Open AccessCBS-GAN: A Band Selection Based Generative Adversarial Net for Hyperspectral Sample Generation
Author(s) -
Yulin Qiao,
Mostofa Zaman Mohammad,
Yang Li,
Xiaobo Liu,
Zhihua Cai
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/734/1/012035
Subject(s) - hyperspectral imaging , sample (material) , computer science , net (polyhedron) , artificial intelligence , pattern recognition (psychology) , selection (genetic algorithm) , generative adversarial network , generative grammar , data mining , image (mathematics) , mathematics , physics , geometry , thermodynamics
Sample generation is an effective method to improve the performance of hyperspectral image classification by generating virtual samples for training sample expansion in the training process of classification. However, there are some defects existing in the previous sample generation methods including the lack of spatial information, the redundant generation and the damage of the original spectral components. In this paper, we propose conditional band selection generative adversarial net, named CBS-GAN, to handle this problem. Firstly, the band selection net of CBS-GAN is utilized to avoid redundant bands and keep original spectral information, then the generation net of CBS-GAN generates the spatial-spectral data blocks by selected bands for sample generation. The experiments of classification are also used to demonstrate the availability of virtual samples generated by our method.