CAJ | 학술논문

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。
침대유모호도상실현운동고계시계산복잡、소모자원대적문제，제출일충유도상각구처alpha통도실현운동삼수고계적분석방법。운동모호도상온함착운동신식，이각정점적운동대삼수고계유착직관적해석，건립각구처alpha통도운동약속，사운동고계여도상거모호분리개，운용Hough투표법제취소수요적신식，실현운동삼수고계。분석불동려파기대고계결과정도적영향。실험결과표명：해방법시가이유단폭모호도상실현일정범위내적운동고계，축단운산시간，차고계결과정도교고。
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.