Fusion of remote sensing images

Recently, there has been greater interest in the Hyper spectral (HS) sensing technology as the information that resides in the HS spectral domain provides significant advantages over the traditional Multi spectral images. The inherent tradeoff between the spectral and spatial resolutions has resulted in the development of remote sensing systems that include fusion of Hyper spectral image and Multi spectral image taken over the same image scene. In this proposed work Matrix Factorization (MF) Un mixing based fusion method is used for the fusion of the HS image and the MS image to produce a fused image data that will be enhanced in terms of its both spatial and spectral qualities which in turn contributes for the accurate identification and classification of various materials in the observed image scene. This algorithm is very straight forward and easy to implement owing to its simple update rules. The effectiveness of the proposed fusion technique for fusion of HS image and MS image over the other traditional fusion techniques like wavelet based fusion and IHS fusion, is analyzed in terms of the spatial and spectral performance metrics.