Structure-Aware Multikernel Learning for Hyperspectral Image Classification

被引:6
作者
Zhou, Chengle [1 ]
Tu, Bing [1 ]
Li, Nanying [2 ]
He, Wei [1 ]
Plaza, Antonio [3 ]
机构
[1] Hunan Inst Sci & Technol, Sch Informat Sci & Engn, Yueyang 414000, Peoples R China
[2] Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Peoples R China
[3] Univ Extremadura, Dept Technol Comp & Commun, Hyperspectral Comp Lab, E-10003 Caceres, Spain
基金
中国国家自然科学基金;
关键词
Feature extraction; Kernel; Support vector machines; Task analysis; Data mining; Earth; Collaboration; Hyperspectral image (HSI) classification; multikernel learning; structure-aware learning; KERNEL COLLABORATIVE REPRESENTATION; REMOTE-SENSING IMAGES; FEATURE-EXTRACTION; EXTINCTION PROFILES; NETWORKS; FUSION; SUPERPIXEL; REGRESSION; FRAMEWORK; DENSITY;
D O I
10.1109/JSTARS.2021.3111740
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Recently, the inclusion of spatial information has drawn increasing attention in hyperspectral image (HSI) applications due to its effectiveness in terms of improving classification accuracy. However, most of the techniques that include such spatial knowledge in the analysis are based on spatial-spectral weak assumptions, i.e., all pixels in a spatial region are assumed to belong to the same class, and close pixels in spectral space are assigned the same label. This article proposes a novel structure-aware multikernel learning (SaMKL) method for HSI classification, which takes into account structural issues in order to effectively overcome the aforementioned weak assumptions and introduce a true multikernel learning process (based on multiple features derived from the original HSI), thus improving the spectral separability of such features. The proposed SaMKL method is composed of the following main steps. First, multiple (i.e., spectral, spatial, and textural) features are extracted from the original HSI based on various filtering operators. Then, a k-peak density approach is designed to define superpixel regions that can properly capture the structural information of HSIs and overcome the aforementioned weak assumptions. Next, three sets of composite kernels are separately constructed to make full use of the spectral, spatial, and textural information. Meanwhile, these three sets of composite kernels are independently incorporated into a support vector machine classifier to obtain their corresponding classification results. Finally, majority voting is used as a simple and effective method to obtain the final classification labels. Experimental results on real HSI datasets indicate that the SaMKL outperforms other well-known and state-of-the-art classification approaches, in particular, when very limited labeled samples are available a priori.
引用
收藏
页码:9837 / 9854
页数:18
相关论文
共 73 条
[31]   Spectral-Spatial Gabor Surface Feature Fusion Approach for Hyperspectral Imagery Classification [J].
Jia, Sen ;
Wu, Kuilin ;
Zhu, Jiasong ;
Jia, Xiuping .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (02) :1142-1154
[32]   Gabor Cube Selection Based Multitask Joint Sparse Representation for Hyperspectral Image Classification [J].
Jia, Sen ;
Hu, Jie ;
Xie, Yao ;
Shen, Linlin ;
Jia, Xiuping ;
Li, Qingquan .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (06) :3174-3187
[33]   Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration [J].
Kang, Jian ;
Hong, Danfeng ;
Liu, Jialin ;
Baier, Gerald ;
Yokoya, Naoto ;
Demir, Begum .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (02) :826-840
[34]   Feature Extraction of Hyperspectral Images With Image Fusion and Recursive Filtering [J].
Kang, Xudong ;
Li, Shutao ;
Benediktsson, Jon Atli .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (06) :3742-3752
[35]   Spectral-Spatial Hyperspectral Image Classification With Edge-Preserving Filtering [J].
Kang, Xudong ;
Li, Shutao ;
Benediktsson, Jon Atli .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (05) :2666-2677
[36]   Regionalization of Uncovered Agricultural Soils Based on Organic Carbon and Soil Texture Estimations [J].
Kanning, Martin ;
Siegmann, Bastian ;
Jarmer, Thomas .
REMOTE SENSING, 2016, 8 (11)
[37]   A Subspace-Based Multinomial Logistic Regression for Hyperspectral Image Classification [J].
Khodadadzadeh, Mahdi ;
Li, Jun ;
Plaza, Antonio ;
Bioucas-Dias, Jose M. .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2014, 11 (12) :2105-2109
[38]   Determining the Effects of Storage on Cotton and Soybean Leaf Samples for Hyperspectral Analysis [J].
Lee, Matthew A. ;
Huang, Yanbo ;
Yao, Haibo ;
Thomson, Steven J. ;
Bruce, Lori Mann .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2014, 7 (06) :2562-2570
[39]  
Li CC, 2017, INT GEOSCI REMOTE SE, P1808, DOI 10.1109/IGARSS.2017.8127327
[40]   Efficient Superpixel-Level Multitask Joint Sparse Representation for Hyperspectral Image Classification [J].
Li, Jiayi ;
Zhang, Hongyan ;
Zhang, Liangpei .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (10) :5338-5351