利用频谱解混叠方法实现超分辨率影像重建  

Super-resolution Image Restoration by Spectral De-aliasing

作　　者：钦桂勤[1] 耿则勋[1] 徐青[1] 

机构地区：[1]信息工程大学测绘学院,河南郑州450052

出　　处：《测绘学报》2003年第2期143-147,共5页Acta Geodaetica et Cartographica Sinica

摘　　要：基于信号处理的超分辨率影像重建技术,可以消除由影像系统引起的影像模糊和退化,同时恢复出光学极限外的频谱信息。首先简要介绍了超分辨率影像重建技术的意义和基本过程;并对影像配准与运动模型估计在超分辨率影像重建中的作用给予简要介绍;接着根据连续傅里叶变换(CFT)和离散傅里叶变换(DFT)的频谱混叠关系及CFT位移性质,推导出频谱解混叠的超分辨率影像重建模型;最后采用文献中的运动模型估计方法和本文的重建算法,对几组数据进行实验,获得了空间分辨率提高近1倍的影像。Superresolution technology is the siginal processing based methods in software. It can remove the blur caused by the imaging system as well as recover spatial frequency information beyond the diffraction limit of the optical system.First this paper gives a brief introduction of superresolution effect and process. And the status and relation of registration and motion estimate in image restoration are presented. Then in order to restore a highresolution image from a sequence of lowresolution, undersampled, discrete frames, this paper presents a new algorithm with reduced the aliasing relationship between the undersampled frames and the reference image. Fullly utilizing the shifts evaluated by the motion estimate that the literature offers, we propose a general formula of restoration in wavenumber domain. Finally success in the use of the algorithm is demonstrated through various simulated examples which afford highresolution image with nearly 2 times resolution as the undersampled frames.

关 键 词：信号处理 超分辨率影像重建技术 频谱信息 影像配准 运动模型估计 影像重建 地球资源卫星 多光谱影像 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]