[1]张因国,陶于祥,罗小波,等.基于特征重要性的高光谱图像分类[J].红外技术,2020,42(12):1185-1191.[doi:doi:10.11846/j.issn.1001_8891.202010009]
 ZHANG Yinguo,TAO Yuxiang,LUO Xiaobo,et al.Hyperspectral Image Classification Based on Feature Importance[J].Infrared Technology,2020,42(12):1185-1191.[doi:doi:10.11846/j.issn.1001_8891.202010009]
点击复制

基于特征重要性的高光谱图像分类
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
42卷
期数:
2020年第12期
页码:
1185-1191
栏目:
出版日期:
2020-12-22

文章信息/Info

Title:
Hyperspectral Image Classification Based on Feature Importance
文章编号:
1001-8891(2020)12-1185-07
作者:
张因国1陶于祥1罗小波2刘明皓1
1. 重庆邮电大学 计算机科学与技术学院,重庆 400065;2. 重庆市气象科学研究所,重庆 401147
Author(s):
ZHANG Yinguo1TAO Yuxiang1LUO Xiaobo2LIU Minghao1
1. 重庆邮电大学 计算机科学与技术学院,重庆 400065;2. 重庆市气象科学研究所,重庆 401147
关键词:
高光谱图像特征重要性波段选择卷积神经网络支持向量机
Keywords:
hyperspectral image feature importance band selection CNN SVM
分类号:
TP751
DOI:
doi:10.11846/j.issn.1001_8891.202010009
文献标志码:
A
摘要:
 为了减少高光谱图像中的冗余以及进一步挖掘潜在的分类信息,本文提出了一种基于特征重要性的卷积神经网络(convolutional neural networks,CNN)分类模型。首先,利用贝叶斯优化训练得到的随机森林模型(random forest,RF)对高光谱遥感图像进行特征重要性评估;其次,依据评估结果选择合适数目的高光谱图像波段,以作为新的训练样本;最后,利用三维卷积神经网络对所得样本进行特征提取并分类。基于两个实测的高光谱遥感图像数据,实验结果均表明:相比原始光谱信息直接采用支持向量机(support vector machine,SVM)和卷积神经网络的分类效果,本文所提基于特征重要性的高光谱分类模型能够在降维的同时有效提高高光谱图像的分类精度。
Abstract:
To reduce the redundancy in hyperspectral images and further explore their potential classification information, a convolutional neural network(CNN) classification model based on feature importance is proposed. First, the random forest(RF) model obtained by Bayesian optimization training is used to evaluate the importance of hyperspectral images. Second, an appropriate number of hyperspectral image bands are selected as new training samples according to the evaluation results. Finally, the 3D-CNN is used to extract and classify the obtained samples. Based on two sets of measured hyperspectral remote sensing image data, the experimental results demonstrate the following: compared with the original spectral information obtained directly using a support vector machine(SVM) and the CNN classification effect, the proposed hyperspectral classification model based on feature importance can effectively improve the classification accuracy of hyperspectral images while reducing dimensionality.

参考文献/References:

