A Band Selection Method for Hyperspectral Image Based on Particle Swarm Optimization Algorithm with Dynamic Sub-Swarms

Abstract

Band selection is an effective means to reduce the hyperspectral data size and to overcome the Hughes phenomenon in ground object classification. This paper presents a band selection method based on particle swarm dynamic with sub-swarms optimization, aiming at the deficiency of particle swarm optimization algorithm being easy to fall into local optimum when applied to hyperspectral image band selection. This algorithm treats fitness function as criterion, dividing all particles into different adaptation degree interval corresponding to the dynamic subgroup and adopting different optimization methods for different subgroups as well as sub -swarms parallel iterative searching for the optimal band. In this way, we can make achievement of clustering optimization of particle with different optimization capability, ensuring the diversity of particles in order to reduce the risk of falling into local optimum. Finally, we prove the effectiveness of this algorithm through selected bands validation by support vector machine.