高光谱图像分类的Wasserstein配置熵非监督波段选择方法

doi:10.11947/j.AGCS.2021.20200006

测绘学报 ›› 2021, Vol. 50 ›› Issue (3): 405-415.doi: 10.11947/j.AGCS.2021.20200006

高光谱图像分类的Wasserstein配置熵非监督波段选择方法

张红^1,2, 吴智伟³, 王继成³, 高培超⁴

1. 华东师范大学全球创新与发展研究院, 上海 200062;
2. 华东师范大学城市与区域科学学院, 上海 200241;
3. 西南交通大学地球科学与环境工程学院, 四川成都 611756;
4. 北京师范大学地表过程与资源生态国家重点实验室, 北京 100875

收稿日期:2020-01-06 修回日期:2021-01-20 发布日期:2021-03-31
通讯作者: 高培超 E-mail:gaopc@bnu.edu.cn
作者简介:张红(1981-),女,博士,副教授,研究方向为地理信息分析、时空建模与复杂网络。E-mail:hzhang@re.ecnu.edu.cn
基金资助:
国家自然科学基金（4191316）；四川省科技支撑计划（2020YJ0325）；成都市重点研发支撑计划（2019-YF05-02119-SN）；上海市哲学社会科学规划课题（2020BGL034）；地表过程与资源生态国家重点实验室开放基金（2020-KF-03）；中央高校基本科研业务费专项资金（2019NTST02）

Unsupervised band selection for hyperspectral image classification using the Wasserstein metric-based configuration entropy

ZHANG Hong^1,2, WU Zhiwei³, WANG Jicheng³, GAO Peichao⁴

1. Institute for Global Innovation and Development, East China Normal University, Shanghai 200062, China;
2. School of Urban and Regional Science, East China Normal University, Shanghai 200241, China;
3. Faculty of Geosciences & Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China;
4. State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China

Received:2020-01-06 Revised:2021-01-20 Published:2021-03-31
Supported by:
The National Natural Science Foundation of China (No. 4191316);The Program of Science and Technology of Sichuan Province (No. 2020YJ0325);The Key Research and Development Program of Chengdu (No. 2019-YF05-02119-SN);Shanghai Philosophy and Social Science Project(No. 2020BGL034);The State Key Laboratory of Earth Surface Processes and Resource Ecology (No. 2020-KF-03);The Fundamental Research Funds for the Central Universities (No. 2019NTST02)

摘要/Abstract

摘要： 高光谱图像波段选择需考虑波段信息。传统香农信息熵指标仅考虑图像的组分信息（像元的种类和比例），忽略了图像的空间配置信息（像元的空间分布），后者可由玻尔兹曼熵刻画。其中，Wasserstein配置熵删除了连续像元的冗余信息，但局限于四邻域，本文将Wasserstein配置熵拓展至八邻域。以印度松木试验场和意大利帕维亚大学高光谱图像为例，使用Wasserstein配置熵差异值测度波段相关性，通过非监督次优搜索法确定最优波段组合，并用支持向量机分类。比较基于Wasserstein配置熵差异值、互信息、4种标准化互信息和两种相对熵变体的图像分类精度。结果表明，四邻域和八邻域Wasserstein配置熵差异值均可用于高光谱图像波段选择，当选择少量波段时优势尤为明显，且八邻域整体优于四邻域。

关键词: 高光谱图像, 图像分类, 香农熵, Wasserstein配置熵, 波段选择

Abstract: Band selection relies on the quantification of band information. Conventional measurements such as Shannon entropy only consider the composition information (e.g., types and ratios of pixels) but ignore the configuration information (e.g., the spatial distribution of pixels). The latter could be quantified by Boltzmann entropy. Among all the metrics of Boltzmann entropy, the Wasserstein metric-based configuration entropy (Wasserstein entropy for short) removes the redundant information of the continuous pixels. However, it is limited to 4-neighborhood. This article improves it to 8-neighborhood. Taking the hyperspectral images of Indian Pines and Italian Pavia University as examples, we used the difference of Wasserstein entropy to measure band correlation and then employed the unsupervised sub-optimal searching algorithm to determine the optimal band combination. We used the support vector machine classifier for image classification. Finally, we compared the accuracy of image classification based on the difference of Wasserstein entropy, mutual information, four types of normalized mutual information, and two variants of relative entropy. Results show that both the 4-neighborhood and 8-neighborhood Wasserstein entropy can be used for band selection of hyperspectral images, especially when few bands are considered. The 8-neighborhood Wasserstein entropy works better than 4-neighborhood.

Key words: hyperspectral image, image classification, Shannon entropy, Wasserstein configuration entropy, band selection

中图分类号:

P237

张红, 吴智伟, 王继成, 高培超. 高光谱图像分类的Wasserstein配置熵非监督波段选择方法[J]. 测绘学报, 2021, 50(3): 405-415.

ZHANG Hong, WU Zhiwei, WANG Jicheng, GAO Peichao. Unsupervised band selection for hyperspectral image classification using the Wasserstein metric-based configuration entropy[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(3): 405-415.

参考文献

[1] 黄鸿, 郑新磊. 高光谱影像空-谱协同嵌入的地物分类算法[J]. 测绘学报, 2016, 45(8):964-972. DOI:10.11947/j.AGCS.2016.20150654. HUANG Hong, ZHENG Xinlei. Hyperspectral image land cover classification algorithm based on spatial-spectral coordination embedding[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(8):964-972. DOI:10.11947/j.AGCS.2016.20150654.
[2] CASA R, UPRETI D, PALOMBO A, et al. Evaluation and exploitation of retrieval algorithms for estimating biophysical crop variables using Sentinel-2, Venus, and PRISMA satellite data[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(4):79-88. DOI:10.11947/j.JGGS.2020.0408.
[3] 杨钊霞, 邹峥嵘, 陶超, 等. 空-谱信息与稀疏表示相结合的高光谱遥感影像分类[J]. 测绘学报, 2015, 44(7):775-781. DOI:10.11947/j.AGCS.2015.20140207. YANG Zhaoxia, ZOU Zhengrong, TAO Chao, et al. Hyperspectral image classification based on the combination of spatial-spectral feature and sparse representation[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(7):775-781. DOI:10.11947/j.AGCS.2015.20140207.
[4] SUN Weiwei, DU Qian. Graph-regularized fast and robust principal component analysis for hyperspectral band selection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(6):3185-3195.
[5] GAO Peichao, WANG Jicheng, ZHANG Hong, et al. Boltzmann entropy-based unsupervised band selection for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(3):462-466.
[6] SAWANT S S, MANOHARAN P. Unsupervised band selection based on weighted information entropy and 3D discrete cosine transform for hyperspectral image classification[J]. International Journal of Remote Sensing, 2020, 41(10):3948-3969.
[7] CHANG C I, DU Qian, SUN T L, et al. A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(6):2631-2641.
[8] CHANG C I, WANG Su. Constrained band selection for hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(6):1575-1585.
[9] MARTÍNEZ-USÓMARTINEZ-USO A, PLA F, SOTOCA J M, et al. Clustering-based hyperspectral band selection using information measures[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12):4158-4171.
[10] GONG Jianya, JI Shunping. Photogrammetry and deep learning[J]. Journal of Geodesy and Geoinformation Science, 2018, 1(1):1-15. DOI:10.11947/j.JGGS.2018.0101.
[11] ZENG Meng, CAI Yaoming, CAI Zhihua, et al. Unsupervised hyperspectral image band selection based on deep subspace clustering[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(12):1889-1893.
[12] 曾梦, 宁彬, 蔡之华, 等. 使用深度对抗子空间聚类实现高光谱波段选择[J]. 计算机应用, 2020, 40(2):381-385. ZENG Meng, NING Bin, CAI Zhihua, et al. Hyperspectral band selection based on deep adversarial subspace clustering[J]. Journal of Computer Applications, 2020, 40(2):381-385.
[13] CAI Yaoming, LIU Xiaobo, CAI Zhihua. BS-Nets:an end-to-end framework for band selection of hyperspectral image[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(3):1969-1984.
[14] 严阳, 华文深, 刘恂, 等. 基于高光谱基本准则的波段选择方法[J]. 光学技术, 2018, 44(5):634-640. YAN Yang, HUA Wenshen, LIU Xun, et al. Band selection method based on hyperspectral fundamental criterion[J]. Optical Technique, 2018, 44(5):634-640.
[15] SHANNON C E. A mathematical theory of communication[J]. The Bell System Technical Journal, 1948, 27(3):379-423.
[16] 李志林, 刘启亮, 高培超. 地图信息论:从狭义到广义的发展回顾[J]. 测绘学报, 2016, 45(7):757-767. DOI:10.11947/j.AGCS.2016.20160235. LI Zhilin, LIU Qiliang, GAO Peichao. Entropy-based cartographic communication models:evolution from special to general cartographic information theory[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(7):757-767. DOI:10.11947/j.AGCS.2016.20160235.
[17] LI Zhilin, HUANG Peizhi. Quantitative measures for spatial information of maps[J]. International Journal of Geographical Information Science, 2002, 16(7):699-709.
[18] CAO Xianghai, HAN Jungong, YANG Shuyuan, et al. Band selection and evaluation with spatial information[J]. International Journal of Remote Sensing, 2016, 37(19):4501-4520.
[19] CUSHMAN S A. Calculating the configurational entropy of a landscape mosaic[J]. Landscape Ecology, 2016, 31(3):481-489.
[20] GAO Peichao, ZHANG Hong, LI Zhilin. A hierarchy-based solution to calculate the configurational entropy of landscape gradients[J]. Landscape Ecology, 2017, 32(6):1133-1146.
[21] ZHAO Yuan, ZHANG Xinchang. Calculating spatial configurational entropy of a landscape mosaic based on the Wasserstein metric[J]. Landscape Ecology, 2019, 34(8):1849-1858.
[22] SUKHOV V I. Information capacity of a map entropy[J]. Geodesy and Aerophotography, 1967, 10(4):212-215.
[23] HARALICK R M, SHANMUGAM K, DINSTEIN I H. Textural features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973(6):610-621.
[24] BOLTZMANN L. Weitere studien über das wärmegleichge-wicht unter gasmolekülen[M]. Sitzungsberichte Akademie der Wissenschaften, 1872, 66:275-370.
[25] ZHANG Mingyang, GONG Maoguo, MAO Yishun, et al. Unsupervised feature extraction in hyperspectral images based on Wasserstein generative adversarial network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(5):2669-2688.
[26] ESTEVEZ P A, TESMER M, PEREZ C A, et al. Normalized mutual information feature selection[J]. IEEE Transactions on Neural Networks, 2009, 20(2):189-201.
[27] VINH N X, EPPS J, BAILEY J. Information theoretic measures for clusterings comparison:Variants, properties, normalization and correction for chance[J]. Journal of Machine Learning Research, 2010, 11(1):2837-2854.
[28] KULLBACK S, LEIBLER R A. On information and sufficiency[J]. Annals of Mathematical Statistics, 1951, 22(1):79-86.
[29] 邬建国. 景观生态学——格局、过程、尺度与等级[M]. 2版. 北京:高等教育出版社, 2007:125-147. WU Jianguo. Landscape ecology:pattern, process, scale and hierarchy[M]. 2nd ed. Beijing:Higher Education Press, 2007:125-147.
[30] HENEBRY G M. Spatial model error analysis using autocorrelation indices[J]. Ecological Modelling, 1995, 82(1):75-91.
[31] BAUMGARDNER M F, BIEHL L L, LANDGREBE D A. 220 band aviris hyperspectral image data set:June 12, 1992 Indian pine test site 3[J]. Purdue University Research Repository, 2015.
[32] GEGE P, BERAN D, MOOSHUBER W, et al. System analysis and performance of the new version of the imaging spectrometer ROSIS[C]//Proceedings of the 1st EARSel Workshop on Imaging Spectroscopy Remote Sensing Laboratories. 1998:29-35.
[33] 魏立飞, 余铭, 钟燕飞, 等. 空-谱融合的条件随机场高光谱影像分类方法[J]. 测绘学报, 2020, 49(3):343-354. DOI:10.11947/j.AGCS.2020.20190042. WEI Lifei, YU Ming, ZHONG Yanfei, et al. Hyperspectral image classification method based on space-spectral fusion conditional random field[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(3):343-354. DOI:10.11947/j.AGCS.2020.20190042.

