Abstract: This paper presents a motion estimation algorithm based on the Horn-Schunck optical flow estimation method. The first step estimates the forward gradients and backward gradients of the current frame. Through selecting the gradients adaptive to reduce the occlusion problem in computing optical flow, the algorithm is implemented on different kinds of video sequences and good segmentation results are achieved.

Key words: motion estimation, adaptive gradient, Horn-Schunck method, occlusion problem

摘要： 给出了一种基于Horn-Schunck的改进光流估计算法，计算了当前帧的前向梯度、后向梯度，根据代价函数自适应地选择前向梯度与后向梯度，减小光流估计时的遮挡问题。试验表明该算法是有效的。

关键词: 运动估计, 自适应梯度, Horn-Schunck法, 遮挡问题

CLC Number: 

• TP391