[1]尤雅萍,成运,苏松志,等.基于谱域-空域结合特征和图割原理的高光谱图像分类[J].智能系统学报,2015,10(02):201-208.[doi:10.3969/j.issn.1673-4785.201410040]
 YOU Yaping,CHENG Yun,SU Songzhi,et al.Hyperspectral image classification based on spectral-spatial combination features and graph cut[J].CAAI Transactions on Intelligent Systems,2015,10(02):201-208.[doi:10.3969/j.issn.1673-4785.201410040]
点击复制

基于谱域-空域结合特征和图割原理的高光谱图像分类(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第10卷
期数:
2015年02期
页码:
201-208
栏目:
学术论文—智能系统
出版日期:
2015-04-25

文章信息/Info

Title:
Hyperspectral image classification based on spectral-spatial combination features and graph cut
作者:
尤雅萍13 成运2 苏松志13 曹冬林13 李绍滋13
1. 厦门大学 信息科学与技术学院, 福建 厦门 361005;
2. 湖南人文科技学院 信息科学与工程系, 湖南 娄底 417000;
3. 福建省仿脑智能系统重点实验室, 福建 厦门 361005
Author(s):
YOU Yaping13 CHENG Yun2 SU Songzhi13 CAO Donglin13 LI Shaozi13
1. School of Information Science and Technology, Xiamen University, Xiamen 361005, China;
2. Department of Information Science and Engineering, Hunan University of Humanities, Science and Technology, Loudi 417000, China;
3. Fujian Key Laboratory of the Brain-Like Intelligent Systems, Xiamen 361005, China
关键词:
高光谱图像分类谱域特征空域特征谱域-空域结合特征均值特征支持向量机图割原理
Keywords:
hyperspectralimage classificationspectral featurespatial featurespectral-spatial combination featuremean featuressupport vector machinesgraph cut
分类号:
TP391.4
DOI:
10.3969/j.issn.1673-4785.201410040
文献标志码:
A
摘要:
高光谱图像中存在着特征维度高而训练集小的问题。为解决该问题,提出了一种2步走的分类方法:1)通过支持向量机对图像进行初步分类,根据分类结果计算出每个类别的均值特征;2)使用1)计算出来的均值特征作为能量函数的数据项,然后利用图割原理对图像做二次分类。实验中发现:空间上相近的像素点往往具有相似的特征,且属于同一个类别。针对这种现象,提取一个将谱域特征和空域特征相结合的新特征。该特征既包含了光谱信息也包含了空间信息,具有较好的分类性能和鲁棒性。在Indian Pine数据集和Pavia University数据集进行实验,实验结果表明了本文提出方法的有效性。
Abstract:
The high-dimension of the feature vs. small-size of training set is an unsolved problem in the hyperspectral image classification task. To solve this problem a two-step classification method is proposed. Firstly, a preliminary classification is performed by the support vector machine (SVM) and the classification results are used to calculate the mean feature (MF) of each class. Secondly, a classification based on the graph cut theory is applied with the MFs as an input of the energy function. The experimental results showed that spatially nearby pixels have large possibilities of having the same label and similar features. Therefore, a new feature called spectral-spatial combination (SSC) is extracted that combines the spectral-based feature and spatial-based feature. The SSC feature contains the related spectral and spatial information of each pixel and provides better classification performance and robustness. Experiment results on the Indian Pine dataset and the Pavia University dataset demonstrated the effectiveness of the proposed method.

参考文献/References:

