基于光流和水平集算法融合的运动目标提取

A Fusion Method of Extracting Moving Object Based on Optical Flow and Level Set

摘要: 本文提出一种简单有效的基于光流场和水平集融合的新的运动目标检测算法.首先, 通过图像序列中相邻两帧图像得到光流场, 并设置阈值对光流大小进行二值化;其次, 应用数学形态学闭运算实现区域连通, 获取运动目标的大致运动区域;最后, 以此区域的边界线为水平集搜索的初始轮廓线, 选择合适的图像颜色模型, 通过能量函数搜索, 得到准确的运动目标轮廓, 从而提取出运动目标.实验结果表明, 该方法不过于依赖光流场估计的正确性, 可有效、快速地检测出运动目标.

Abstract: A new simple and effective fusion method based on optical flow field and level set method is proposed in this paper.Optical flow field is acquired by the adjacent two frames of the image sequences.Binary image is got from optical flow by setting a threshold.Then, the coarse moving object area can be obtained by mathematical morphological close operation, which is aimed at attaining the initial contour line of a level set curve evolution method.After selecting the appropriate image color model, the precise contour is searched by the energy function for evolution to extract moving object.Experimental results show that this method is suitable for detecting the moving object rapidly and effectively without depending on the accuracy of optical flow field heavily.