Hyperspectral Image Classification Based on Novel Binary Particle Swarm with Mutation Mechanism for Band Selection

DOI

10.2991/mmsa-18.2018.56How to use a DOI?

Keywords

binary particle swarm optimization; band selection; parameters determination; mutation mechanism; support vector machines

Abstract

Hyperspectral remote sensing sensors can capture hundreds of narrow contiguous bands and provide plenty of valuable information. Duo to the high-dimension characteristics of hyperspectral data, band selection plays an important role in the field of Hyperspectral Image (HSI) classification. In this paper, a HSI classification method based on Novel Binary Particle Swarm Optimization with mutation mechanism (MNBPSO) for band selection is proposed. First, we present a thorough experimental study to show the superiority of the MNBPSO method. Then we introduce a pre-processing method for feature selection and parameters determination simultaneously based on MNBPSO. Experiments are conducted on the Indian Pines dataset. The evaluation results show that the proposed approach can select those bands with more discriminative information and improve the classification accuracy effectively.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lishuan Hu
AU  - Qun Wang
AU  - Tingyan Xing
PY  - 2018/03
DA  - 2018/03
TI  - Hyperspectral Image Classification Based on Novel Binary Particle Swarm with Mutation Mechanism for Band Selection
BT  - Proceedings of the 2018 International Conference on Mathematics, Modelling, Simulation and Algorithms (MMSA 2018)
PB  - Atlantis Press
SP  - 249
EP  - 253
SN  - 1951-6851
UR  - https://doi.org/10.2991/mmsa-18.2018.56
DO  - 10.2991/mmsa-18.2018.56
ID  - Hu2018/03
ER  -