Progressive Band Processing of Simplex Growing Algorithm for Finding Endmembers in Hyperspectral Imagery

This paper presents a progressive band processing (PBP) version of an endmember finding algorithm, simplex growing algorithm (SGA), to be called PBP-SGA, which allows users to perform SGA band by band progressively. Several advantages can be gained from this approach. First of all, PBP-SGA does not require data dimensionality reduction since PBP begins with a lower band dimension and gradually increases band dimensions band by band progressively until it achieves the desired results. Secondly, PBP can process SGA whenever bands are available without waiting for the information from all band information to be received. As a result, PBP-SGA can be used for data transmission and communication. Thirdly, PBP-SGA can help identify which bands are crucial during the process of finding endmembers. Finally, PBP-SGA provides feasibility of being implemented in real time according to Band SeQuential (BSQ) format.