車輛偵測與計數系統一直以來都是智慧型運輸系統(Intelligent Transportation Systems, ITS)中一項重要之議題，此系統可以有效提升交通管理系統之管理效率，進而達到提升交通安全。在本研究中，吾人提出一個名為車輛偵測與計數系統之演算法，本系統提供了兩種運算模組，分別處理白天與夜晚環境之影像，它們使用不同方法去偵測車輛，被偵測到之車輛會被分類為摩托車與汽車。在處理白天環境之子系統中，提取被偵測到車輛之寬度、長度與面積作為特徵，根據這些特徵可以簡單地將被偵測到之車輛分成兩類；在處理夜晚環境之子系統中，使用汽車車頭燈所形成的區域之個數作為特徵，根據這項特徵可以簡單地將被偵測到之車輛分成兩類。本系統適應環境變化動態地更新背景，利用背景相減法去擷取位於目前訊框上之移動物件，初始背景經由平均所拍攝之一序列影像得到。本系統之測試影片經由拍攝實際道路、高速公路與一般道路所得到，依環境分成晴天、多雲、陰影、雨天與夜晚，經過實驗結果發現，本系統在晴天與多雲時偵測正確率達到95%，在雨天與夜晚也可達到90%。

Vehicle detection and counting system is one of important issues of an intelligent transportation system (ITS). The system can be used to improve the managing efficiency of a traffic management system. In this research, a system called vehicle detection and counting system was proposed. It provides two operation scenarios; one is for day-time and another one is for nighttime. They used different methods for vehicle detection. The detected vehicles are classified as motorcycle and automobile. For the daytime subsystem, the width, length and area of the detected vehicle are applied as the features. According these features, the detected vehicles can be easily classified into the two classes. For the nighttime subsystem, the number of lighting area produced by the head lights of the vehicle is used as the features. The system used background—updated from the previous frame, subtraction method to extract those motion objects located on the current frame. The initial background frame is obtained by averaging a number of frames of the staring frames captured by camera. The testing videos captured from the real road, high way and general way; and the considered time includes in sunny, cloudy, rainy, and at night time had been applied to the proposed system. It shows that the detection rate for sunny and cloudy cases is more than 95%. It is more than 90% for both rainy and night time.

[1]交通部，「機動車輛登記數」，http://www.motc.gov.tw/(2011 /6/12)。
[2]內政部警政署，「道路交通事故及違規概況」，http: //www.npa.gov.tw/(2011/6/12)。
[3]I. Masaki, “Machine-vision systems for intelligent transportation systems,” IEEE Intelligent Systems, Vol. 13, Issue 6, pp. 24-31, 1998.
[4]Ling Lin, Xiao-Bin Han, Ru Ding, Gang Li, and Quan Hong, “Mini Inductive Loop Vehicle Detection Sensor,” Chinese Journal of Sensors and Actuators, Vol.19, No.4, pp.994-1000, 2006.
[5]B. Coifman, D. Beymer, P. McLauchlan, and I. Malik, “A real-time computer vision system for vehicle tracking and traffic surveillance,” Transportation Research Part C:Emerging Technologies﹐Vol. 6﹐Issue 4, pp.271-288, 1998.
[6]B. K.Horn and B. G. Schunck, “determine optical flow,” Artificial intelligence, Vol. 17, Issues 1-3, pp. 185-203, 1981.
[7]C. Anderson, Peter Burt, and G. van der Wal, “Change detection and tracking using pyramid transformation techniques,” In Proceedings of SPIE - Intelligent Robots and Computer Vision, vol. 579, pp. 72-78, 1985.
[8]S. Takaba, T. Sekine, and B.W. Hwang, “A Traffic Flow Measuring System Using a Solid State Sensor,” International Conference on Road Traffic Data Collection, London, UK, pp.110-114, 1984.
[9]De-Zh Ding, and De-We Hou, “Algorithm for adaptive background model building,” computer Engineering and Design, Vol. 30, Issue 1, pp.219-221, 2009
[10]許芝華，“應用於交通監視系統上之及時車輛計數演算法”，國立成功大學電腦與通信工程研究所碩士論文，2007.
[11]C. Stauffer and W.E.L Grimson, “Adaptive background mixture models for real-time tracking,” IEEE Conference on Computer Vision and Parttern Recognition, Vol. 2, pp. 246-252, 1999.
