首页 | 本学科首页   官方微博 | 高级检索  
     

面向高光谱影像分类的生成式对抗网络
引用本文:张鹏强,刘冰,余旭初,谭熊,杨帆,周增华. 面向高光谱影像分类的生成式对抗网络[J]. 测绘通报, 2020, 0(3): 29-34. DOI: 10.13474/j.cnki.11-2246.2020.0073
作者姓名:张鹏强  刘冰  余旭初  谭熊  杨帆  周增华
作者单位:1. 信息工程大学, 河南 郑州 450001;2. 31009部队, 北京 100088
基金项目:河南省科技攻关计划项目(152102210014);信息工程大学自主科研课题(41201477)。
摘    要:为了提高高光谱影像分类精度,提出了一种基于生成式对抗网络的高光谱影像分类方法。生成式对抗网络由生成器、判别器和分类器3部分组成,其中生成器用于模拟高光谱样本的数据分布,生成特定类别的样本;判别器是一个二值分类器,用于判断输入的样本是否为真实数据;分类器用于对输入的样本进行分类。利用反向传播算法依次更新生成器、判别器和分类器的网络参数使损失函数最小,从而达到训练网络的目的。生成器和判别器能够模拟高光谱影像的样本分布来辅助训练分类器,因此能够提高高光谱影像的分类精度。分别采用Pavia大学和Salinas高光谱数据集进行分类试验,试验结果表明提出的分类方法能够在小样本条件下提高高光谱影像的分类精度。

关 键 词:高光谱影像分类  小样本  生成式对抗网络  深度学习  生成模型
收稿时间:2019-06-20
修稿时间:2020-01-13

Generative adversarial networks for hyperspectral image classification
ZHANG Pengqiang,LIU Bing,YU Xuchu,TAN Xiong,YANG Fan,ZHOU Zenghua. Generative adversarial networks for hyperspectral image classification[J]. Bulletin of Surveying and Mapping, 2020, 0(3): 29-34. DOI: 10.13474/j.cnki.11-2246.2020.0073
Authors:ZHANG Pengqiang  LIU Bing  YU Xuchu  TAN Xiong  YANG Fan  ZHOU Zenghua
Affiliation:1. Information Engineering University, Zhengzhou 450001, China;2. Troops 31009, Beijing 100088, China
Abstract:In order to improve the classification accuracy of hyperspectral images,a novel hyperspectral image classification method based on generative adversarial network is proposed. The proposed generative adversarial network consists of generator,discriminator and classifier,in which the generator is used to approximate the data distribution of hyperspectral samples and generate specific categories of samples. The discriminator is a binary classifier to determine whether the input samples are real data. And the classifier is used to classify the input samples. The parameters of generator,discriminator and classifier are updated sequentially by back propagation algorithm to minimize the loss function,so as to achieve the goal of training the network. Generators and discriminators can approximate the sample distribution of hyperspectral images to assist the training of the classifier. Therefore,they can effectively improve the classification accuracy of hyperspectral images. Pavia University and Salinas hyperspectral data sets are used for classification experiments respectively. The experimental results show that the proposed classification method can effectively improve the classification accuracy of hyperspectral images with only small samples.
Keywords:hyperspectral image classification  small samples  generative adversarial networks  deep learning  generative models
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《测绘通报》浏览原始摘要信息
点击此处可从《测绘通报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号