首页 > 论文 > 光学学报 > 39卷 > 10期(pp:1028002--1)

基于双通道GAN的高光谱图像分类算法

Hyperspectral Image Classification Algorithm Based on Two-Channel Generative Adversarial Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

高光谱图像分类问题是高光谱遥感图像处理问题中的研究基础,它的主要目的是根据高光谱遥感图像中的光谱信息和空间信息将图像中的每个像元划分为不同的地物类别[1]。高光谱图像分类技术被广泛应用于环境监测、矿产勘探、军事目标识别等领域,然而高光谱图像的高维特性、波段间的高度相关性、光谱混合等使得高光谱图像分类面临着巨大的挑战。因此,高光谱图像分类问题越来越受到学者们的广泛关注[2-4]。

Abstract

The existing hyperspectral image generative adversarial network(GAN) classification algorithm cannot fully extract spectral and spatial-spectral features, which leads to the degradation of hyperspectral image classification accuracy. To resolve this issue, this study proposes a hyperspectral image classification algorithm based on a two-channel GAN. Improved one- and two-dimensional GAN classification frameworks are used to extract complete spectral and spatial-spectral features, respectively. Those features are nonlinearly fused to form a more comprehensive spatial-spectral features for classification. The experiments on two commonly used hyperspectral image datasets show that the proposed algorithm achieves the best classification accuracy; further, the results verify the effectiveness and advantages of the proposed algorithm.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/AOS201939.1028002

所属栏目:遥感与传感器

基金项目:国家自然科学基金;

收稿日期:2019-02-22

修改稿日期:2019-06-21

网络出版日期:2019-10-01

作者单位    点击查看

毕晓君:中央民族大学信息工程学院, 北京 100081
周泽宇:哈尔滨工程大学信息与通信工程学院, 黑龙江 哈尔滨 150001

联系人作者:周泽宇(zhouzeyu100@hrbeu.edu.cn)

备注:国家自然科学基金;

【1】Cui Y, Xu K, Lu Z J et al. Combination strategy of active learning for hyperspectral images classification. Journal on Communications. 39(4), (2018).
崔颖, 徐凯, 陆忠军 等. 主动学习策略融合算法在高光谱图像分类中的应用. 通信学报. 39(4), (2018).

【2】Dong A G, Li J X, Zhang B et al. Hyperspectral image classification algorithm based on spectral clustering and sparse representation. Acta Optica Sinica. 37(8), (2017).
董安国, 李佳逊, 张蓓 等. 基于谱聚类和稀疏表示的高光谱图像分类算法. 光学学报. 37(8), (2017).

【3】Hou B H, Yao M L, Wang R et al. Spatial-spectral semi-supervised local discriminant analysis for hyperspectral image classification. Acta Optica Sinica. 37(7), (2017).
侯榜焕, 姚敏立, 王榕 等. 面向高光谱图像分类的空谱半监督局部判别分析. 光学学报. 37(7), (2017).

【4】Yu C Y, Zhao M, Song M P et al. Hyperspectral image classification method based on targets constraint and spectral-spatial iteration. Acta Optica Sinica. 38(6), (2018).
于纯妍, 赵猛, 宋梅萍 等. 基于目标约束与谱空迭代的高光谱图像分类方法. 光学学报. 38(6), (2018).

【5】Chen Y S, Jiang H L, Li C Y et al. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing. 54(10), 6232-6251(2016).

【6】Li Y, Zhang H K and Shen Q. Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sensing. 9(1), (2017).

【7】Wu H and Prasad S. Convolutional recurrent neural networks for hyperspectral data classification. Remote Sensing. 9(3), (2017).

【8】Zhao W Z and Du S H. Spectral-spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach. IEEE Transactions on Geoscience and Remote Sensing. 54(8), 4544-4554(2016).

【9】Aptoula E, Ozdemir M C and Yanikoglu B. Deep learning with attribute profiles for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters. 13(12), 1970-1974(2016).

【10】Zhang H K, Li Y and Jiang Y N. Deep learning for hyperspectral imagery classification: the state of the art and prospects. Acta Automatica Sinica. 44(6), 961-977(2018).
张号逵, 李映, 姜晔楠. 深度学习在高光谱图像分类领域的研究现状与展望. 自动化学报. 44(6), 961-977(2018).

【11】Goodfellow I J, Pouget-Abadie J, Mirza M et al. Generative adversarial nets[C]∥Proceedings of the 27th International Conference on Neural Information Processing Systems, December 8-13, 2014, Montreal, Canada. Cambridge, MA,. 2, 2672-2680(2014).

【12】Zhan Y, Hu D, Wang Y T et al. Semisupervised hyperspectral image classification based on generative adversarial networks. IEEE Geoscience and Remote Sensing Letters. 15(2), 212-216(2018).

【13】Zhu L, Chen Y S, Ghamisi P et al. Generative adversarial networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing. 56(9), 5046-5063(2018).

【14】Radford A and Metz L. -01-07)[2019-02-10]. https: ∥arxiv. org/abs/1511, (2016).

【15】Yang S S. Research on conditional generative adversarial networks model based on VAE. Changchun: Jilin University. 26-29(2018).
杨韶晟. 基于VAE的条件生成式对抗网络模型研究. 长春: 吉林大学. 26-29(2018).

【16】Odena A, Olah C and Shlens J. Conditional image synthesis with auxiliary classifier GANs. [C]∥Proceedings of the 34th International Conference on Machine Learning, August 6-11, 2017, Sydney, Australis. Massachusetts: JMLR. org. 2642-2651(2017).

【17】Ma X R. Hyperspectral imagery classification based on deep learning. Dalian: Dalian University of Technology. 30-31(2017).
马晓瑞. 基于深度学习的高光谱影像分类方法研究. 大连: 大连理工大学. 30-31(2017).

引用该论文

Xiaojun Bi,Zeyu Zhou. Hyperspectral Image Classification Algorithm Based on Two-Channel Generative Adversarial Network[J]. Acta Optica Sinica, 2019, 39(10): 1028002

毕晓君,周泽宇. 基于双通道GAN的高光谱图像分类算法[J]. 光学学报, 2019, 39(10): 1028002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF