旋转运动模糊的盲复原  

The Method of Blind Restoration for Uniform Rotation Motion Blurred Images

作　　者：朱近[1] 薛钗琨[1] 陆宏伟 陈晓峰 罗丁 

机构地区：[1]南京理工大学计算机科学与技术学院,南京210094 [2]二炮装备研究院,北京100085

出　　处：《火力与指挥控制》2011年第7期36-38,41,共4页Fire Control & Command Control

基　　金：军队"863"基金资助项目(J200706006)

摘　　要：旋转运动模糊图像的盲复原是一个挑战性的课题。提出了一种新颖的模糊参数的估计方法:首先将旋转运动模糊图像分割成子图块,并将各子图块的运动模糊近似为直线模糊,运用基于Hough变换方法和微分自相关方法估算出各子图块的模糊尺度和方向,构成整图的离散旋转运动场。然后利用所得到离散运动场,用最小二乘技术估算出整图的旋转运动模糊参数(模糊中心和模糊角度)。最后采用基于极坐标变换的旋转运动模糊的恢复方法进行了恢复实验。实验表明新方法具有方法简单,处理速度快和精度好的特点。The blind restoration of rotational motion blurred images is a challenging task.This paper proposed a novel estimation method of blur parameters for rotational motion blurred images.At first,the blurred image is divided into some sub-blocks.The motion blur in blocks is approximated as linear,then estimating blur scale and direction in the block are estimated with hough transform method and differential self-correlation method and formed the discrete rotation field for whole image.Using the discrete rotation field,the rotational motion blur parameters（center and angle） in the image are estimated with least-squares technique.At last,the restoration experiments are tested for the rotational motion blur based on the polar coordinate transform.The results show that the new method is effective for simplicity,rapid processing speed and high precision.

关 键 词：旋转运动 运动模糊 盲复原 HOUGH变换 最小二乘 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]