輛，但在靜態單張影像中無法偵測移動特徵。本研究嘗試以線段特徵為基礎的方法，在影像中進行車輛待選區域的定位，再以對稱性特徵進行確認，達到在靜態單張影像中偵測車輛的目的。

With the economic development and progress of technology, the load on the transportation syystems become higher and higher and it is desired to “control” the traffic flow. Intelligent transportation system (ITS) is thus proposed to improve traffic efficiency. Among the various functions, vehicle detection plays an important role in ITS. Successfully detecting vehicle help us to get the traffic paraments, like traffic flow, vehicle speed and so on. Compared with active sensors, like laser radar, optical sensors together with image processing to detect vehcile have the advantage of being lower cost, higher detection speed, and so on, hance becomes an hot issue in ITS .
Due to the variations of lighting condition, view-point, vehicle colors, sizes, orientaions and shapes, developing a robust and effective system of vision-based vehicle detection is very challenging. Typical visual surveillance in traffic scenes attempts to detect vehicle using image sequences. Since vehicles can usually be identified in a single image, we believe it is more reasonable to do it this way. In this direction, we develop a line-based method to locate the candidate vehicle regions in the static image, and then verify them with symmetry feature.

[1] S.S. Beauchemin, J.L. Barron, “The computation of optical flow,” ACM Computing Surveys, vol.27, no.3, pp.433-466, Sep. 1995.
[2] G.L. Foresti, V. Murino, C. Regazzoni, “Vehicle recognition and tracking from road image sequences,” IEEE Transactions on Vehicular Technology, vol.48, no.1, pp.301-318, Jan. 1999.
[3] Y. Kameda and M. Minoh, “A human motion estimation method using 3-successive video frames,” In Proc. of the Int'l. Conf. on Visual Systems and Multimedia '96, pp.135-140, Sep. 1996.
[4] C. Wren, Ali Azarbayejani, Trevor Darrell, and Alex Pentland, “Pfinder: Real-time tracking of the human body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.19, no.7, pp.780-785, July 1997.
[5] W.E.L. Grimson and C. Stauer, “Adaptive background mixture models for real-time tracking,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol.2, pp.252,23-25, June 1999.
[6] B. Maurin, O. Masoud, N. Papanikolopoulos, “Monitoring crowded traffic scenes,” The IEEE 5th International Conference on Intelligent Transportation Systems, pp.19-24, 2002.
[7] X. Yuan, Z. Sun, Y. Varol, G. Bebis, “A distributed visual surveillance system,” Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, pp.199-204, July 2003.
[8] W.L. Hsu, H.Y.M. Liao, B.S. Jeng, K.C. Fan, “Real-time vehicle tracking on highway,” Proceedings of The IEEE Conference on Intelligent Transprotation Systems, vol.2, pp.909-914, Oct. 2003.
[9] G.L. Foresti, V. Murino, C. Regazzoni, “Vehicle recognition and tracking from road image sequences,” IEEE Transations on Vehicular Technology, vol.48, no.1, pp.301-318, Jan. 1999.
[10] L.W. Tsai, J.W. Hsieh, K.C. Fan, ”Vehicle detection using normalized color and edge map,” IEEE International Conference on Image Processing, vol.2, pp.598-601, Sep. 2005.
[11] K. Yamada, M. Mizuno, “A vehicle parking detection method using image segmentation,” Electronics and Communications in Japan, vol.84, no.10 , pp.25-34, Apr. 2001.
[12] T. Zielke, M. Brauchkmann, W. von Seelen, “CARTRACK： computer vision-based car following,” IEEE Workshop on Applications of Computer Vision, Proceedings, pp.156-163, 1992.
[13] Y. Du, N.P. Papanikolopoulos, “Real-time vehicle following through a novel symmetry-based approach,” IEEE International Conference on Robotics and Automation, vol.4, pp.3160-3165, Apr. 1997.
[14] M. Bertozzi, A. Broggi, S. Castelluccio, “ A real-time oriented system for vehicle detection,” Journal of Systems Architecture, pp.317-325, 1997.
[15] C. Hilario, J.M. Collado, I.M. Armingol, A. de la Escalera, “Pyramidal image analysis for vehicle detection,” Proceedings of The IEEE Conference on Intelligent Vehicles Symposium, pp.88-93, June. 2005.
[16] M.D. Heath, S. Sarkar, T. Sanocki, K.W. Bowyer, “A robust visual method for assessing the relative performance of edge-detection algorithms,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.19, no.12, pp.1338-1359, Dec. 1997.
[17] I. Biederman, “Human image understanding: Recent research and a theory,” Comput. Vision Graphics and Image Processing, vol.32, pp.29-73, 1985.
[18] R. Duda, P. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Communications of the ACM, vol.15, no.1, pp.11-15, Jan. 1972.
[19] Y. Liu, T. S. Huang, “Determining straight line correspondences from intensity images,” Pattern Recognition, vol.24, pp.489 -504, 1991.
[20] G.Q. Lu, H.G. Xu, Y.B. Li, “Line detection based on chain code detection,” IEEE International Conference on Vehicular Electronics and safety, pp.98-103, Oct. 2005.
[21] A. Etemadi, “Robust segmentation of edge data,” Proceedings of 4th IEE International Conference on Image Processing and Applications, 1992.
[22] T.H. Hong, M.O. Shneier, R.L. Hartley, A. Rosenfeld, “Using pyramids to detect good contunuation,” IEEE Transactions on Systems,Man and Cybernetics, vol. 13, pp.631-635, 1983.
[23] C.S. Regazzoni, G.L. Foresti, V. Murino, “A Distributed Hierarchical Regularization System for Recognition of Planar Surfaces,” Optical Engineering, vol.32, no.6, pp. 1167-1192, 1993.
[24] T. Liu, N. Zheng, L.Zhao, H. Cheng, “Learning based symmetric features selection for vehicle detection,” Proceedings of The IEEE Conference on Intelligent Vehicles Symposium, pp.124-129, June. 2005.
[25]N. Friedman and S. Russell, “Image segmentation in video sequences: A probabilistic approach,” In Thirteenth Conference on Uncertainty in Artificial Intelligence(UAI), Aug. 1997.
[26] A. Elgammal, R. Duraiswami, D. Harwood and L. S. Davis, “Background and Foreground Modeling using Non-parametric Kernel Density Estimation for Visual Surveillance”, Proceedings of the IEEE, vol.90, no.7, pp.1151-1163, July 2002.
[27] S. Jabri, Z. Duric, H. Wechsler, and A. Rosenfeld, “Detection and Location of People in Video Images Using Adaptive Fusion of Color and Edge Information,” Proc. Int'l Conf. Pattern Recognition, pp. 627-630, 2000.
[28]D.W. Scott, “Multivariate density estimation,” New York：Wiley Interscience, 1992.
[29]R.J. Althof, M.G.J. Wind, J.T. Dobbins, “A rapid and automatic image registration algorithm with subpixel accuracy”, IEEE Transactions on Medical Imaging, vol.16, pp. 308-316, 1997.
[30] M.C. Huang, S.H. Yen, “A real-time and color-based computer vision for traffic monitoring system,” IEEE International Conference on Multimedia and Expo, vol.3, pp.2119-2122, June 2004.