一种新的两分类器融合的空谱联合高光谱分类方法

doi:10.3969/j.issn.0372-2112.2015.11.011

电子学报 ›› 2015, Vol. 43 ›› Issue (11): 2210-2217.DOI: 10.3969/j.issn.0372-2112.2015.11.011

一种新的两分类器融合的空谱联合高光谱分类方法

孙乐^1,2, 吴泽彬³, 冯灿⁴, 刘建军³, 肖亮³, 韦志辉³

1. 江苏省网络监控工程中心, 江苏南京 210044;
2. 南京信息工程大学计算机与软件学院, 江苏南京 210044;
3. 南京理工大学计算机科学与工程学院, 江苏南京 210094;
4. 北方信息控制集团软件中心, 江苏南京 211153

收稿日期:2014-02-27 修回日期:2014-07-30 出版日期:2015-11-25
- 作者简介:
- 孙乐男,1987年生于江苏宿迁.博士,南京信息工程大学讲师.研究方向为高光谱遥感图像解混、分类和目标识别.E-mail:sunlecncom@163.com;吴泽彬 男,1977年生于浙江杭州.南京理工大学计算机科学与工程学院副教授.研究方向为数据挖掘、虚拟仿真、高光谱图像处理.E-mail:zebin.wu@gmail.com
- 基金资助:
- 国家自然科学基金 (No.61101194,No.61301215,No.61301217); 国家自然科学基金面上项目 (No.61471199); 江苏省气象探测与信息处理重点实验室开放课题 (No.KDXS1404); 江苏省自然科学基金 (青年项目) (No.BK20150923); 南京信息工程大学人才启动经费; 江苏省光谱成像与智能感知重点实验室开放课题

A Novel Two-Classifier Fusion Method for Spectral-Spatial Hyperspectral Classification

SUN Le^1,2, WU Ze-bin³, FENG Can⁴, LIU Jian-jun³, XIAO Liang³, WEI Zhi-hui³

1. Jiangsu Engineering Center of Network Monitoring, Nanjing, Jiangsu 210044, China;
2. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, Jiangsu 210044, China;
3. Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China;
4. Software Center of China North Industries Group Corporation, Nanjing, Jiangsu 211153, China

Received:2014-02-27 Revised:2014-07-30 Online:2015-11-25 Published:2015-11-25

摘要/Abstract

摘要：

本文提出一种两分类器融合的高光谱空谱联合分类方法,首先利用子空间多项式逻辑回归在图像的特征子空间中分类,得到满概率图;根据满概率将每个像元分至概率最大的两个最可信类别,并在原始空间中构建最可信类别字典,利用稀疏解混对每个像元在最可信类别字典下进行稀疏表示,得到稀疏概率图;最后将满概率图和稀疏概率图线性融合,并利用边缘保持的马尔可夫正则项挖掘图像空间信息,得到具有边缘保持的空谱分类模型.实验表明,提出的两分类器融合方法即使在训练样本较少时也比现有方法得到更好的分类结果.

关键词: 高光谱分类, 子空间逻辑回归, 稀疏解混, 多分类器, 马尔可夫正则项

Abstract:

This paper presents a new multiple-classifier approach for spectral-spatial classification of hyperspectral images(HSI).Firstly,subspace based multinomial logistic regression(MLRsub) method is used to calculate the full probability of each pixel in the feature space;Secondly,the sub-dictionary is constructed by the training samples of the most two reliable classes,which is determined by the full probability for each pixel.Then,sparse unmixing(SU) is used to calculate the sparse probability in the original HSI.Finally,the full probability and sparse probability are fused linearly and the spatial information is exploit by an edge preserving Markov random field(MRF) regularizer.Experimental results indicate that our proposed multiple-classifier leads to better classification performance than the state-of-the-art methods,even with small training samples.

Key words: hyperspectral classification, subspace multinomial logistic regression, sparse unmixing, multiple classifier, MRF regularizer

中图分类号:

TP751

孙乐, 吴泽彬, 冯灿, 刘建军, 肖亮, 韦志辉. 一种新的两分类器融合的空谱联合高光谱分类方法[J]. 电子学报, 2015, 43(11): 2210-2217.

SUN Le, WU Ze-bin, FENG Can, LIU Jian-jun, XIAO Liang, WEI Zhi-hui. A Novel Two-Classifier Fusion Method for Spectral-Spatial Hyperspectral Classification[J]. Acta Electronica Sinica, 2015, 43(11): 2210-2217.

