Cascade conditional generative adversarial nets for spatial-spectral hyperspectral sample generation  

作　　者：Xiaobo LIU Yulin QIAO Yonghua XIONG Zhihua CAI Peng LIU 

机构地区：[1]School of Automation,China University of Geosciences(Wuhan),Wuhan 430074,China [2]Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems,Wuhan 430074,China [3]Ministry of Education Key Laboratory of Geological Survey and Evaluation,Wuhan 430074,China [4]School of Computer Science,China University of Geosciences(Wuhan),Wuhan 430074,China [5]The Beibu Gulf Big Data Resources Utilization Laboratory,Beibu Gulf University,Qinzhou 535011,China

出　　处：《Science China(Information Sciences)》2020年第4期77-92,共16页中国科学（信息科学）（英文版）

基　　金：supported by National Nature Science Foundation of China(Grant Nos.61973285,61873249,61773355,61603355);National Nature Science Foundation of Hubei Province(Grant No.2018CFB528);Opening Fund of the Ministry of Education Key Laboratory of Geological Survey and Evaluation(Grant No.CUG2019ZR10);Fundamental Research Funds for the Central Universities(Grant No.CUGL17022)。

摘　　要：Sample generation is an effective way to solve the problem of the insufficiency of training data for hyperspectral image classification.The generative adversarial network(GAN)is one of the popular deep learning methods,which utilizes adversarial training to generate the region of samples based on the required class label.In this paper,we propose cascade conditional generative adversarial nets for hyperspectral image complete spatial-spectral sample generation,named C2GAN.The C2GAN includes two stages.The stageone model consists of the spatial information generation with a window size that entails feeding random noise and the required class label.The second stage is the spatial-spectral information generation that generates spectral information of all bands in the spatial region by feeding the label regions.The visualization and verification of generated samples based on the Pavia University and Salinas datasets show superior performance,which demonstrates that our method is useful for hyperspectral image classification.Sample generation is an effective way to solve the problem of the insufficiency of training data for hyperspectral image classification. The generative adversarial network(GAN) is one of the popular deep learning methods, which utilizes adversarial training to generate the region of samples based on the required class label. In this paper, we propose cascade conditional generative adversarial nets for hyperspectral image complete spatial-spectral sample generation, named C^2GAN. The C^2GAN includes two stages. The stageone model consists of the spatial information generation with a window size that entails feeding random noise and the required class label. The second stage is the spatial-spectral information generation that generates spectral information of all bands in the spatial region by feeding the label regions. The visualization and verification of generated samples based on the Pavia University and Salinas datasets show superior performance, which demonstrates that our method is useful for hyperspectral image classification.

关 键 词：HYPERSPECTRAL image sample generation GENERATIVE adversarial nets(GAN) deep learning spatial-spectral information 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程]