单幅运动模糊图像的恢复及应用  

Motion Deblurring and Application from a Single Motion Blurred Image

作　　者：程姝[1] 赵志刚[1] 蒋静[1] 陈莹莹[1] 潘振宽[1] 

机构地区：[1]青岛大学信息工程学院,山东青岛266071

出　　处：《青岛大学学报（自然科学版）》2012年第3期50-56,87,共8页Journal of Qingdao University(Natural Science Edition)

基　　金：国家自然科学基金项目(61170106);青岛市科技计划项目基金(06-2-2-2-JC)

摘　　要：运动模糊图像复原技术高度依赖于点扩散函数的估计,即估计线性运动模糊的方向和长度,这两个参数与物体实际运动速度有一定几何关系。本文在去除运动模糊的同时,提出一种基于单幅模糊图像估计车速的方法。由于运动模糊通常发生在图像的动态区域,因此在恢复图像的同时依据成像几何、相机摆姿和估计出的模糊参数经过数学推导可以计算出车速。本文依据模糊像素扩散现象及模糊图像在频域的性质来估计模糊参数,结合维纳滤波方法进行复原。从而辨识车辆、估计车速、辅助交通管理。实验表明本文方法实用性强,效果较好。Motion blurred image restoration technology is highly depending on the blur parameters estima-tion, such as direction and length. The two parameters have geometric relations with objects＇ movement speed. In this paper, at the same time removing the motion blur , we propose a method to estimated speed of vehicles through a single image. Due to the relative motion between the camera and a moving object dur-ing the camera exposure time, motion blur occurs in the dynamic region of the image. It provides a visual cue for the speed measurement of a moving object. So at the time of image restoration the, vehicle speed is calculated according to the imaging geometry, camera pose, and blur extent in the image. This method is mainly based on the blur pixel spreading and the property of image in the frequency domain estimating the point spread function and combined with the wiener filtering method deblurring. Thus identificate vehi-cles, estimates the speed, help manage traffic. Experiment shows that the method practical strong and have a good effect.

关 键 词：运动模糊 运动分析 速度测量 维纳滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]