融合空时显著性的雪天运动目标检测方法

摘要

下雪天存在雪花动态背景噪声,对运动目标检测有较大干扰,现有方法难以解决问题.将空间静态图像的显著性检测方法引入到运动目标检测中,提出了一种适应于雪天的运动目标检测方法,采用空时显著性融合的方法得到运动目标的区域位置信息.实验结果表明,该方法可以有效解决下雪天相机静止情况下的运动目标检测,并在相机移动的动态背景情况中也有一定的检测潜力.%There are snowflakes dynamic background noise in the snow day,which has great interference to the moving target detection.The existing method is hard to solve the problem.The method of detecting the salience of the spatial static image is intro-duced into the detection of the moving target.A moving object detection method is proposed.The space position information of the moving target is obtained by space-time significant fusion method.Experimental results show that the proposed method can effective-ly solve the moving target detection in the snowy days when the camera is still in motion,and also has certain detection potential in the dynamic background of camera movement.