高光谱图像分类的Wasserstein配置熵非监督波段选择方法

Unsupervised band selection for hyperspectral image classification using the Wasserstein metric-based configuration entropy

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	张作宇, 廖守亿, 孙大为, 张合新, 王仕成. 稀疏差异先验信息支持的高光谱图像稀疏解混算法[J]. 测绘学报, 2020, 49(8): 1032-1041.
[2]	徐君, 王彩玲, 王丽. 采用PPI算法改进的一种数学形态学端元提取方法[J]. 测绘学报, 2019, 48(8): 996-1003.
[3]	黄鸿, 陈美利, 王丽华, 李政英. 空-谱协同正则化稀疏超图嵌入的高光谱图像分类[J]. 测绘学报, 2019, 48(6): 676-687.
[4]	谷雨, 徐英, 郭宝峰. 融合空谱特征和集成超限学习机的高光谱图像分类[J]. 测绘学报, 2018, 47(9): 1238-1249.
[5]	侯榜焕, 王锟, 姚敏立, 贾维敏, 王榕. 面向高光谱图像分类的半监督空谱判别分析[J]. 测绘学报, 2017, 46(9): 1098-1106.
[6]	王忠美, 杨晓梅, 顾行发. 张量组稀疏表示的高光谱图像去噪算法[J]. 测绘学报, 2017, 46(5): 614-622.
[7]	邵远杰吴国平马丽. 属类概率距离构图的半监督高光谱图像分类[J]. 测绘学报, 2014, 43(11): 1182-1189.
[8]	施蓓琦刘春孙伟伟陈能. 应用稀疏非负矩阵分解聚类实现高光谱影像波段的优化选择[J]. , 2013, 42(3): 0-0.
[9]	刘小芳,何彬彬,李小文. 基于半监督核模糊C-均值算法的北京一号小卫星多光谱图像分类[J]. 测绘学报, 2011, 40(3): 301-306.
[10]	刘艳芳兰泽英刘洋唐祥云. 基于混合熵模型的遥感分类不确定性的多尺度评价方法研究 [J]. 测绘学报, 2009, 38(1): 0-11.