基于小波变换的多波段遥感图像条带噪声的去除

Destriping Multi-sensor Imagery Based on Wavelet Transform

介绍了几种在TM,MSS,SPOT等多传感器遥感图像中条带噪声去除方法的特点,提出了一种基于小波变换的条带噪声去除方法,并以几何纠正前的非均匀地物分布的CMODIS图像为实验数据,对这些方法的去条带噪声效果作了比较。结果表明,本文提出的方法要优于以前的几种常用方法,具有很好的去条带效果,同时较好地保持了原图像的特征。这种方法在其它多传感器遥感图像的条带噪声去除中也有很强的适用性。

CMODIS contains abundant spectral information with 34 channels in the range from visible to infrared. But sensor to sensor variation within instrument often leads to striping in many channels of CMODIS. The striping noise can distractingly and obstructively affects the interpretation and application of CMODIS data. This paper discusses the method previously used in striping removal of TM, MSS , MOS- B and presnts a new method based on wavelet transform. The application results of the method to non-geometrically corrected CMODIS data and quantitative analysis of the results show that the new method can achieve the better result than the previously used ones and preserve the spectral characteristic of original image . The new method is also applicable in striping removal of other multi-sensor remote sensing data.