参考文献

[1] 童庆禧,张兵,郑兰芬.高光谱遥感-原理、技术与应用[M]. 北京:高等教育出版社,2006. Tong Qingxi,Zhang Bing,Zheng Lanfen.Hyperspectral Remote Sensing[M]. Beijing:Higher Education Press,2006.(in Chinese)
[2] 吴泽彬,韦志辉,孙乐,刘建军.基于迭代加权L1正则化的高光谱混合像元分解[J]. 南京理工大学学报,2011,35(4):431-435. Wu Zebin,Wei Zhihui,Sun Le,Liu Jian-jun.Hyperspectral unmixing based on iterative weighted L1 regularization[J]. Journal of Nanjing University of Science and Technology,2011,35(4):431-435.(in Chinese)
[3] 宋相法,焦李成.基于稀疏表示及光谱信息的高光谱遥感图像分类[J]. 电子与信息学报,2012,34(2):268-272. Song Xiangfa,Jiao Licheng.Classification of hyperspectral remote sensing image based on sparse representation and spectral information[J]. Journal of Electronics and Information Technology,2012,34(2):268-272.(in Chinese)
[4] 刘建军,吴泽彬,韦志辉,肖亮,孙乐.基于约束非负矩阵分解的高光谱图像解混快速算法[J]. 电子学报,2013,41(3):432-437. Liu Jianjun,Wu Zebin,Wei Zhihui,Xiao Liang,Sun Le.A fast algorithm for hyperspectral unmixing based on constrained nonnegative matrix factorization[J]. Acta Electronica Sinica,2013,41(3):432-437.(in Chinese)
[5] Melgani F,Bruzzone L.Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE Trans Geosci Remote Sensing,2011,42(8):1778-1790.
[6] Fauvel M,Benediktsson J,et al.Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles[J]. IEEE Trans Geosci Remote Sensing,2008,46(11):3804-3814.
[7] Li Jun,Bioucas-Dias J,Plaza A.Spectral-spatial classification of hyperspectral data using loopy belief propagation and active learning[J]. IEEE Trans Geosci Remote Sensing,2013,51(2):844-856.
[8] Li Jun,Bioucas-Dias J,Plaza A.Semi-supervised hyperspectral image segmentation using multinomial logistic regression with active learning[J]. IEEE Trans Geosci Remote Sensing,2010,48(11):4085-4098.
[9] Li Jun,Bioucas-Dias J,Plaza A.Spectral-spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random fields[J]. IEEE Trans Geosci Remote Sensing,2012,50(3):809-823.
[10] Yi Chen,Nasrabadi N M,Tran D.Hyperspectral image classification using dictionary-based sparse representation[J]. IEEE Trans Geosci Remote Sensing,2011,49(10):3973-3985.
[11] Plaza A,Benediktsson A,et al.Recent advances in techniques for hyperspectral image processing[J]. Remote Sensing of Environment,2009,113:S110-S122.
[12] Camps-Valls G,GomeZ-Chova L,et al.Composite kernels for hyperspectral image classification[J]. IEEE Trans Geosci Remote Sensing Lett,2006,3(1):93-97.
[13] Tarabalka Y,Benedikstsson J A,Chanussot J.Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques[J]. IEEE Trans Geosci Remote Sensing,2009,47(8):2973-2987.
[14] Mauro D M,Alberto V,et al.Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis[J]. IEEE Trans Geosci Remote Sensing Lett,2011,8(3):542-546.
[15] Sun Le,Wu Zebin,et al.A novel supervised method for hyperspectral image classification with spectral-spatial constraints[J]. Chinese Journal of Electronics,2014,23(1):135-141.
[16] Le Sun,Zebin Wu,et al.Supervised spectral-spatial hyperspectral image classification with weighted Markov random fields[J]. IEEE Trans Geosci Remote Sensing,2015,53(3):1490-1503.
[17] Tarabalka Y,Benediktsson J,et al.Multiple spectral-spatial classification approach for hyperspectral data[J]. IEEE Trans Geosci Remote Sensing,2010,48(11):4122-4132.
[18] XiaJunshi,Du Peijun,He Xiyan.MRF-based multiple classifier system for hyperspectral remote sensing image classification[J]. Multiple Classifier Systems,2013,7872:343-351.
[19] Bigdeli B,Samadzadegan F,Reinartz P.A multiple SVM system for classification of Hyperspectral remote sensing data[J]. Journal of the Indian Society of Remote Sensing,2013,41(4):763-776.
[20] Khodadadzadeh M,Li Jun,et al.Spectral-spatial classification of hyperspectral data using local and global probabilities for mixed pixel characterization[J]. IEEE Trans Geosci Remote Sensing,2014,52(10):6298-6314.
[21] Boykov Y,Kolmogorov V.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Trans on PAMI,2004,26(9):1124-1137.

一种新的两分类器融合的空谱联合高光谱分类方法

A Novel Two-Classifier Fusion Method for Spectral-Spatial Hyperspectral Classification

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

[1]	张绍泉, 黄志浩, 邓承志, 李璠, 徐晨光, 吴朝明, 汪胜前. 光谱加权协同稀疏和全变差正则化高光谱图像解混[J]. 电子学报, 2020, 48(12): 2453-2461.
[2]	李艳秋, 任福继, 胡敏. 动态模糊密度的多分类器融合算法[J]. 电子学报, 2018, 46(5): 1246-1252.
[3]	李康, 何发智, 潘一腾, 孙航. 基于簇相似的多分类器目标跟踪算法[J]. 电子学报, 2016, 44(4): 821-825.
[4]	黄江涛;;王明辉;李武劲;古博. 基于动态权值的多分类器故障诊断系统[J]. 电子学报, 2012, 40(4): 734-738.
[5]	米爱中;郝红卫;郑雪峰;涂序彦. 一种自整定权值的多分类器融合方法[J]. 电子学报, 2009, 37(11): 2604-2609.