[1] FONG M. Dimension reduction on hyperspectral images[R]. Los Angeles: University of California, 2007.
[2] WANG J, CHANG C I. Independent component analysis based dimensionality reduction with applications in hyperspectral image analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(6): 1586-1600.
[3] HUANG H Y, KUO B C. Double nearest proportion feature extraction for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(11): 4034-4046.
[4] 苏红军,杜培军,盛业华. 高光谱遥感数据光谱特征提取算法与分类研究[J]. 计算机应用研究, 2008, 25(2):390-394.SU Hongjun, DU Peijun, SHENG Yesheng. Study on feature extraction and experiment of hyperspectral data[J]. Application Research of Computers, 2008, 25(2): 390-394.
[5] 赵春晖, 齐滨, YOUN E. 基于蒙特卡罗特征降维算法的小样本高光谱图像分类[J]. 红外与毫米波学报, 2013, 32(1): 62-67.ZHAO Chun Hui, QI Bin, YOUN E. Hyperspectral image classification based on Monte Carlo feature reduction method[J]. J Infrared Millim Waves, 2013, 32(1): 62-67.
[6] QIAN Y T, YE M, ZHOU J. Hyperspectral image classification based structured sparse logistic regression and three-dimensional wavelet texture features[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(4): 2276-2291.
[7] 彭艳斌,艾解清. 基于谱聚类波段选择的高光谱图像分类[J]. 光电工程, 2012, 39(2): 63-67.PENG Yanbin, AI Jieqing. Hyperspectral imagery classification based on spectral clustering band selection[J]. Opto-Electronic Engineering, 2012, 39(2): 63-67.
[8] 王国立,孙杰,肖倩. 结合空-谱信息的高光谱图像分类方法[J]. 黑龙江大学自然科学学报, 2010, 27(6): 788-791.WANG Guoli, SUN Jie, XIAO Qian. Combination of spatial information and spectral information for hyperspectral imagery classification[J]. Journal of Natural Science of HeiLongJiang University, 2010, 27(6): 788-791.
[9] 吴见, 彭道黎. 基于空间信息的高光谱遥感植被分类技术[J]. 农业工程学报, 2012, 28(5): 150-153.WU Jian, PENG Daoli. Vegetation classification technology of hyperspectral remote sensing based on spatial information[J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(5): 150-153.
[10] JI R R, GAO Y, HONG R, et al. Spectral-spatial constraint hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(3): 1811-1824.
[11] 高恒振,万建伟,粘永健,等. 一种基于谱域-空域组合特征支持向量机的高光谱图像分类算法[J]. 宇航学报, 2011, 32(4): 917-921.GAO Hengzhen, WAN Jianwei, NIAN Yongjian, et al. Hyeprspectral image classification algorithm based on spectral-spatial hybird features and SVM[J]. Journal of Astronautics, 2011, 32(4):917-921.
[12] BENEDIKTSSON A, PALMASON J A, SVEINSSON J R. Classification of hyperspectral data from urban areas based on extended morphological profiles[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3): 480-491.
[13] FREUND Y and SCHAPIRE R E. A decision theoretic generalization of online learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997, 55(1): 119-139.
[14] MARCONCINI M, CAMPS-VALLS G, BRUZZONE L. A composite semisupervised SVM for classification of hyperspectral images[J]. IEEE Geoscience Remote and Sensing Letters, 2009, 6(2): 234-238.
[15] ARCHIBALD R, FANN G. Feature selection and classification of hyperspectral images with support vector machines[J]. IEEE Geoscience Remote and Sensing Letters, 2007, 4(4): 674-677.
[16] BRUZZONE L, CHI M, MARCONCINI M. A novel transductive SVM for semisupervised classification of remote sensing images[J]. IEEE Geoscience Remote and Sensing Letters, 2006, 44(11): 3363-3373.
[17] BOYKOV Y, VEKSLER O, ZABIH R. Fast approximate energy minimization via graph cuts[J]. IEEE Transactions on Pattern Analysis and Machine Inteligence, 2001, 23(11): 1222-1239.
[18] BAI J, XIANG S M, PAN C H. A graph based classification method for hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 51(2): 803-817.

相似文献/References:

