Endmember Extraction of Hyperspectral Remote Sensing Images Based on the Discrete Particle Swarm Optimization Algorithm

This paper described endmember extraction as a combinatorial optimization problem (COP). By defining particles´ position and velocity, discrete particle swarm optimization (D-PSO) was proposed based on particle swarm optimization to resolve COP. The algorithm was tested and evaluated by hyperspectral remote sensing data. Experimental results showed that, while extracting the same number of endmembers, D-PSO could get a smaller root-mean-square error between an original image and its remixed image on the precondition of correct extraction results compared to the algorithms of vertex component analysis (VCA) and N-FINDR, which meant that D-PSO could acquire higher extraction precision.