Towards the acceleration of sequential endmember extraction algorithms for time critical applications

Abstract

This paper presents a new strategy in order to accelerate the execution of sequential endmember extraction algorithms without compromising their performance in terms of the accuracy of the estimated endmembers. In particular, our proposal takes advantage of the correlation between pixels located in adjacent spatial positions as well as of the information provided by the dimensionality reduction step that takes place priors to the endmember extraction itself. The results demonstrate that when the proposed strategy is applied to the well-known Vertex Component Analysis (VCA) sequential algorithm, almost half of the computing time is saved with negligible variations in the quality of the endmembers extracted. Moreover, this is achieved with independence of the amount of noise and/or the number of endmembers of the hyperspectral image under processing.