折/反射全方位视觉空间移变点扩散函数建模与图像复原

Space variant PSF modeling and image restoration for catadioptric omnidirectional vision

在分析折/反射全方位视觉(COV)图像模糊尺度分布规律的基础上提出了一种基于径向边缘检测的空间移变点扩散函数(SV-PSF)建模方法,并且研究了基于一种可以方便地加入空域可变模糊模型等先验知识的凸集投影(POCS)图像复原方法。本文提出的建模方法在有限的径向边界区域建立COV的全局SV-PSF模型,避免了一般建模方法需要大量的边缘检测和图像分割计算;采用基于POCS算法空域图像复原方法,很好容纳了SV-PSF这一先验知识,在实验中与MATLAB的盲反卷积工具箱函数的处理结果进行了对比,结果表明本文方法的灵活性和有效性。

In this paper,space variant point spread function（SV-PSF） modeling is proposed,and image restoration method for the COV is studied.Firstly,a radial edge detection based SV-PSF modeling method is proposed,rest on the analysis of the blur regions′ distribution pattern in the COV image.Then,an image restoration method based on projection onto the convex sets（POCS） is studied;in view of the POCS is such a iterative solution that can be easily joined in the prior information （such as the space variant blur）.The proposed method models global SV-PSF for the COV at limited regions where radial edges locate,avoiding the huge amount of calculation of edge detection and image segmentation.The POCS based restoration method is adopted so that the prior method SV-PSF is utilized well.Experiment results indicate that our method is flexible and efficient by comparing with the result processed by the MATLAB image restoration toolbox.