基于三角核估计模型的运动目标检测方法

文章对基于高斯模型的运动目标检测算法进行了研究,在此基础上,采用三角核估计的非参数方法来对背景建模,从而检测出运动目标;并结合检测结果来更新样本和带宽,提出了与之相对应的背景更新方法。实验结果证明,该方法能准确快速的检测出运动目标,具有较强的鲁棒性。

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.