ABSTRACT
A method for generating natural color composite of satellite images based on local endmembers of ground features was proposed. First, the reference satellite image which has similar land cover types with the target satellite image is segmented into multiple local patches. Secondly, endmembers of ground features are extracted from each local patch, then we choose better end-members and gather them into a sample set. Thirdly, we use the sample set to build up the relationship between the spectral values of the blue band and the other bands. Finally, the spectrum relationship is used to generate natural color composite of the target image. The verification experiment on Landsat TM5 images shows that the proposed method is reliable and stable to generate the natural color composite of images. The other experiment on IRS-P6 images shows that our method is able to promote for other satellite images. In experiments, we also compared the existing "reference image-image" method and "spectral library-image" method qualitatively and quantificationally, indicating that our method is more precise to simulate spectrums of all kinds of ground features.
ABSTRACT
Due to the problem that the convex cone analysis (CCA) method can only extract limited endmember in multispectral imagery, this paper proposed a new endmember extraction method by spatial adaptive spectral feature analysis in multispectral remote sensing image based on spatial clustering and imagery slice. Firstly, in order to remove spatial and spectral redundancies, the principal component analysis (PCA) algorithm was used for lowering the dimensions of the multispectral data. Secondly, iterative self-organizing data analysis technology algorithm (ISODATA) was used for image cluster through the similarity of the pixel spectral. And then, through clustering post process and litter clusters combination, we divided the whole image data into several blocks (tiles). Lastly, according to the complexity of image blocks' landscape and the feature of the scatter diagrams analysis, the authors can determine the number of endmembers. Then using hourglass algorithm extracts endmembers. Through the endmember extraction experiment on TM multispectral imagery, the experiment result showed that the method can extract endmember spectra form multispectral imagery effectively. What's more, the method resolved the problem of the amount of endmember limitation and improved accuracy of the endmember extraction. The method has provided a new way for multispectral image endmember extraction.
