关键词: 运动目标检测, 混合高斯模型, 背景相减法, 混合差分法

Abstract:

A novel moving objects detection algorithm based on background subtraction and hybrid difference is proposed for video surveillance system with static camera.First,the mixed Gaussian model is constructed for the color images,and the background model is updated timely,then the idea of hybrid difference is presented on the basis of the adjacent frame difference,and finally the background subtraction is combined with hybrid difference to gain exact moving objects.Experimental results show that the proposed method could construct background model accurately,and that it not only gets moving objects completely,but also adapts to the complex environmental change so that both the accuracy and speed are improved.

Key words: moving objects detection;mixed Gaussian background model;background subtraction;hybrid difference