基于ViBe模型和五帧差分法的目标检测算法

Target Detection Algorithm Based on ViBe Model and Five-Frame Difference Method

针对当前常用ViBe算法对光照适应性差,当光照突变时ViBe算法把大面积的背景误判成前景;为此提出了一种结合ViBe背景模型与五帧差分法的新的运动目标提取方法。首先采用ViBe算法提取运动前景目标,然后将整个前景图片分成若干区域,统计这些区域中前景像素个数大于预设阈值的区域的个数,将符合条件的区域的个数与整个前景图片区域总数相比,当比值大于某一阈值,发生了判断为光照突变改用五帧差分法处理图像;最后通过连通性检测和形态学操作等后处理,最终提取出运动前景目标。实验结果表明:该算法能够有效地防止ViBe算法把大面积的背景误判成前景,提高了ViBe算法对光照变化场景下的鲁棒性,检测效果优于单独使用ViBe算法和五帧差分法的检测效果。

In view of the poor adaptability of the current ViBe algorithm to illumination,a new method of moving target extraction is proposed,which combines the ViBe background model with the five-frame difference method.Firstly,the motion foreground object is extracted using the ViBe algorithm,and then the entire foreground picture is divided into several areas. Counting the number of areas where the number of foreground pixels in these areas is greater than the preset threshold value,and the number of areas that meet the conditions are compared with the total number of foreground image areas. Secondly,When the ratio is greater than a certain threshold,then it is determined that the light irradiation mutation has been determined and the image is processed by the five-frame difference method. Finally,after the post-processing of connectivity detection and morphological operation,the motion foreground target is finally extracted. The experimental results show that the algorithm can effectively prevent the ViBe algorithm from misjudging the large area of the background into the foreground,and improve the robustness of the ViBe algorithm to the illumination change scene.