[1] YE M C, JI C X, CHEN H, et al. Residual deep PCA-based feature extraction for hyperspectral image[J/OL]. Neural Computing& Applications, 2020, 32(7): doi:10.1007/s00521-019-04503-3.
[2] Donoho D L. High-dimensional data analysis: the curses and blessings of dimensionality[J]. AMS Math Challenges Lecture, 2000, 1: 32.
[3] Marpu G, Chanussot P R J, Benediktsson J A. Linear versus nonlinear PCA for the classification of hyperspectral data based on the extended morphological profiles[J]. IEEE Geosci. Remote Sens. Lett., 2012, 9(3): 447-451.
[4] Villa A, Benediktsson J A, Chanussot J, et al. Hyperspectral image classification with independent component discriminant analysis[J]. IEEE Trans. Geosci. Remote Sens., 2011, 49(12): 4865-4876.
[5] Zabalza J, REN J, WANG Z, et al. Singular spectrum analysis for effective feature extraction in hyperspectral imaging[J]. IEEE Geosci. Remote Sens. Lett., 2014, 11(11): 1886-1890.
[6] Chacvez P S, Berlin G L, Sowers L B. Statistical method for selecting landsat MSS retio[J]. Jourmal of Applied Photographic Engineering, 1982, 1(8): 23-30.
[7] Charles S. Selecting band combination from multispectral data[J]. Photogrammetric Engineering and Remote Sensing, 1985, 51(6): 681-687.
[8] 张爱武, 杜楠, 康孝岩, 等. 非线性变换和信息相邻相关的高光谱自适应波段选择[J]. 红外与激光工程, 2017, 46(5): 05308001.
ZHANG Aiwu, DU Nan, KANG Xiaoyan, et al. Adaptive band selection for nonlinear transform and information adjacent correlation[J]. Infrared and Laser Engineering, 2017, 46(5): 05308001.
[9] HU W, HUANG Y, WEI L, et al. Deep convolutional neural networks for hyperspectral image classification[J]. Journal of Sensors, 2015, 2015: e258619.
[10] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014, 2: 2672-2680.
[11] Haut J, Paoletti M, Plaza J, et al. Cloud implementation of the K-means algorithm for hyperspectral image analysis[J]. J. Supercomput., 2017, 73(1): 514-529.
[12] Melgani F, Lorenzo B. Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE Trans. Geosci. Remote Sens., 2004, 42(8): 1778-1790.
[13] Camps-Valls G, Bruzzone L. Kernel-based methods for hyperspectral image classification[J]. IEEE Trans. Geosci. Remote Sens., 2004, 43(6): 1351-1362.
[14] Haut J, Paoletti M, Paz-Gallardo A, et al. Cloud implementation of logistic regression for hyperspectral image classification[C]//Comput. Math. Methods Sci. Eng. (CMMSE), 2017, 3: 1063-2321.
[15] Bazi Y, Melgani F. Gaussian process approach to remote sensing image classification[J]. IEEE Trans. Geosci. Remote Sens., 2010, 48(1): 186-197.
[16] Breiman L. Bagging predictors[J]. Mach Learn, 1996, 24(2): 123-140.
[17] Cutler A, Cutler D R, Stevens J R. Random Forests[M]//Ensemble Machine Learning, Boston: Springer, 2012: 157-175.
[18] 李贞贵. 随机森林改进的若干研究[D]. 厦门: 厦门大学, 2013.
LI Z G. Several Research on Random Forest Improvement[D]. Xiamen: Xiamen University, 2013.
[19] LI Y, ZHANG H, SHEN Q. Spectral-spatial classification of hyper- spectral imagery with 3D convolutional neural network[J]. Remote Sensing, 2017, 9(1): 67.
[20] CHEN Y, JIANG H, LI C X, et al. Deep features extraction and classification of hyperspectral images based on convolutional neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(10): 6232-6251.

相似文献/References:

