Hyperspectral Remote Sensing Image Classification Based on BOVW and Complex Networks

doi:10.3778/j.issn.1002-8331.2010-0134

Abstract

Abstract: For the sake of mining the deep features of hyperspectral remote sensing images（HSRSI） and obtaining the optimized feature space to improve the classification accuracy, a spectral feature extraction method combining bag of visual words and complex networks（BOVW-CN） is proposed. By improving BOVW method, K-Means method is used to calculate the clustering centers of all kinds of samples as dictionaries, and the difference between the spectral pixel value of each sample to be tested and the same spectral band in the codebook spectral vectors is calculated, and word frequency histogram of a single sample is calculated. Meanwhile, in order to improve the expression of the extracted features about the correlation between the pixel bands, the complex networks theory is applied. The spectral vector of the sample points is matrixed, and the complex network is constructed by using the matrix position and pixel value of the pixels. Then, the threshold value of the network is dynamically evolved, and the topological features of each sub network are extracted. Finally, the features extracted from them are fused for classification. Experimental results on Salinas and KSC hyperspectral remote sensing data sets show that the algorithm can achieve better classification results.

Key words: hyperspectral remote sensing image, bag of visual words（BOVW）, complex networks, image classification

摘要： 为挖掘高光谱遥感图像的深层光谱特征，获取优化特征空间以提高分类准确率，提出了一种基于视觉词典和复杂网络的高光谱遥感图像分类的光谱特征提取方法。通过改进视觉词典方法，使用K-Means方法计算各类样本的聚类中心作为词典，并计算各待测试样本的光谱像素值与词典光谱向量中相同光谱波段的差值，计算出单个待测样本点的词频直方图。同时，为提升所提取特征关于像素点波段之间关联的表达，引入复杂网络理论，将样本点光谱向量矩阵化，利用像素点的矩阵位置和像素值构建复杂网络，再对网络进行阈值动态演化，并提取各个子网络拓扑特征。融合二者所提取的特征进行分类。在Salinas和KSC高光谱遥感数据集上的实验结果表明，该算法都可以取得更优的分类效果。

关键词: 高光谱遥感图像, 视觉词典（BOVW）, 复杂网络, 图像分类

NING Chen, XIE Hongwei, MENG Linan. Hyperspectral Remote Sensing Image Classification Based on BOVW and Complex Networks[J]. Computer Engineering and Applications, 2022, 58(9): 219-229.

宁晨, 谢红薇, 孟丽楠. 融合BOVW和复杂网络的高光谱遥感图像分类[J]. 计算机工程与应用, 2022, 58(9): 219-229.

