基于S3VM模型的高光谱遥感影像分类

doi:10.13474/j.cnki.11-2246.2017.0376

测绘通报 ›› 2017, Vol. 0 ›› Issue (12): 43-47.doi: 10.13474/j.cnki.11-2246.2017.0376

基于S³VM模型的高光谱遥感影像分类

魏立飞^1,2, 俸秀强¹, 李丹丹³, 牟紫薇^1,2

1. 湖北大学资源环境学院, 湖北武汉 430062;
2. 区域开发与环境响应湖北省重点实验室, 湖北武汉 430062;
3. 农业部农业信息技术重点实验室, 北京 100081

收稿日期:2017-03-15 修回日期:2017-05-24 出版日期:2017-12-25 发布日期:2018-01-05
作者简介:魏立飞(1979-),男,博士生,讲师,主要研究方向为城市遥感及遥感影像智能化处理。E-mail:weilifeihb@163.com
基金资助:
国家自然科学基金（61201341；41371344）；干旱气象科学研究基金（IAM201512）；数字制图与国土信息应用工程国家测绘地理信息局重点实验室开放研究基金（GCWD201407）

Classification of Hyperspectral Remote Sensing Image Based on S³VM Model

WEI Lifei^1,2, FENG Xiuqiang¹, LI Dandan³, MOU Ziwei^1,2

1. Faculty of Resources and Environmental Science, Hubei University, Wuhan 430062, China;
2. Hubei Key Laboratory of Regional Development and Environmental Response, Wuhan 430062, China;
3. Key Laboratory of Agri-informatics, Ministry of Agriculture, P. R. China, Beijing 100081, China

Received:2017-03-15 Revised:2017-05-24 Online:2017-12-25 Published:2018-01-05

摘要/Abstract

摘要： 针对传统的高光谱遥感影像分类受限于训练样本的个数，难以取得较好分类结果的不足，提出了一种基于聚类核的半监督支持向量机（S³VM）模型的高光谱遥感影像分类方法。该算法在半监督支持向量机的体系上加入未标记样本来辅助构建核矩阵，从而获得更优异的分类器，在小样本的基础上提高分类精度。试验结果表明，本文方法的分类精度好于传统方法，并且稳定性良好。

关键词: 高光谱遥感影像, S³VM模型, 未标记样本, 半监督分类

Abstract: The traditional hyperspectral remote sensing image classification is limited by the number of training samples,so it is difficult to obtain the better classification results.This paper proposes a hyperspectral remote sensing image classification method based on semi-supervised support vector machine of clustering kernel.The method constructs a kernel matrix to obtain more excellent classifier by semi-supervised support vector machine and unlabeled sample,and improves classification accuracy based on small sample.The experimental results show that the classification accuracy of this method proposed in this paper is better than the traditional method,and has good stability.

Key words: hyperspectral remote sensing image, S³VM model, unlabeled sample, semi-supervised classification

中图分类号:

P237

魏立飞, 俸秀强, 李丹丹, 牟紫薇. 基于S³VM模型的高光谱遥感影像分类[J]. 测绘通报, 2017, 0(12): 43-47.

WEI Lifei, FENG Xiuqiang, LI Dandan, MOU Ziwei. Classification of Hyperspectral Remote Sensing Image Based on S³VM Model[J]. 测绘通报, 2017, 0(12): 43-47.

参考文献

[1] 张兵,高连如.高光谱图像分类与目标探测[M].北京:科学出版社,2011.
[2] 浦瑞良.高光谱遥感及其应用[M].北京:高等教育出版社,2000.
[3] 雒立群,郭舟,赵文智,等.结合高光谱和高空间分辨率影像提取城市固体废弃物堆[J].测绘通报,2016(2):38-41.
[4] ZHONG Y,ZHANG L,HUANG B,et al.An Unsupervised Artificial Immune Classifier for Multi-hyperspectral Remote Sensing Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(2):420-431.
[5] 谭琨,杜培军.基于再生核Hilbert空间小波核函数支持向量机的高光谱遥感影像分类[J].测绘学报,2011,40(2):142-147.
[6] 丁胜,袁修孝,陈黎.粒子群优化算法用于高光谱遥感影像分类的自动波段选择[J].测绘学报,2010,39(3):257-263.
[7] WAN L,TANG K,LI M,et al.Collaborative Active and Semisupervised Learning for Hyperspectral Remote Sensing Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(5):2384-2396.
[8] 张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
[9] CHERKASSKY V S,MULIER F.Learning from Data:Concepts,Theory,and Methods[M].Wiley:IEEE Press,2007.
[10] VAPNIK V N.An Overview of Statistical Learning Theory[J].IEEE Transactions on Neural Networks,1999,10(5):988-999.
[11] MAYORAZ E,ALPAYDIN E.Support Vector Machines for Multi-class Classification[C]//Procecdings of the International Workshop on Engineering Applications of Bio-Inspired Artificial Neural Networks.[S.l.]:IEEE,1999.
[12] BREDENSTEINER E J,BENNETT K P.Multicategory Classification by Support Vector Machines[J].Computational Optimization and Applications,1999,12(1):53-79.
[13] HSU C W,LIN C J.A Comparison of Methods for Multiclass Support Vector Machines[J].IEEE Transactions on Neural Networks,2002,13(2):415-425.
[14] ZHANG J S,PAN Y Z,HE C Y,et al.The High Spatial Resolution Remote Sensing Image Classification Based on SVM with the Multi-source Data[J].IEEE International Geoscience & Remote Sensing Symposium,2005(6):3818-3821.
[15] ZHANG J S,HE C Y,PAN Y Z,et al.The High Spatial Resolution RS Image Classification Based on SVM Method with the Multi-Source Data[J].Journal of Remote Sensing,2006,10(1):49-57.

基于S³VM模型的高光谱遥感影像分类

Classification of Hyperspectral Remote Sensing Image Based on S³VM Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	谢福鼎, 赫佳妮, 郑宏亮. 半监督离散势理论在遥感影像变化检测中的应用[J]. 测绘通报, 2019, 0(8): 54-58.
[2]	胡冬翠, 谢福鼎, 杨俊, 张永. 一种基于空间信息和遗传算法的半监督高光谱图像分类方法[J]. 测绘通报, 2018, 0(10): 22-26.
[3]	谢福鼎, 李壮. 基于改进的半监督FCM算法的高光谱遥感影像分类[J]. 测绘通报, 2016, 0(9): 60-62,72.