Shadow detection using index-based principal component analysis of satellite images

In remote sensing, satellite images are shown vital role analyzing the information about the land surface area and atmosphere related applications without physical contact. Satellite images are given high resolution images, due to sun angle the earth object shadow appears on land surface, its gives wrong information about object. The identification of shadow is very important for getting detailed information of perticulr object. In this paper proposes an effective procedure for shadow detection for high resolution multispectral satellite images. shadow index based principal component analysis developed for shadow detection in more than one band of land sat data. Shadow detector index distinguishes shadow and non shadow pixels based on spectral difference. The proposed method is compared with other state of the art methods experimentally gives superior results in terms of qualitatively and quantitatively.