References

[1] GOETZ A F H.Three decades of hyperspectral remote sensing of the earth：a personal view[J].Remote Sensing of Environment，2009，113：5-16.
[2] SAWANT S S，PRABUKUMAR M.A review on graph-based semi-supervised learning methods for hyperspectral image classification[J].Egyptian Journal of Remote Sensing & Space Science，2018，23（2）：243-248.
[3] 张建伟，陈允杰.高光谱图像分类方法综述[J].南京信息工程大学学报，2020，12（1）：89-100.
ZHANG J W，CHEN Y J.Overview of hyperspectral image classification methods[J].Journal of Nanjing University of Information Science & Technology，2020，12（1）：89-100.
[4] HUGHES G F，HUGHES　G.On the mean accuracy of statistical pattern recognizers[J].IEEE Transactions on Information Theory，1968，14（1）：55-63.
[5] PLAZA A，BENEDIKTSSON J A，BOARDMAN J W，et al.Recent advances in techniques for hyperspectral image processing[J].Remote Sensing of Environment，2009，113（S1）：110-122.
[6] JIA X，KUO B C，CRAWFORD M M.Feature mining for hyperspectral image classification[J].Proceedings of the IEEE，2013，101（3）：676-697.
[7] UDDIN M P，MAMUN M A，HOSSAIN M A.PCA-based feature reduction for hyperspectral remote sensing image classification[J].IETE Technical Review，2020（5）：1-21.
[8] ZHANG C，ZHENG Y.Hyperspectral remote sensing image classification based on combined SVM and LDA[C]//Multispectral，Hyperspectral，and Ultraspectral Remote Sensing Technology，Techniques and Applications V.International Society for Optics and Photonics，2014：9263-92632.
[9] WEI Q，BIOUCAS-DIAS J，DOBIGEON N，et al.Hyperspectral and multispectral image fusion based on a sparse representation[J].IEEE Transactions on Geoence and Remote Sensing，2015，53（7）：3658-3668.
[10] 舒速，杨明.基于分水岭分割和稀疏表示的高光谱图像分类方法[J].计算机科学，2016，43（2）：89-94.
SHU S，YANG M.Hyperspectral linage classification method based on watershed segmentation and sparse reprentation[J].Computer Science，2016，43（2）：89-94.
[11] 莫文通，周源.基于K近邻非线性分类器的高光谱遥感数据分类研究[J].城市勘测，2014（4）：16-19.
MO W T，ZHOU Y.A nonlinear K-nearest neighbor classifier for hyperspectral remote sensing imagery classification[J].Urban Geotechnical Investigation & Surveying，2014（4）：16-19.
[12] VADDI R，PRABUKUMAR M.Comparative study of feature extraction techniques for hyper spectral remote sensing image classification：a survey[C]//2017 International Conference on Intelligent Computing and Control Systems（ICICCS），2017：543-548.
[13] GHAMISI P，PLAZA J，CHEN Y，et al.Advanced spectral classifiers for hyperspectral images：a review[J].Geoscience & Remote Sensing，2017，5（1）：8-32.
[14] 黄冬梅，梁素玲，王振华，等.利用信息熵的高光谱遥感影像降维方法[J].计算机工程与应用，2019，55（6）：197-202.
HUANG D M，LIANG S L，WANG Z H，et al.Dimensionality reduction method for hyperspectral remote sensing image based on information entropy[J].Computer Engineering and Applications，2019，55（6）：197-202.
[15] KUO B C，LI C H，YANG J M.Kernel nonparametric weighted feature extraction for hyperspectral image classification[J].IEEE Transactions on Geoscience & Remote Sensing，2009，47（4）：1139-1155.
[16] BHOSLE K，MUSANDE V.Evaluation of deep learning CNN model for land use land cover classification and crop identification using hyperspectral remote sensing images[J].Journal of the Indian Society of Remote Sensing，2019，47（3）：1949-1958.
[17] CHEN Y，JIANG H，LI C，et al.Deep feature extraction and classification of hyperspectral images based on convolutional neural networks[J].IEEE Transactions on Geoence & Remote Sensing，2016，54（10）：6232-6251.
[18] GUO A J X，ZHU F.A CNN-based spatial feature fusion algorithm for hyperspectral imagery classification[J].IEEE Transactions on Geoence and Remote Sensing，2019，57（9）：7170-7181.
[19] 王立伟，李吉明，周国民，等.深度迁移学习在高光谱图像分类中的运用[J].计算机工程与应用，2019，55（5）：181-186.
WANG L W，LI J M，ZHOU G M，et al.Application of deep transfer learning in hyperspectral image classification[J].Computer Engineering and Applications，2019，55（5）：181-186.
[20] 陈方杰，李吉明，杨东勇.基于生成对抗网络的高光谱图像分类[J].计算机工程与应用，2019，55（22）：172-179.
CHEN F J，LI J M，YANG D Y.Hyperspectral image classification based on generative adversarial networks[J].Computer Engineering and Applications，2019，55（22）：172-179.
[21] MA L，MA A，JU C，et al.Graph-based semi-supervised learning for spectral-spatial hyperspectral image classification[J].Pattern Recognition Letters，2016，83（1）：133-142.
[22] FAUVEL M，TARABALKA Y，BENEDIKTSSON J A，et al.Advances in spectral-spatial classification of hyperspectral images[J].Proceedings of the IEEE，2012，101（3）：652-675.
[23] FANG L，JIE W，RUSHI L，et al.Hyperspectral image classification using multi-feature fusion[J].Optics & Laser Technology，2018，110（SI）：176-183.
[24] ZHANG C，LI G，DU S.Multi-scale dense networks for hyperspectral remote sensing image classification[J].IEEE Transactions on Geoscience and Remote Sensing，2019，57（11）：9201-9222.
[25] ZOU Q，BAI J.Interest points detection in image based on topology features of multi-level complex networks[J].Wireless Personal Communications，2018（103）：715-725.
[26] SCABINI L F S，CONDORI R H M，GON?ALVES，et al.Multilayer complex network descriptors for color-texture characterization[J].Information Sciences，2018（491）：30-47.
[27] XU D，CHEN X，XIE Y，et al.Complex networks-based texture extraction and classification method for mineral flotation froth images[J].Minerals Engineering，2015，83：105-116.
[28] 赫南，李德毅，淦文燕，等.复杂网络中重要性节点发掘综述[J].计算机科学，2007，34（12）：l-5.
HE N，LI D Y，GAN W Y，et al.Mining vital nodes in complex networks[J].Computer Science，2007，34（12）：l-5.
[29] BOCCALETTI S，LATORA V，MORENO Y，et al.Complex networks：structure and dynamics[J].Physics Reports，2006，424（4/5）：175-308.
[30] SILVA T C，ZHAO L.Machine learning in complex networks[M].Switzerland：Springer International Publishing，2016：71-91.
[31] DE LIMA G V L，SAITO P T M，LOPES F M，et al.Classification of texture based on bag-of-visual-words through complex networks[J].Expert Systems with Application，2019，133：215-224.
[32] BACKES A R，CASANOVA D，BRUNO O M.Texture analysis and classification：a complex network-based approach[J].Information Sciences，2013，219：168-180.
[33] 徐佳庆，万文，吕启.基于二阶矩稀疏编码的高光谱遥感图像分类[J].计算机科学，2018，45（9）：288-293.
XU J Q，WAN W，LV Q.Classification of hyperspectral remote sensing imagery based on second order moment sparse coding[J].Computer Science，2018，45（9）：288-293.
[34] RASCHE H，HILTEMANN S.Galactic circos：user-friendly circos plots within the galaxy platform[J].Gigaence，2020，9（6）：65.