Improvements in the Ant Colony Optimization Algorithm for Endmember Extraction From Hyperspectral Images

Bing Zhang, Jianwei Gao, Lianru Gao, Xu Sun

Abstract: Endmember extraction is a vital step in spectral unmixing of hyperspectral images. The Ant Colony Optimization (ACO) algorithm has been recently developed for endmember extraction from hyperspectral data. However, this algorithm may result in a local optimal solution for some hyperspectral images without prescient information, and also has limitation in computational performance. Therefore, in this paper, we proposed several new methods to improve the ACO algorithm for endmember extraction (ACOEE). Firstly, the heuristic information was optimized to improve the algorithm accuracy. In the improved ACOEE, only the pheromones were adopted as the heuristic information when there was no prescient information about hyperspectral data. Then, to enhance algorithm performance, an elitist strategy was proposed to lessen the iteration numbers without reducing the accuracy, and the parallel implementation of ACOEE on graphics processing units (GPUs) also was utilized to shorten the computational time per iteration. The experiment for real hyperspectral data demonstrated that both the endmember extraction accuracy and the computational performance of ACOEE benefited from these methods.