A improved dynamic background updating algorithm based on traffic video

Produced are varieties of information, such as tracking, speed, and recognition of cars as well as traffic density from traffic video, while there are many tasks to be solved. In view of the faults of traditional method, a new dynamic background updating algorithm for traffic video is proposed. Based on researches of existing methods, the reason of weakness and shortage is analyzed, and improved the traditional method. Experiments show that it is practical method that is robust under lighting variations, fast in speed, satisfactory in vehicles detection.