A Mutation Operator Accelerated Quantum-Behaved Particle Swarm Optimization Algorithm for Hyperspectral Endmember Extraction

Mingming Xu,Bo Du,Liangpei Zhang,Yanguo Fan,Dongmei Song,Lefei Zhang

doi:10.3390/rs9030197

Abstract

The endmember extraction algorithm, which selects a collection of pure signature spectra for different materials, plays an important role in hyperspectral unmixing. In this paper, the endmember extraction algorithm is described as a combinatorial optimization problem and a novel Mutation Operator Accelerated Quantum-Behaved Particle Swarm Optimization (MOAQPSO) algorithm is proposed. The proposed approach employs Quantum-Behaved Particle Swarm Optimization (QPSO) to find endmembers with good performances. To the best of our knowledge, this is the first time that QPSO has been introduced into hyperspectral endmember extraction. In order to follow the law of particle movement, a high-dimensional particle definition is proposed. In addition, in order to avoid falling into a local optimum, a mutation operation is used to increase the population diversity. The proposed MOAQPSO algorithm was evaluated on both synthetic and real hyperspectral data sets. The experimental results indicated that the proposed method obtained better results than other state-of-the-art algorithms, including Vertex Component Analysis (VCA), N-FINDR, and Discrete Particle Swarm Optimization (D-PSO).

Highlights

Dozens or even hundreds of narrow, adjacent spectral bands can effectively represent the unique materials in hyperspectral remote sensing images
Popular pure pixel based algorithms include the Pixel Purity Index (PPI) [16], N-FINDR [17], the Simplex Growing Algorithm (SGA) [18], and Vertex Component Analysis (VCA) [19], as well as some new swarm intelligence algorithms proposed in recent years, such
In this paper we introduced Quantum-Behaved Particle Swarm Optimization (QPSO) to endmember extraction, which to the best of our knowledge has not previously been used for this purpose

Summary

Introduction

Dozens or even hundreds of narrow, adjacent spectral bands can effectively represent the unique materials in hyperspectral remote sensing images. Spectral unmixing is a technique that decomposes the mixed-pixel spectra into a collection of pure spectra, named endmembers, and the corresponding abundance fractions of each endmember [3,4,5,6,7,8]. Simplex theory is one of the most important theories on which many endmember extraction algorithms are based. Popular pure pixel based algorithms include the Pixel Purity Index (PPI) [16], N-FINDR [17], the Simplex Growing Algorithm (SGA) [18], and Vertex Component Analysis (VCA) [19], as well as some new swarm intelligence algorithms proposed in recent years, such

Methods

Discussion

Conclusion