[1]李海峰,杜军平.颜色特征的图像分类技术研究[J].智能系统学报,2008,3(02):65.[doi:CNKI:SUN:ZNXT.0.2008-02-017]
[2]李海峰,杜军平.颜色特征的图像分类技术研究[J].智能系统学报,2008,3(02):155.
 LI Hai-feng,DU Jun-ping.Image classification technology based on color features[J].CAAI Transactions on Intelligent Systems,2008,3(02):155.
[3]姚伏天,钱沄涛.高斯过程及其在高光谱图像分类中的应用[J].智能系统学报,2011,6(05):396.
 YAO Futian,QIAN Yuntao.Gaussian process and its applications in hyperspectral image classification[J].CAAI Transactions on Intelligent Systems,2011,6(02):396.
[4]赵骞,李敏,赵晓杰,等.基于感受野学习的特征词袋模型简化算法[J].智能系统学报,2016,11(5):663.[doi:10.11992/tis.201601001]
 ZHAO Qian,LI Min,ZHAO Xiaojie,et al.Learning receptive fields for compact bag-of-feature model[J].CAAI Transactions on Intelligent Systems,2016,11(02):663.[doi:10.11992/tis.201601001]
[5]费宇杰,吴小俊.一种局部聚合描述符和组显著编码相结合的编码方法[J].智能系统学报,2017,12(02):172.[doi:10.11992/tis.201602010]
 FEI Yujie,WU Xiaojun.A new feature coding algorithm based on the combination of group salient coding and VLAD[J].CAAI Transactions on Intelligent Systems,2017,12(02):172.[doi:10.11992/tis.201602010]
[6]杨梦铎,栾咏红,刘文军,等.基于自编码器的特征迁移算法[J].智能系统学报,2017,12(06):894.[doi:10.11992/tis.201706037]
 YANG Mengduo,LUAN Yonghong,LIU Wenjun,et al.Feature transfer algorithm based on an auto-encoder[J].CAAI Transactions on Intelligent Systems,2017,12(02):894.[doi:10.11992/tis.201706037]
[7]马忠丽,刘权勇,武凌羽,等.一种基于联合表示的图像分类方法[J].智能系统学报,2018,13(02):220.[doi:10.11992/tis.201611036]
 MA Zhongli,LIU Quanyong,WU Lingyu,et al.Syncretic representation method for image classification[J].CAAI Transactions on Intelligent Systems,2018,13(02):220.[doi:10.11992/tis.201611036]
[8]魏彩锋,孙永聪,曾宪华.图正则化字典对学习的轻度认知功能障碍预测[J].智能系统学报,2019,14(2):369.[doi:10.11992/tis.201709033]
 WEI Caifeng,SUN Yongcong,ZENG Xianhua.Dictionary pair learning with graph regularization for mild cognitive impairment prediction[J].CAAI Transactions on Intelligent Systems,2019,14(02):369.[doi:10.11992/tis.201709033]
[9]赵玉新,赵廷.海底声呐图像智能底质分类技术研究综述[J].智能系统学报,2020,15(3):587.[doi:10.11992/tis.202004026]
 ZHAO Yuxin,ZHAO Ting.Survey of the intelligent seabed sediment classification technology based on sonar images[J].CAAI Transactions on Intelligent Systems,2020,15(02):587.[doi:10.11992/tis.202004026]
[10]高淑萍,赵清源,齐小刚,等.改进MobileNet的图像分类方法研究[J].智能系统学报,2021,16(1):11.[doi:10.11992/tis.202012034]
 GAO Shuping,ZHAO Qingyuan,QI Xiaogang,et al.Research on the improved image classification method of MobileNet[J].CAAI Transactions on Intelligent Systems,2021,16(02):11.[doi:10.11992/tis.202012034]

备注/Memo

备注/Memo:
收稿日期:2014-10-29;改回日期:。
基金项目:国家自然科学基金资助项目(61202143);福建省自然科学基金资助项目(2013J05100,2010J01345,2011J01367);湖南省自然科学基金资助项目(12JJ2040).
作者简介:尤雅萍,女,1990年生,硕士研究生,主要研究方向为高光谱图像分类技术;苏松志,1982年生,男,博士,助理教授,主要研究方向为人体行为分析与理解。主持国家青年基金一项,主持省青年基金一项,参与多项国家级基金项目,发表学术论文多篇,其中被SCI检索7篇;李绍滋,1963年生,男,教授,博士生导师,博士,福建省人工智能学会副理事长,主要研究方向为运动目标检测与识别、自然语言处理与多媒体信息检等。发表学术论文200余篇,其中被SCI检索26篇、被EI检索170篇。
通讯作者:李绍滋.E-mail:szlig@xmu.edu.cn.
更新日期/Last Update: 2015-06-15