3-D Gabor Convolutional Neural Network for Hyperspectral Image Classification

被引:36
作者
Jia, Sen [1 ,2 ]
Liao, Jianhui [1 ,2 ]
Xu, Meng [1 ,2 ]
Li, Yan [1 ]
Zhu, Jiasong [2 ]
Sun, Weiwei [3 ]
Jia, Xiuping [4 ]
Li, Qingquan [2 ]
机构
[1] Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Peoples R China
[2] Shenzhen Univ, Key Lab Geoenvironm Monitoring Coastal Zone, Minist Nat Resources, Shenzhen 518060, Peoples R China
[3] Ningbo Univ, Coll Architectural Engn, Civil Engn & Environm, Ningbo 315211, Peoples R China
[4] Univ New South Wales, Sch Engn & Informat Technol, Canberra, ACT 2612, Australia
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2022年 / 60卷
基金
中国国家自然科学基金;
关键词
Feature extraction; Kernel; Training; Hyperspectral imaging; Data mining; Data models; Convolution; Convolutional neural networks (CNNs); Gabor wavelet; hyperspectral image (HSI); DISCRIMINANT-ANALYSIS;
D O I
10.1109/TGRS.2021.3087186
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Due to the detailed spectral information through hundreds of narrow spectral bands provided by hyperspectral image (HSI) data, it can be employed to accurately classify diverse materials of interest, which is one of the core applications of hyperspectral remote sensing technology. In recent years, with the rapid development of deep learning, convolutional neural networks (CNNs) have been successfully applied in many fields, including HSI classification. However, the random gradient descent-based parameter updating scheme is too general and leading to the inefficiency of CNN models. Moreover, the high dimensionality and limited training samples of HSI data also exacerbate the overfitting problem. To tackle these issues, in this article, a novel deep network with multilayer and multibranch architecture, named 3-D Gabor CNN (3DG-CNN), is proposed for HSI classification. More precisely, since the predefined 3-D Gabor filters in multiple scales and orientations could well characterize the internal spatial-spectral structure of HSI data from various perspectives, the 3-D Gabor-modulated kernels (3-D GMKs) are employed to replace the random initialization kernels. Moreover, the specially designed multibranch architecture enables the network to better integrating the scalable property of 3-D Gabor filters; thus, the representative ability and robustness of the extracted features can be greatly improved. Alternatively, the number of network parameters is substantially reduced due to the incorporation of 3-D Gabor modulation, relieving the training complexity and also alleviating the training process from overfitting. Experimental results on four real HSI datasets (including two newly released ones in the literature) have demonstrated that the proposed 3DG-CNN model can achieve better performance than several widely used machine-learning-based and deep-learning-based approaches. For the sake of reproducibility, the codes of the proposed 3DG-CNN model are available at http://jiasen.tech/papers/.
引用
收藏
页数:16
相关论文
共 48 条
[1]  
[Anonymous], 2018, IEEE GRSS Data Fusion Contest
[2]   3-D Deep Learning Approach for Remote Sensing Image Classification [J].
Ben Hamida, Amina ;
Benoit, Alexandre ;
Lambert, Patrick ;
Ben Amar, Chokri .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (08) :4420-4434
[3]   Evaluation of the effects of Gabor filter parameters on texture classification [J].
Bianconi, Francesco ;
Fernandez, Antonio .
PATTERN RECOGNITION, 2007, 40 (12) :3325-3335
[4]   Hyperspectral Remote Sensing Data Analysis and Future Challenges [J].
Bioucas-Dias, Jose M. ;
Plaza, Antonio ;
Camps-Valls, Gustavo ;
Scheunders, Paul ;
Nasrabadi, Nasser M. ;
Chanussot, Jocelyn .
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE, 2013, 1 (02) :6-36
[5]   Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction [J].
Bruce, LM ;
Koger, CH ;
Li, J .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (10) :2331-2338
[6]  
Calderon A., 2003, PROC INT C COMPUT IN, P429
[7]  
[岑奕 Cen Yi], 2020, [遥感学报, Journal of Remote Sensing], V24, P1299
[8]  
Chang SY, 2014, INTERSPEECH, P905
[9]   Hyperspectral Images Classification With Gabor Filtering and Convolutional Neural Network [J].
Chen, Yushi ;
Zhu, Lin ;
Ghamisi, Pedram ;
Jia, Xiuping ;
Li, Guoyu ;
Tang, Liang .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2017, 14 (12) :2355-2359
[10]   Deep Learning-Based Classification of Hyperspectral Data [J].
Chen, Yushi ;
Lin, Zhouhan ;
Zhao, Xing ;
Wang, Gang ;
Gu, Yanfeng .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2014, 7 (06) :2094-2107