Spectral unmixing based image restoration for optical remote sensing images covered by thin cloud
基于混合像元分解的薄云下光学遥感图像恢复方法

The obscuring effect of clouds is one of the major factors which restrict the observation capabilities of optical remote sensing satellites. In this paper, aimed at image restoration for optical remote sensing images covered by thin clouds, three contributions have been made. Firstly, with characteristics of clouds, an enhanced linear mixing model has been proposed, in which the influence of clouds on the measured spectra has been presented explicitly. Secondly, two spectral unmixing based image restoration methods have been given, namely the direct elimination method (DEM) and the abundance adjusting method (AAM). At last, with different combinations of the two spectral unmixing algorisms VCA/MDC-NMF and two image restoration methods DEM/AAM, the capabilities and results of relevant methods are analyzed qualitatively and quantitatively, using both simulated and real datasets. Experimental results show that, the combination of MDC-NMF and AAM can achieve the best image restoration result.