一种视频运动目标精确分割新算法

针对视频图像中单个运动目标的分割问题,提出了一种基于Kirsch边缘算子的视频运动目标分割算法,该算法将Kirsch算子检测到的边缘作为主分割信息,运动矢量场作为次要分割信息。首先利用双重尺度的运动矢量场进行累加和滤波处理来获得辅助分割信息；然后将Kirsch算子的模板分解为差值模板和公共模板以提高边缘的抗噪性；最后用自适应状态标记的方法将边缘信息和运动矢量信息相融合来准确地分割运动目标。实验结果表明该方法分割比较精确。

A Video Moving Object Accurate Segmentation Algorithm

For the problem of moving object segmentation in video sequence, a new video moving object segmentation algorithm based on Kirsch edge operator is proposed. The edge detected by Kirsch operator is taken as primary partition information, and motion vector field is taken as secondary partition information. First assisted segmentation information is obtained by accumulating and filtering Dual-scale motion vector field; Secondly, templates of Kirsch operators are decomposed into difference templates and common templates to improve the noise immunity of edges; then, the edge information and the motion vectors are fused to get moving object accurately by adaptive state labeling. The experimental results show that the proposed algorithm has a better veracity of segmentation.