New algorithm for moving object detection based on the triangle kernel density estimation model

Detection of moving objects is the basic function of a video surveillance and monitoring system.In this paper,the current moving object detection algorithms using the Gaussian model are discussed,and from the point of view of statistics,a novel non-parametric method of triangle kernel estimation is presented to model the scene background so as to detect the moving object.Then based on the detecting result,the background sample and bandwidth can be updated.It has been proved by the experiments that this algorithm can achieve high sensitivity in the deuection of moving objects with the lowest possible false alarm rates.