[1]张翔.基于光谱特征增强的高光谱图像地物目标识别[J].红外技术,2010,32(12):717.
 Target Recognition of Hyperspectral Image Based?on Enhanced Spectral Characteristics[J].Infrared Technology,2010,32(12):717.
[2]何高攀,杨桄,张筱晗,等.基于端元提取的高光谱异常目标检测[J].红外技术,2015,37(十):836.[doi:10.11846/j.issn.1001_8891.201510006]
 HE Gao-pan,YANG Guang,ZHANG Xiao-han,et al.Anomaly Detection Algorithm Based on Endmember Extraction in Hyperspectral Imagery[J].Infrared Technology,2015,37(12):836.[doi:10.11846/j.issn.1001_8891.201510006]
[3]陈海挺.基于非下采样Contourlet变换的异常检测SVDD算法[J].红外技术,2016,38(1):047.[doi:10.11846/j.issn.1001_8891.201601008]
 CHEN Haiting.Anomaly Detection SVDD Algorithm Based on Nonsubsampled Contourlet Transform[J].Infrared Technology,2016,38(12):047.[doi:10.11846/j.issn.1001_8891.201601008]
[4]向英杰,张俭峰,杨 桄,等.基于混合噪声估计的高光谱图像异常检测方法[J].红外技术,2017,39(8):734.[doi:10.11846/j.issn.1001_8891.201708011]
 XIANG Yingjie,ZHANG Jianfeng,YANG Guang,et al.A Mixed-Noise Estimation-Based Anomaly Detection Method for Hyperspectral Image [J].Infrared Technology,2017,39(12):734.[doi:10.11846/j.issn.1001_8891.201708011]
[5]向英杰,杨 桄,张俭峰,等. 采用分段行-列核2DPCA的高光谱图像降维[J].红外技术,2017,39(12):1107.[doi:10.11846/j.issn.1001_8891.201712007]
 XIANG Yingjie,YANG Guang,ZHANG Jianfeng,et al. Dimensionality Reduction for Hyperspectral Image Using a Segmented Row-column Kernel Two-dimensional Principal Component Analysis Method[J].Infrared Technology,2017,39(12):1107.[doi:10.11846/j.issn.1001_8891.201712007]
[6]徐杭威,赵 壮,岳 江,等. 一种基于归一化光谱向量的高光谱图像实时性非监督分类方法[J].红外技术,2018,40(4):362.[doi:10.11846/j.issn.1001_8891.201804010]
 XU Hangwei,ZHAO Zhuang,YUE Jiang,et al.Real-time Unsupervised Classification Method of Hyperspectral Images Based on the Normalized Spectral Vector [J].Infrared Technology,2018,40(12):362.[doi:10.11846/j.issn.1001_8891.201804010]
[7]徐 君,王旭红,杨 勇,等.一种基于光谱角空间变换的高光谱图像分割方法[J].红外技术,2018,40(10):1013.[doi:10.11846/j.issn.1001_8891.201810014]
 XU Jun,WANG Xuhong,YANG Yong,et al.A Hyperspectral Image Segmentation Method Based on Spectral Angular Space Transformation [J].Infrared Technology,2018,40(12):1013.[doi:10.11846/j.issn.1001_8891.201810014]
[8]严 阳,华文深,张 炎,等.可见-近红外高光谱伪装目标特性分析[J].红外技术,2019,41(2):171.[doi:10.11846/j.issn.1001_8891.2019020011]
 YAN Yang,HUA Wenshen,ZHANG Yan,et al.Visible Near-infrared Hyperspectral Camouflage Target Characteristic Analysis[J].Infrared Technology,2019,41(12):171.[doi:10.11846/j.issn.1001_8891.2019020011]
[9]张国东,周浩,方淇,等.基于栈式自编码神经网络对高光谱遥感图像分类研究[J].红外技术,2019,41(5):450.[doi:10.11846/j.issn.1001_8891.201905010]
 ZHANG Guodong,ZHOU Hao,FANG Qi,et al.Classification of Hyperspectral Remote Sensing Images Based on Stack Self-encoding Neural Network[J].Infrared Technology,2019,41(12):450.[doi:10.11846/j.issn.1001_8891.201905010]
[10]陈 欣,粘永健,王忠良.基于线性混合模型的高光谱图像分布式压缩感知[J].红外技术,2019,41(8):758.[doi:10.11846/j.issn.1001_8891.2019080011]
 CHEN Xin,NIAN Yongjian,WANG Zhongliang.Distributed Compressive Sensing for Hyperspectral Imaging Based on Linear Mixing Model [J].Infrared Technology,2019,41(12):758.[doi:10.11846/j.issn.1001_8891.2019080011]

备注/Memo

备注/Memo:
收稿日期:2020-07-21;修订日期:2020-09-15.
作者简介:张因国(1996-),男,硕士研究生,主要从事遥感图像分类研究。E-mail:S180231026@cqupt.edu.cn。
通信作者:陶于祥(1966-),男,博士,教授,研究方向为资源与环境经济学。E-mail:taoyx@cqupt.edu.cn。
基金项目:国家自然科学基金项目,“城市地表温度降尺度模型及热岛时空演变规律研究”(41871226);重庆市应用开发计划重点项目(cstc2014yykfB30003)。
更新日期/Last Update: 2020-12-21