利用拉东变换估计全景图像点扩散函数  

Using Radon transform to estimate the PSF of the panoramic image

作　　者：朱齐丹[1] 孙磊[1] 蔡成涛[1] 

机构地区：[1]哈尔滨工程大学自动化学院,黑龙江哈尔滨150001

出　　处：《光电子．激光》2013年第11期2233-2239,共7页Journal of Optoelectronics·Laser

基　　金：国家自然科学基金(61175089;61203255);博士后研究人员落户黑龙江科研启动基金(LBH-Q11135);中央高校基本科研业务费专项基金(HEUCF1321001)资助项目

摘　　要：针对全景图像点扩散函数(PSF)空间移变的特点,提出一种利用拉东(Radon)变换估计全景图像局部区域的PSF算法。算法首先分析全景成像原理和PSF拉东变换与图像中模糊直线响应的关系;然后利用有效的采样方法得到孤立的采样边缘,并通过求导得到图像边缘的直线响应;最后利用采样信息复原出PSF并结合Lucy-Richardson(L-R)算法对图像进行复原。同时采用迭代最优化的估计算法解决由于采样边缘较少导致PSF估计的不准确问题。实验表明,本文算法可以有效地估计出全景图像不同区域的PSF,有很好的工程使用价值。Because the point spread function （PSF） of the panoramic image is spatially vari ant,an algorithm using Radon transform to estimate the PSF of the localized panoramic image is proposed.We first analyze the panoramic imaging system and the relationship between the Radon transform of the PSF and the blurred lines in the image.Then the effective sampling method is used to get isolated sampling edges.Finally the PSF is restor ed by using the sample information and the image is deblurred by the Lucy-Richardson algorithm.Meanwhile,the iterative optimization algorithm is used to overcome the problem of the less sampling edges,which leads to inaccurate estima tion of the PSF.The experiments show that the algorithm can effectively estimate the PSFs of the different localized panoramic images and i t also can be used in engineering practice.

关 键 词：全景图像 点扩散函数(PSF) 拉东(Radon)变换 图像复原 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]