[1]刘群,陈锻生.采用ACGAN及多特征融合的高光谱遥感图像分类[J].华侨大学学报(自然科学版),2019,40(1):113-120.[doi:10.11830/ISSN.1000-5013.201710006]
　LIU Qun,CHEN Duansheng.Classification of Hyperspectral Remote Sensing Images Using ACGAN and Fusion of Multifeature[J].Journal of Huaqiao University(Natural Science),2019,40(1):113-120.[doi:10.11830/ISSN.1000-5013.201710006]
点击复制

采用ACGAN及多特征融合的高光谱遥感图像分类()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第40卷
期数:
2019年第1期
页码:
113-120
栏目:
出版日期:
2019-01-20

文章信息/Info

Title:
Classification of Hyperspectral Remote Sensing Images Using ACGAN and Fusion of Multifeature
文章编号:
1000-5013(2019)01-0113-08
作者:
刘群;  陈锻生
华侨大学 计算机科学与技术学院, 福建 厦门 361021
Author(s):
LIU Qun;  CHEN Duansheng
College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China
关键词:
高光谱图像分类;  生成对抗网络;  局部二值模式;  卷积神经网络
Keywords:
hyperspectral image classification;  generative adversarial networks;  local binary pattern;  convolutional neural networks
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201710006
文献标志码:
A
摘要:
为解决标记样本缺乏、提升分类精度及增强模型容错性等问题,提出一种基于辅助分类器生成对抗网络(ACGAN)的分类方法.首先,将预训练的ACGAN模型作为光谱特征提取器,采用局部二值模式(LBP)算法提取图像的纹理特征;然后,融合光谱特征和纹理特征,由卷积神经网络(CNN)进行分类.在2个广泛使用的数据集上进行实验,结果表明:相较于其他方法,文中方法可显著提高分类精度.
Abstract:
In oder to solve the problem for lack of labeled samples, improve the classification accuracy and enhance the fault tolerance of the model, a hyperspectral sensing image classification method based on auxiliary classifier generative adversarial network(ACGAN)is proposed. Firstly, the pre-trained ACGAN model is treated as a spectral feature extractor, and the texture features of the image are extracted by local binary pattern(LBP)algorithm. Then, the spectral features and texture features are merged and calssified by convolutional neural network(CNN). Experiments on two widely used datasets show that compared with other methods, the proposed method can significantly improve the classification accuracy.

参考文献/References:

[1] 刘雪松,葛亮,王斌,等.基于最大信息量的高光谱遥感图像无监督波段选择方法[J].红外与毫米波学报,2012,31(2):166-170.
[2] 吴培强,张杰,马毅,等.基于地物光谱可分性的CHRIS高光谱影像波段选择及其分类应用[J].海洋科学,2015,39(2):20-24.DOI:10.11759/hykx20141011007.
[3] 许明明,张良培,杜博,等.基于类别可分性的高光谱图像波段选择[J].计算机科学,2015,42(4):274-275.
[4] MARTÍNEZ-USÓMARTINEZ-USO A,PLA F,SOTOCA J M,et al.Clustering-based hyperspectral band selection using information measures[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(12):4158-4171.DOI:10.1109/TGRS.2007.904951.
[5] 施蓓琦,刘春,孙伟伟,等.应用稀疏非负矩阵分解聚类实现高光谱影像波段的优化选择[J].测绘学报,2013,42(3):351-358.
[6] 张连蓬.基于投影寻踪和非线性主曲线的高光谱遥感图像特征提取及分类研究[D].青岛:山东科技大学,2003.
[7] 吴波,周小成,高海燕.面向混合像元分解的光谱维小波特征提取[J].华侨大学学报(自然科学版),2008,29(1):156-160.DOI:10.11830/ISSN.1000-5013.2008.01.0156.
[8] DATTA A,GHOSH S,GHOSH A.Unsupervised band extraction for hyperspectral images using clustering and kernel principal component analysis[J].International Journal of Remote Sensing,2017,38(3):850-873.
[9] 孙宁,邓承志,汪胜前.基于滤波后处理的主动学习高光谱遥感图像分类[J].南昌工程学院学报,2015(1):7-11.DOI:10.3969/j.issn.1006-4869.2015.01.002.
[10] 王巧玉,陈锻生.结合波段选择和保边去噪滤波的高光谱遥感图像分类[J].小型微型计算机系统,2017,38(5):1098-1102.DOI:10.3969/j.issn.1000-1220.2017.05.036.
[11] GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial networks[J].Advances in Neural Information Processing Systems,2014,3:2672-2680.
[12] HE Zhi,LIU Han,WANG Yiwen,et al.Generative adversarial networks-based semi-supervised learning for hyperspectral image classification[J].Remote Sensing,2017,9(10):1042.DOI:10.3390/rs9101042.
[13] LIN Daoyu,FU Kun,WANG Yang,et al.MARTA GANs: Unsupervised representation learning for remote sensing image classification[J].IEEE Geoscience and Remote Sensing Letters,2017,14(11):2092-2096.
[14] ARINALDI A,FANANY M I.Generating single subject activity videos as a sequence of actions using 3D convolutional generative adversarial networks[C]//International Conference on Artificial General Intelligence.Berlin:Springer,2017:133-142.
[15] PIETIKAEINEN M,OJALA T,NISULA J,et al.Experiments with two industrial problems using texture classification based on feature distributions[J].Proc Spie,1994,2354:197-204.DOI:10.1117/12.189087.
[16] 王春来,张森原,崔璐,等.训练样本数量选择和总体分类精度的关系研究[J].河南城建学院学报,2015(3):51-55.DOI:10.14140/j.cnki.hncjxb.2015.03.012.
[17] WU Bo,CHEN Chongcheng,KECHADI T M,et al.A comparative evaluation of filter-based feature selection methods for hyper-spectral band selection[J].International Journal of Remote Sensing,2013,34(22):7974-7990.
[18] 樊利恒,吕俊伟,于振涛,等.基于核映射多光谱特征融合的高光谱遥感图像分类法[J].光子学报,2014,43(6):87-92.DOI:10.3788/gzxb20144306.0630001.
[19] 李祖传,马建文,张睿,等.利用SVM-CRF进行高光谱遥感数据分类[J].武汉大学学报(信息科学版),2011,36(3):306-310.DOI:10.13203/j.whugis2011.03.009.
[20] MONSERU R A,LEEMANSB R.Comparing global vegetation maps with the Kappa statistic[J].Ecological Modelling,1992,62(4):275-293.DOI:10.1016/0304-3800(92)90003-W.

备注/Memo

备注/Memo:
收稿日期: 2017-10-17
通信作者: 陈锻生(1959-),男,教授,博士,主要从事数字图像处理与模式识别的研究.E-mail:dschen@hqu.edu.cn.
基金项目: 国家自然科学基金面上资助项目(61370006); 福建省科技计划重点资助项目(2015H0025)
更新日期/Last Update: 2019-01-20