A fast spectral clustering algorithm for hyperspectral remote sensing images

doi:10.13474/j.cnki.11-2246.2019.0387

Abstract

Abstract: In order to obtain a better classification method of remote sensing images and solve the problem of slow classification operation of hyperspectral remote sensing images, this paper integrates Lanczos algorithm and spectral clustering algorithm, discusses the feasibility of spectral clustering algorithm of hyperspectral remote sensing images applied to remote sensing image classification, and proposes a hyperspectral remote sensing image-oriented fast spectral clustering algorithm. By comparing the classification results of K-means algorithm and spectral clustering algorithm for hyperspectral remote sensing image of San Diego Airport, USA, it is found that spectral clustering algorithm for hyperspectral remote sensing image is easy to recognize linear features, and the classification speed can be greatly improved.

Key words: hyperspectral remote sensing images, spectral clustering, K-means, Lanczos, image classification

CLC Number:

P237

ZHANG Yaping, ZHANG Yu, YANG Nan, LUO Xiao, LUO Qian. A fast spectral clustering algorithm for hyperspectral remote sensing images[J]. Bulletin of Surveying and Mapping, 2019, 0(12): 60-64.

References

[1] ORFANIDIS G, TEFAS A, NIKOLAIDIS N, et al. Facial image clustering in stereoscopic videos using double spectral analysis[J]. Signal Processing:Image Communication, 2015, 33:86-105.
[2] SHI J B, MALIK J. Normalized cuts and image segmenta-tion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8):888-905.
[3] CHIFU A G, HRISTEA F, MOTHE J, et al. Word sense discrimination in information retrieval:a spectral clustering-based approach[J]. Information Processing and Management, 2015, 51(2):16-31.
[4] QUIRÓS-TORTÓS J, WALL P, DING L, et al. Determina-tion of sectionalising strategies for parallel power system restoration:a spectral clustering-based methodology[J]. Electric Power Systems Research, 2014, 116:381-390.
[5] QIN G M, GAO L. Spectral clustering for detecting protein complexes in protein-protein interaction (PPI) networks[J]. Mathematical and Computer Modelling, 2010, 52(11-12):2066-2074.
[6] 杜培军,夏俊士, 薛朝辉, 等.高光谱遥感影像分类研究进展[J]. 遥感学报,2016, 20(2):236-256.
[7] 万幼川,黄俊.几何和图论特征对高分辨率遥感影像土地利用分类的影响[J].武汉大学学报(信息科学版),2009,34(7):794-798.
[8] 党宇,张继贤,邓喀中,等.基于深度学习AlexNet的遥感影像地表覆盖分类评价研究[J].地球信息科学学报,2017,19(11):1530-1537.
[9] 李刚,万幼川.商空间理论下面向对象的遥感影像分类[J].光电工程,2011,38(2):108-114.
[10] 陈永良,林楠,李学斌. 求解大样本核主成分分析模型的Lanczos算法[J].吉林大学学报(地球科学版), 2010, 40(1):222-226.
[11] 刘丽丽. 基于谱聚类方法的SAR图像分割[D].天津:天津理工大学,2011.
[12] ZHANG J, MARSZALEK M, LAZEBNIK S, et al. Local features and kernels for classification of texture and object categories:a comprehensive study[J]. International Journal of Computer Vision, 2007, 73(2):213-238.
[13] 王国栋. 相似矩阵与谱聚类[D].北京:北京交通大学,2009.
[14] 马恒. 基于混合数据的谱聚类算法研究[D].徐州:中国矿业大学,2016.

[1]	YANG Jun, LIU Linghui. Feature extraction of spatial and temporal change of land in functional areas based on weighted full-polarization SAR image classification [J]. Bulletin of Surveying and Mapping, 2022, 0(7): 138-142,153.
[2]	DOU Shiqing, CHEN Zhiyu, XU Yong, ZHENG Hegang, MIAO Linlin, SONG Yingying. Hyperspectral image classification based on multi-feature fusion and dimensionality reduction algorithms [J]. Bulletin of Surveying and Mapping, 2022, 0(4): 32-36,50.
[3]	ZHANG Qiang, BAI Zhengdong, XIN Haohao, CHENG Yuhang, GUO Jinping. Fine-grained clustering based on spatio-temporal big data of shared bikes [J]. Bulletin of Surveying and Mapping, 2021, 0(5): 15-19,29.
[4]	YE Yuanxin, TAN Xin, SUN Miaomiao, WANG Mengmeng. High-resolution remote sensing image classification based on improved DeepLabV3 network [J]. Bulletin of Surveying and Mapping, 2021, 0(4): 40-44.
[5]	HU Chuanwen, LU Shijie, YANG Wenjing, ZHU Xiaoyong. Deep learning architecture for building extraction using LiDAR point clouds [J]. Bulletin of Surveying and Mapping, 2021, 0(12): 88-93.
[6]	HAN Jianping. Environmental change monitoring in Qinghai province based on remote sensing image [J]. Bulletin of Surveying and Mapping, 2021, 0(10): 123-126,145.
[7]	PENG Shugang, WANG Dacheng, TAN Junhui, AO Xuanfeng, YU Jiaying. A video intelligent detection method for urban underground drainage pipe based on improved convolutional neural network [J]. Bulletin of Surveying and Mapping, 2021, 0(10): 132-135,167.
[8]	SUN Wei, LI Sheng, JIANG Yi, KE Shuisong, XIA Anke. Reflection on the application of deep learning method in “multiple-investigation-coordination” in Shenzhen [J]. Bulletin of Surveying and Mapping, 2021, 0(1): 138-141.
[9]	ZHAO Jiayao, LI Hongwei. Time series spectral clustering analysis of taxi data [J]. Bulletin of Surveying and Mapping, 2020, 0(8): 112-116.
[10]	ZHANG Yong, ZHU Daming, FENG Yu, DAI Decheng. A method for travel safety analysis supported by user GPS trajectory data [J]. Bulletin of Surveying and Mapping, 2020, 0(5): 73-79.
[11]	WANG Zheqi, XU Liuhua, YU Zhiqiang. Method of handling suspended ground objects in tilt photography real scene model [J]. Bulletin of Surveying and Mapping, 2020, 0(5): 111-114.
[12]	ZHANG Pengqiang, LIU Bing, YU Xuchu, TAN Xiong, YANG Fan, ZHOU Zenghua. Generative adversarial networks for hyperspectral image classification [J]. Bulletin of Surveying and Mapping, 2020, 0(3): 29-34.
[13]	CHANG Xiangyu, KE Changqing. Urban impervious surface information extraction based on random forest algorithm: taking Changchun as an example [J]. Bulletin of Surveying and Mapping, 2020, 0(11): 43-49.
[14]	WANG Luyao, GAO Shan, LI Jun, FAN Hong. The sales character analysis of retails based on K-means method and spatial correlation [J]. 测绘通报, 2019, 0(9): 51-54.
[15]	XU Huimin, QI Hua, NAN Ke, CHEN Min. High-resolution remote sensing image classification by combining deep learning with nDSM [J]. 测绘通报, 2019, 0(8): 63-67.