[12]C. Wren, A. Azarhayejani, T. Darrell, and A.P. Pentland, “Pfinder: real-time tracking of the human body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 780-785, 1997.
[13]N. Friedman, and S. Russell, “Image segmentation in video sequences: a probabilistic
approach,” Thirteenth Conference on Uncertainty in Artificial Intelligence, pp. 175-181, 1997.
[14]M. Piccardi, “Background subtraction techniques: a review,” IEEE International Conference on Systems, Man and Cybernetics, Vol. 4, pp. 3099-3104, 2004.
[15] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, “Detecting moving objects, ghosts, and shadows in video streams,” IEEE Tranactions on Pattern Analysis and Machine Intelligence, Vol.25, No.10, pp. 1337-1442, 2003.
[16]A. Elgammal, D. Hanvood, and L.S. Davis, “Non-parametric model for background subtraction,” Proceedings of the 6th European Conference on Computer Vision, Ireland, Vol. 1843, pp. 751-767, 2000.
[17]B. Han, D. Comaniciu, and L.S. Davis, “Sequential kernel density approximation through mode propagation: applications to background modeling,” Asian Conference on Computer Vision(ACCV), Jeju Island, Korea, Jan. 2004.
[18]N.M. Oliver, B. Rosario, and A.P. Pentland, “A Bayesian computer vision system for modeling human interactions,” IEEE Transactions on Pattern Analysis and Machine intelligence, Vol. 22, No. 8, pp. 831-843, 2000.
[19]A. Yoneyama, C. H. Yeh, and C. C. J. Kuo, “Robust Vehicle and Traffic Information Extraction for Highway Surveillance,” EURASIP Journal on Applied Signal Processing, Vol. 2005, Issue 14, pp. 2305-2321, 2005.
[20]Y. Iwasaki, “A Method of Real-time Moving Vehicle Detection for Bad Environments Using Infrared Thermal Images,” Innovations and Advanced Techniques in Systems, Computing Sciences and Software Engineering, pp 43-46, 2008.
[21]Rita Cucchiara, Massimo Piccardi, and Paola Mello, “Image Analysis and Rule-Based Reasoning for a Traffic Monitoring System,” IEEE Transactions on Intelligent Trasportation Systems, Vol. 1, No. 2, June 2000.
[22]Urban Meis, Wemer Ritter, and Heiko Neumann, “Detection and Classification of Obstacles in Night Vision Traffic Scenes based on Infrared Imagery,” IEEE International Conference on Intelligent Transportation Systems, Shanghai, China, pp. 1140-1145, Oct. 2003.
[23]Thou-Ho Chen, Jun-Liang Chen, and Chin-Hsing Chen,“Vehicle Detection and Counting by Using Headlight Information in the Dark Environment,” Third International Conference on International Information Hiding and Multimedia Signal Processing (IIH-MSP 2007), Vol. 2, pp. 519-522, 2007.
[24]Luo-Wei Tsai, Jun-Wei Hsieh, and Kao-Chin Fan, “Vehicle detection using normalized color and edge map,” IEEE Transactions on Image Processing., Vol. 16, No. 3, pp. 850–864, Mar. 2007.
[25]吳上立, 林宏墩, C語言數位影像處理, 全華, 2006
[26]R. Cucchiara, C. Grana, M. Piccardi, A. Prati, and S. Sirotti, “Detecting Moving Objects, Ghosts, and Shadows in Video Streams,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, pp. 1337-1342, 2003.
[27]Ernesto de la Rocha, and Rafael Palacios, “Image-processing algorithms for detecting and counting vehicles waiting at a traffic light,” Journal of Electronic Imaging, Vol. 19, Issue 4, Dec. 2010.
[28]W. F. Gardner, and D. T. Lawton, “Interactive model-based vehicle tracking,” IEEE Transactions on Pattern Analysis and Machine intelligence, Vol. 18, No. 11, pp. 1115-1121, Nov. 1996.
[29]Ching-Po Lin, Jen-Chao Tai, and Kai-Tai Song, “Traffic monitoring based on real-time image tracking,” 2003 IEEE International Conference On Robotics And Automation, Vol. 2, pp. 2091-2096, Sept. 2003.
[30]Luo-Wei Tsai, Jun-Wei Hsieh, and Kuo-Chin Fan, “Vehicle detection using normalized color and edge map,” IEEE Transactions on Image Processing, Vol. 16, No. 3, pp. 850-864, Mar. 2007.