全Bregman散度和二部图相结合的高光谱图像稳健聚类算法

doi:10.11947/j.AGCS.2023.20220637

摘要/Abstract

摘要： 针对传统基于图的谱聚类算法底层计算复杂度高、聚类精度低,难以应用于大规模数据聚类,本文利用锚点与数据点之间的相似性度量,提出了一种基于图的聚类算法来处理高光谱图像分类问题,称为全Bregman散度和二部图相结合的高光谱图像稳健聚类算法(RTBBG)。首先,在构造二部图的过程中添加了高光谱图像的空间信息,使得高光谱图像丰富的空间信息得以充分利用;然后,利用全Bregman散度来优化传统的欧氏距离作为数据点与锚点之间新的相似性度量,使得构建的二部图更加稳定,增强了算法稳健性;最后,利用K-means算法直接进行光谱聚类得到最终聚类结果。通过在3个大规模高光谱数据集上进行测试,验证了本文算法的有效性。

关键词: 高光谱图像, 二部图, 全Bregman散度, 相似性度量, 空间信息

Abstract: In view of the high computational complexity and low clustering accuracy of traditional graph based spectral clustering algorithms, which are difficult to apply to large-scale data clustering, this paper proposes a graph based clustering algorithm to deal with hyperspectral image classification problems by using the similarity measurement between anchor points and data points, which is called robust hyperspectral image clustering integrating total Bregman divergence and bipartite graph (RTBBG). Firstly, the spatial information of hyperspectral image is added in the construction of bipartite graph, which makes full use of the rich spatial information of hyperspectral image. Secondly, the total Bregman divergence is used to optimize the traditional Euclidean distance as a similarity measure between data points and anchors, which makes the constructed bipartite graph more stable and enhances the robustness of the algorithm. Finally, K-means algorithm is used to directly cluster the spectra to obtain the final clustering results. The effectiveness of the algorithm is verified by testing on three large-scale hyperspectral datasets.

Key words: hyperspectral image, bipartite graph, total Bregman divergence, similarity measurement, spatial information

中图分类号:

P237

刘含, 吴成茂, 李昌兴. 全Bregman散度和二部图相结合的高光谱图像稳健聚类算法[J]. 测绘学报, 2023, 52(10): 1749-1759.

LIU Han, WU Chengmao, LI Changxing. Robust hyperspectral image clustering integrating total Bregman divergence and bipartite graph[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(10): 1749-1759.

