Effect of Dimensionality Reduction on Sparsity Based Hyperspectral Unmixing

Abstract

Interpretation of hyperspectral data is challenging due to the lack of spatial resolution, which causes mixing of endmember information in each pixel. Hyperspectral unmixing aims at extracting the information related to the fractional abundance of each endmember present in every pixel. The unmixing problem can be carried out by considering that the spectral signature of each endmember is a linear combination of the pure spectral signatures known in prior. In this work, sparse unmixing techniques such as, Orthogonal Matching Pursuit and Alternating Directional Multiplier Methods are applied along with dimensionality reduction of the hyperspectral image. Dimensionality reduction is obtained using the Inter-Band Block Correlation followed by singular value and QR decomposition (SVD-QR). Furthermore, we analyze the effect of dimensionality reduction on two different unmixing algorithms. Our experimentation is carried out on two real hyperspectral datasets namely ‘samson’ and ‘jasper ridge’ and the results comprises of a comparison between hyperspectral unmixing before and after dimensionality reduction using the standard metrics such as root mean square error, classwise-accuracy and visual perception. This provides a new outlook for the unmixing process as abundance estimation can be done with only the most informative bands of the image instead of using the entire data by using the dimensionality reduction technique.