For the problems of complex calculation and large consumption of motion estimation from blurred image, a novel method of estimating the motion parameters based on alpha channel of corner region is proposed. The motion blurred images contain motion information, and the corner motion is a significant interpretation for motion parameters estimation. When the motion constraint of alpha channel in the corner region is established, motion estimation and image deblurring can be separated; then take the Hough voting approach to extract the information which we need, to get the motion estimation. Analyze the effects of the different filter on estimation accuracy. The experiment results show that the method is effective within a certain range by using a single blurred image with the operation time shortened and estimation result accuracy.%针对由模糊图像实现运动估计时计算复杂、消耗资源大的问题，提出一种由图像角区处alpha通道实现运动参数估计的分析方法。运动模糊图像蕴含着运动信息，而角顶点的运动对参数估计有着直观的解释，建立角区处alpha通道运动约束，使运动估计与图像去模糊分离开，运用Hough投票法提取所需要的信息，实现运动参数估计。分析不同滤波器对估计结果精度的影响。实验结果表明：该方法是可以由单幅模糊图像实现一定范围内的运动估计，缩短运算时间，且估计结果精度较高。
展开▼