参考文献

[1] APPICE A, GUCCIONE P, ACCIARO E, et al. Detecting salient regions in a bi-temporal hyperspectral scene by iterating clustering and classification[J]. Applied Intelligence, 2020, 50(10):3179-3200.
[2] MAKANTASIS K, DOULAMIS A D, DOULAMIS N D, et al. Tensor-based classification models for hyperspectral data analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(12):6884-6898.
[3] SUN Le, WU Feiyang, HE Chengxu, et al. Weighted collaborative sparse and L1/2 low-rank regularizations with superpixel segmentation for hyperspectral unmixing[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19:5500405.
[4] RESHM S, VENI S. Comparative analysis of classification techniques for crop classification using airborne hyperspectral data[C]//Proceedings of 2017 International Conference on Wireless Communications, Signal Processing and Networking. Chennai:IEEE, 2018:2272-2276.
[5] CABALLERO B, CALVINI R, AMIGO J M. Hyperspectral imaging in crop fields:precision agriculture[M]//Data Handling in Science and Technology. Amsterdam:Elsevier, 2019:453-473.
[6] WEI Lifei, YU Mingxuan, LIANG Yajing, et al. Precise crop classification using spectral-spatial-location fusion based on conditional random fields for UAV-borne hyperspectral remote sensing imagery[J]. Remote Sensing, 2019, 11(17):2011.
[7] MEI Shaohui, HOU Junhui, CHEN Jie, et al. Simultaneous spatial and spectral low-rank representation of hyperspectral images for classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(5):2872-2886.
[8] DENG Cheng, CHEN Zhaojia, LIU Xianglong, et al. Triplet-based deep hashing network for cross-modal retrieval[J]. IEEE Transactions on Image Processing, 2018, 27(8):3893-3903.
[9] 杨国鹏,余旭初,冯伍法,等.高光谱遥感技术的发展与应用现状[J].测绘通报, 2008(10):1-4. YANG Guopeng, YU Xuchu, FENG Wufa, et al. The development and application of hyperspectral RS technology[J]. Bulletin of Surveying and Mapping, 2008(10):1-4.
[10] HONG Danfeng, GAO Lianru, YAO Jing, et al. Graph convolutional networks for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(7):5966-5978.
[11] WANG Kexian, ZHENG Shunyi, LI Rui, et al. A deep double-channel dense network for hyperspectral image classification[J]. Journal of Geoinformation Science, 2021, 4(4):46-62.
[12] XUE Zhaohui, NIE Xiangyu. Low-rank and sparse representation with adaptive neighborhood regularization for hyperspectral image classification[J]. Journal of Geoinformation Science, 2022, 5(1):73-90.
[13] ZHANG Hongyan, ZHAI Han, ZHANG Liangpei, et al. Spectral-spatial sparse subspace clustering for hyperspectral remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(6):3672-3684.
[14] BEZDEK J C. Pattern recognition with fuzzy objective function algorithms[M]. New York:Plenum Press, 1981.
[15] HARTIGAN A, WONG A. A K-means clustering algorithm[J]. Applied Statistics, 1979, 28(1):100-108.
[16] CHEN Songcan, ZHANG Daoqiang. Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2004, 34(4):1907-1916.
[17] KRINIDIS S, CHATZIS V. A robust fuzzy local information C-means clustering algorithm[J]. IEEE Transactions on Image Processing, 2010, 19(5):1328-1337.
[18] VON LUXBURG U. A tutorial on spectral clustering[J]. Statistics and Computing, 2007, 17(4):395-416.
[19] WANG Rong, NIE Feiping, YU Weizhong. Fast spectral clustering with anchor graph for large hyperspectral images[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(11):2003-2007.
[20] WANG Rong, NIE Feiping, WANG Zhen, et al. Scalable graph-based clustering with nonnegative relaxation for large hyperspectral image[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(10):7352-7364.
[21] 李康,徐金东,赵甜雨,等.一种面向高光谱图像分类的模糊谱聚类算法[J].中国科技论文, 2021, 16(7):743-747. LI Kang, XU Jindong, ZHAO Tianyu, et al. A fuzzy spectral clustering algorithm for hyperspectral image classification[J]. China Sciencepaper, 2021, 16(7):743-747.
[22] 许裕雄,杨晓君,蔡湧达,等.基于二叉树锚点的高光谱快速聚类算法[J].激光与光电子学进展, 2021, 58(2):0210021. XU Yuxiong, YANG Xiaojun, CAI Yongda, et al. Hyperspectral fast clustering algorithm based on binary tree anchor point[J]. Laser&Optoelectronics Progress, 2021, 58(2):0210021.
[23] CAI Deng, CHEN Xinlei. Large scale spectral clustering via landmark-based sparse representation[J]. IEEE Transactions on Cybernetics, 2015, 45(8):1669-1680.
[24] YANG Xiaojun, XU Yuxiong, LI Siyuan, et al. Fuzzy embedded clustering based on bipartite graph for large-scale hyperspectral image[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19:5505605.
[25] 聂飞平,王成龙,王榕.基于二部图的快速聚类算法[J].深圳大学学报(理工版), 2019, 36(1):18-23. NIE Feiping, WANG Chenglong, WANG Rong. Fast clustering based on bipartite graph[J]. Journal of Shenzhen University (Science&Engineering), 2019, 36(1):18-23.
[26] BANERJEE A, MERUGU S, DHILLON I, et al. Clustering with Bregman divergences[C]//Proceedings of 2004 SIAM International Conference on Data Mining. Philadelphia:Society for Industrial and Applied Mathematics, 2004:234-245.
[27] HASNAT M A, ALATA O, TRÉMEAU A. Model-based hierarchical clustering with Bregman divergences and fishers mixture model:application to depth image analysis[J]. Statistics and Computing, 2016, 26(4):861-880.
[28] WU Chengmao, ZHANG Xue. A novel kernelized total Bregman divergence-based fuzzy clustering with local information for image segmentation[J]. International Journal of Approximate Reasoning, 2021, 136:281-305.
[29] LIU Meizhu, VEMURI B C, AMARI S I, et al. Total Bregman divergence and its applications to shape retrieval[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco:IEEE, 2010:3463-3468.
[30] NIELSEN F, NOCK R. Total Jensen divergences:definition, properties and k-means++clustering[EB/OL].[2022-11-17]. https://arxiv.org/pdf/1309.7109.pdf.
[31] WU Chengmao, ZHANG Xue. Total Bregman divergence-based fuzzy local information C-means clustering for robust image segmentation[J]. Applied Soft Computing, 2020, 94:106468.
[32] LI Yeqing, NIE Feiping, HUANG Heng, et al. Large-scale multi-view spectral clustering via bipartite graph[C]//Proceedings of 2015 AAAI Conference on Artificial Intelligence. Palo Alto:AAAI Press, 2015:2750-2756.
[33] LIU W, HE J F, CHANG S F. Large graph construction for scalable semi-supervised learning[EB/OL].[2022-11-17]. https://icml.cc/Conferences/2010/papers/16.pdf.
[34] CHENG Gong, XIE Xingxing, HAN Junwei, et al. Remote sensing image scene classification meets deep learning:challenges, methods, benchmarks, and opportunities[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13:3735-3756.
[35] ZHENG Xiaoxiong, CHEN Tao. High spatial resolution remote sensing image segmentation based on the multiclassification model and the binary classification model[J]. Neural Computing and Applications, 2023, 35(5):3597-3604