基于随机子空间核极端学习机集成的高光谱遥感图像分类

计算机科学 ›› 2016, Vol. 43 ›› Issue (3): 301-304.doi: 10.11896/j.issn.1002-137X.2016.03.056

基于随机子空间核极端学习机集成的高光谱遥感图像分类

宋相法,曹志伟,郑逢斌,焦李成

河南大学计算机与信息工程学院开封475004,河南大学计算机与信息工程学院开封475004,河南大学计算机与信息工程学院开封475004,西安电子科技大学智能感知与图像理解教育部重点实验室西安710071

出版日期:2018-12-01 发布日期:2018-12-01
基金资助:
本文受国家自然科学基金(61272282,1),教育部“长江学者和创新团队发展计划”(IRT1170),河南省高等学校重点科研项目(15A520010)资助

Classification of Hyperspectral Remote Sensing Image Based on Random Subspace and Kernel Extreme Learning Machine Ensemble

SONG Xiang-fa, CAO Zhi-wei, ZHENG Feng-bin and JIAO Li-cheng

Online:2018-12-01 Published:2018-12-01

摘要/Abstract

摘要： 结合随机子空间和核极端学习机集成提出了一种新的高光谱遥感图像分类方法。首先利用随机子空间方法从高光谱遥感图像数据的整体特征中随机生成多个大小相同的特征子集；然后利用核极端学习机在这些特征子集上进行训练从而获得基分类器；最后将所有基分类器的输出集成起来,通过投票机制得到分类结果。在高光谱遥感图像数据集上的实验结果表明:所提方法能够提高分类效果,且其分类总精度要高于核极端学习机和随机森林方法。

关键词: 高光谱遥感图像分类,核极端学习机,随机子空间,分类器集成

Abstract: This paper presented a novel classification algorithm of hyperspectral remote sensing image based on random subspace and kernel extreme learning machine ensemble.Firstly,many feature subsets of the same size are generated from the whole feature of hyperspectral remote sensing image data with random subspace method.Then the base classifiers of kernel extreme learning machine are trained based on these feature subsets.Finally,the classification result is decided by voting strategy.The experimental results on hyperspectral remote sensing image indicate that the proposed method has better performance than the methods based on kernel extreme learning machine and random forest respectively,and has a higher classification overall accuracy.

Key words: Hyperspectral remote sensing image classification,Kernel extreme learning machine,Random subspace,Classifier ensemble

宋相法,曹志伟,郑逢斌,焦李成. 基于随机子空间核极端学习机集成的高光谱遥感图像分类[J]. 计算机科学, 2016, 43(3): 301-304. https://doi.org/10.11896/j.issn.1002-137X.2016.03.056

SONG Xiang-fa, CAO Zhi-wei, ZHENG Feng-bin and JIAO Li-cheng. Classification of Hyperspectral Remote Sensing Image Based on Random Subspace and Kernel Extreme Learning Machine Ensemble[J]. Computer Science, 2016, 43(3): 301-304. https://doi.org/10.11896/j.issn.1002-137X.2016.03.056

参考文献

[1] Tong Qing-xi,Zhang Bing,Zheng Lan-fen.Hyperspectral Re-mote Sensing—Theory,Technology and Applications [M].Beijing:Higer Education Press,2006(in Chinese) 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,2006:145-146
[2] Camps-Valls G,Tuia D,Bruzzone L,et al.Advances in Hyperspectral Image Classification:Earth Monitoring with Statistical Learning Methods [J].IEEE Signal Processing Magazine,2014,31(1):45-54
[3] Ham J,Chen Y,Crawford M,et al.Investigation of the randomforest framework for classification of hyperspectral data[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):492-501
[4] Chan J C W,Paelinckx D.Evaluation of Random Forest and Ada-boost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery[J] Remote Sensing Environment,2008,112 (6):2999-3011
[5] Rodriguez-Galiano V F,Ghimire B,Rogan J,et al.An assessment of the effectiveness of a Random Forest classifier for land-cover classification[J].ISPRS J.Photogramm,2012,67(1):93-104
[6] Song Xiang-fa,Jiao Li-cheng.Classification of Hyperspectral Remote Sensing Image Based on Sparse Representation and Spectral Information[J].Journal of Electronics & Information Technology,2012,34(2):268-272(in Chinese) 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
[7] Feng Hai-liang,Pan Jing-wen,Huang Hong.Hyperspectral Image Classification Based on Semi-supervised Neighborhood Preserving Embedding[J].Computer Science,2014,41(6A):230-233(in Chinese) 冯海亮,潘竞文,黄鸿.半监督邻域保持嵌入在高光谱影像分类中的应用[J].计算机科学,2014,41(6A):230-233
[8] Zhang Fan,Du Bo,Zhang Liang-pei,et al.Band Grouping Based Hyperspectral Image Classification Using Mathematical Morphology and Support Vector Machines[J].Computer Science,2014,41(12):275-279(in Chinese) 张帆,杜博,张良培,等.一种结合波段分组特征和形态学特征的高光谱图像分类方法[J].计算机科学,2014,1(12):275-279
[9] Ren Yue-mei,Li Lei,Zhang Yang-ning,et al.Band Selection and Classification for Hyperspectral Image Based on Multiple Particle Swarm Cooperative Optimization[J].Computer Science,2014,41(12):283-287(in Chinese) 任越美,李垒,张艳宁,等.一种基于多粒子群协同进化的高光谱图像波段选择与分类方法[J].计算机科学,2014,1(12):283-287
[10] Zhou Zhi-hua.Ensemble Methods:Foundations and Algorithms [M].Boca Raton,FL:Chapman & Hall/CRC,2012:109-112
[11] Marin J,Vazquez D,Lopez A M,et al.Occlusion Handling via Random Subspace Classifiers for Human Detection[J].IEEE Transaction on Systems,Man,and Cybernetics,2014,44(3):342-354
[12] Yao Xu,Wang Xiao-dan,Zhang Yu-xi,et al.A Self-AdaptionEnsemble Algorithm Based on Random Subspace and AdaBoost [J].Acta Electronic Sinica,2013,1(4):810-814(in Chinese) 姚旭,王晓丹,张玉玺,等.基于随机子空间和AdaBoost的自适应集成方法[J].电子学报,2013,1(4):810-814
[13] Huang Guang-Bin,Zhu Qin-Yu,Siew C K.Extreme learningmachine:Theory and applications[J].Neurocomputing,2006,70(1-3):489-501
[14] Huang Guang-bin,Zhou Hong-ming,Ding Xiao-jian,et al.Ex-treme learning machine for regression and multiclass classification[J].IEEE Transactions on Systems,Man and Cybernetics,Part B,2012,42(2):513-529
[15] Chen Chen,Li Wei,Su Hong-jun,et al.Spectral-Spatial Classification of Hyperspectral Image Based on Kernel Extreme Lear-ning Machine [J].Remote Sensing,2014,6(6):5795-5814
[16] Pal M,Maxwell A E,Warner T A.Kernel-based extreme learning machine for remote-sensing image classification [J].Remote Sensing Letter,2013,4(9):853-862

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed