融合累积变异比和集成超限学习机的高光谱图像分类  

Ensemble extreme learning machine with cumulative variation quotient for hyperspectral image classification

作　　者：尹玉萍[1] 魏林 刘万军[3] Yin Yuping;Wei Lin;Liu Wanjun(School of Electrical and Control Engineering,Liaoning Technical University,Huludao 125105,China;Department of Basic Education,Liaoning Technical University,Huludao 125105,China;School of Software,Liaoning Technical University,Huludao 125105,China)

机构地区：[1]辽宁工程技术大学电气与控制工程学院,葫芦岛125105 [2]辽宁工程技术大学基础教学部,葫芦岛125105 [3]辽宁工程技术大学软件学院,葫芦岛125105

出　　处：《中国图象图形学报》2020年第5期1053-1068,共16页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61172144);辽宁省教育厅科学技术研究项目(LJ2017QL021);辽宁工程技术大学博士启动基金项目(19-1026)。

摘　　要：目的 高光谱图像具有高维度的光谱结构,而且邻近波段之间往往存在大量冗余信息,导致在随机样本选择策略和图像分类过程中出现选择波段算法复杂度较高和不适合小样本的现象.针对该问题,在集成学习算法的基础上,考虑不同波段在高光谱图像分类过程中的作用不同,提出一种融合累积变异比和超限学习机的高光谱图像分类算法.方法 定义波段的累积变异比函数来确定各波段在分类算法的贡献程度.基于累积变异比函数剔除低效波段,并结合空谱特征进行平均分组加权随机选择策略进行数据降维.为了进一步提高算法的泛化能力,对降维后提取的空谱特征进行多次样本重采样,训练得到多个超限学习机弱分类器,再将多个弱分类器的结果通过投票表决法得到最后的分类结果.结果 实验使用Indian Pines、Pavia University scene和Salinas这3种典型的高光谱图像作为实验标准数据集,采用支持向量机(support vector machine,SVM),超限学习机(extreme learningmachine,ELM),基于二进制多层Gabor超限学习机(ELM with Gabor,GELM),核函数超限学习机(ELM with kernel,KELM),GELM-CK(GELM with composite kernel),KELM-CK(KELM with composite kernel)和SS-EELM(spatial-spec-tral and ensemble ELM)为标准检测算法验证本文算法的有效性,在样本比例较小的实验中,本文算法的总体分类精度在3种数据集中分别为98.0%、98.9%和97.9%,比其他算法平均分别高出9.6%和4.7%和4.1%.本文算法耗时在3种数据集中分别为15.2s、60.4s和169.4 s.在同类目标空谱特性差异较大的情况下,相比于分类精度较高的KELM-CK和SS-EELM算法减少了算法耗时,提高了总体分类精度;在同类目标空谱特性相近的情况下,相比于其他算法,样本数量的增加对本文算法的耗时影响较小.结论 本文算法通过波段的累积变异比函数优化了平均分组波段选择策略,针对各类地物目标分布较广泛并且同Objective Hyperspectral remote sensing has become a promising research field and is applied to various aspects.Hyperspectral image classification has become a key part of hyperspectral image processing. However,high-dimensional data structures bring new challenges for hyperspectral image classification. In particular,problems may occur in the feature extraction and classification process of a hyperspectral image dataset,e. g.,the Hughes phenomenon,because of the unbalance between the high-dimensionality of the data and the limited number of training samples. To improve the accuracy of hyperspectral image classification,we propose a hyperspectral image classification algorithm based on ensemble extreme learning machine (ELM) with cumulative variation quotient,referred to as EELM with cumulative variation quotient (CVQEELM). Method In this study,the coefficient of variation is usually used as the index to show the data dispersion. Compared with the standard deviation,its main advantage is that it is not affected by the measurement scale. In particular,the coefficient of variation takes into account the influence of the average value of the data. The coefficient of variation is improved and applied to the dimensionality reduction of the HIS dataset. First,the cumulative variation functions of the intraclass and the interclass and the cumulative variation quotient are proposed. In actual operation,some pixels may contain multiple ground objects,while the gray values of the intraclass are quite different. Therefore,the cumulative variation function of the interclass and the cumulative variation function of the intraclass should be comprehensively considered to define the cumulative variation quotient function of bands. On the premise of the same band,the quotient of the norm of the interclass’ cumulative variation function and the sum of the norm of the intraclass’ cumulative variation function is called the cumulative variation quotient of the band. If the cumulative variation quotient of the band is far from 1,i

关 键 词：高光谱图像 超限学习机 累积变异比 投票表决 分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]