动态成像条件下基于SURF和Mean shift的运动目标高精度检测

High precision detection of a mobile object under dynamic imaging based on SURF and Mean shift

针对动态成像条件下运动目标检测的难点问题,提出了一种将SURF特征和Mean shift图像分割相结合的高精度运动目标检测方法.首先利用SURF特征进行图像配准,以补偿背景图像的运动漂移;然后利用差分求积二值化和形态学滤波方法检测出运动目标区域;最后结合Mean shift图像分割方法实现运动目标的精确检测.通过一系列实拍视频的运动目标检测实验验证了此算法的有效性和可行性.实验结果表明,此方法能精确检测出动态成像条件下所形成的动态背景中的运动目标,而且具有良好的鲁棒性和抗噪能力,对于光照条件和亮度变化等不利因素也有较强的适应能力.

Taking into account the difficulty of moving-object detection with a dynamic background caused by camera motion,a new method was proposed based on speeded-up robust features（SURF） and Mean shift.First,the image registration based on SURF was applied to compensate the background motion,and then binarization of quadrature by difference method and morphological filters was carried out to detect the moving-object＇s area so that the accurate detection and segmentation of the moving object was accomplished with Mean shift.Finally,the effectiveness and satisfactory performance were validated through a series of experiments of dynamic videos.The results indicate that the proposed algorithm is characterized by high precision,low false detection,and strong robustness to noises,and thus can be extended to application in practical engineering.