Noise Reduction Algorithm Using Area and Shape Suppression in Vehicle Detection

Vehicle detection is one of the key technologies in Intelligent Transportation System (ITS), and it is an important stage of vehicle tracking in visual surveillance. Due to the clutter of traffic scenes, the captured video sequence has a lot of noise with significant size. This paper defines the non--objects shape and area suppression according to human vision, and proposes a new noise--removing algorithm. In order to improve the compute efficiency, this paper modifies the sequential algorithm to reduce the computational complekity. Experimental results show that this algorithm is effective and efficient in extracting the moving vehicles in clutter scene.