Real-time Rear of Vehicle Detection from a Moving Camera

Based on the requirement of real-time on road vehicle detection from a moving camera, a feature based rear of vehicle detection algorithm is developed. A Haar-like feature classifier is trained to capture the rear of vehicles from the video stream in real-lime and a premier test is performed. Aiming at some issues found in the test, which include duplicated detection, false alarms, undetected objects and the failure of detecting distant object due to limited resolution, a revised algorithm is given. Some further tests and analyses indicate that the revised algorithm can effectively detect the rear of vehicles in real-time with complex background from a moving camera.