Real Time and Automatic Vehicle Type Recognition System Design and Its Application
Using a fixed single camera and video capture card, the real time video flow of a highway toll stations vehicle passing has be collected, with technology of motion detection on digital image, all data frames include vehicle image can be detected automatically from the video, at the same time, vehicle type will be recognized and displayed automatically. The system process consists of four main steps: Reading video capture card and decomposing video flow into frames; Moving vehicle detection; Processing vehicle digital image; Vehicle type recognition. Experiment shows: the system design is simple and effective; the algorithm flow of vehicle image processing is simpler than that of references. Specially, the algorithm of vehicle type recognition through counting the total number of black pixels included in vehicle body contour is an innovation.
VehicteTypeRecognition Background Subtraction Threshold Segmentation Anti-color Processing on Image Counting total Number of Black Pixels
Wei Zhan ZhiQing Luo
College of Computer Science, Yangtze University, Jingzhou, HuBei, China School of Computer Science, School of Computer Science, China University of Geosciences, Wuhan, HuBei, China
国际会议
太原
英文
565-567
2011-02-26（万方平台首次上网日期，不代表论文的发表时间）