A new algorithm of background image extraction and update in the vehicle detection system

摘要

To improve the rate of vehicle recognition, this article proposed a new improved Surendra background update algorithm, then accomplished the experiment comparison under the different environment with the traditional multi-frame image average background update algorithm. The experimental results indicated that the new improved Surendra background update algorithm has the obvious comprehensive superiority compared to the old algorithm, it can gain the accurate background image, and carry on the background image update effectively, then increases the rate of vehicle recognition.