Detecting Moving Targets from Traffic Video Based BSFD- Background Subtraction Frame Difference Algorithm

Abstract

Advantages and drawbacks of two common algorithms often employed in the moving target detection, background subtraction technique and frame distinction methodology are analyzed and compared during this paper. Then supported the background subtraction methodology, a BFSD target detection rule is projected. The background image used to process the next frame image is generated through superposition of the current frame image and therefore the current background image with certain chance. This algorithm makes the objects that keep long-standing, however not be detected as a part of the background. The experimental results show that this algorithm can detect moving objects a lot of effectively and precisely.