Affiliations: [a] School of Electrical Information, City College of Science and Technology, Chongqing University, Yongchuan, Chongqing, China
| [b] College of Optoelectronic Engineering, Chongqing University, Chongqing, Chongqing, China
| [c] Faculty of Computers and Informatics, Zagazig University, Zagazig, Egypt
Correspondence:
[*]
Corresponding author. Yu Gao, School of Electrical Information, City College of Science and Technology, Chongqing University, Yongchuan 402167, Chongqing, China. E-mail: gaoyu@cqucc.edu.cn.
Abstract: Hyperspectral remote sensing combines spectrum, ground space and images organically to provide humans with unprecedented rich information. However, a prominent problem faced in the extraction and identification of hyperspectral remote sensing information is mixed pixels, and the method to solve mixed pixels is mixed pixel decomposition. The purpose of this paper is to study the swarm intelligence algorithm of spatial-spectral feature extraction and mixed pixel decomposition of hyperspectral remote sensing images. This paper first introduces two different methods for extracting spatial spectrum features, then studies linear and non-linear spectral hybrid models, and then studies end element extraction methods based on quantum particle swarm optimization. The degree inversion method, the experimental part is based on the accuracy of the quantum particle swarm optimization-based end-element extraction method and two spatial-spectrum feature extraction methods. The experimental results show that the algorithm proposed in this paper improves the effect of group pixel decomposition based on the swarm intelligence algorithm. The classification accuracy of the 3DLBP spatial spectrum feature proposed in this paper is 94.22%.
