Vehicle detection and classification information is invaluable in many transportation issues. Vehicle feature extraction and detection are the preprocesses required for vehicle classification. Current automatic vehicle classification systems have deficiencies: low accuracy, special requirements, fixed orientation of the camera, or additional hardware and devices. This paper discusses a vehicle detection and classification system using model-based and fuzzy logic approaches. The system was tested with the use of a variety of images captured by the highway traffic control center of the Utah Department of Transportation. In comparison with existing systems, major advantages of the proposed system are ( a) no special orientation of the camera is required, ( b) no additional devices are needed, and ( c) high classification accuracy is provided. Experimental results show that the performance of the proposed system exceeds that of the existing video-based vehicle classification systems.
A Model-Based Approach for Fast Vehicle Detection in Continuously Streamed Urban LIDAR Point Clouds