The background subtraction in traffic surveillance system

Abstract

Background subtraction is widely used for detecting non-static object from the video or fixed camera such as traffic surveillance. The background model finds difficult to extract the good foreground if it is implement in real-time, the change of light and weather that make the detected-foreground is not clear, has countless noise. Therefore, to avoid that problem, the Mixture of Gaussian need subsequent processing step to make the foreground better. The paper proposes a method which degrade several drawbacks of Background Subtraction, which intended to be used in urban traffic scenes. Keywords: Background subtraction, Mixture of Gaussian, contour, morphology, quantitative performance, surveillance system.