Abstract
Hyperspectral images (HSIs) have great potential in military reconnaissance, land use, marine monitoring and many other fields. In recent years, the convolutional neural network (CNN) has been successfully used to classify hyperspectral data and achieved remarkable performance. However, the limited labeled samples of HSI lead to the small sample size problem, which remains the major challenge for CNN-based HSI classification. Besides, most CNN models have large number of parameters needed to be learned, which cause high computational cost. To address the aforementioned two issues, a novel CNN-based HSI classification method is proposed. The proposed classification method has several distinguishing characteristics. First, the proposed method can robustly extract spectral and spatial features of the HSI simultaneously. Second, in the proposed CNN architecture, all convolution layers are 1 × 1 convolution layer except the first one, which can greatly reduce the number of network parameters, thus accelerating the training and testing process. Third, a small convolution and feature reuse (SC-FR) module is developed. The SC-FR module is composed of two composite layers and each composite layer consists of two cascaded 1 × 1 convolution layers. Through cross-layer connecting, the input and output features of each composite layer are concatenated and passed to the next convolution layer, thus achieving feature reuse mechanism. Cross-layer connection increases information flow and the utilization rate of middle-level features, which enhances the generalization performance of CNN effectively. Experimental results on three benchmark HSIs demonstrate the competitive superiority of the proposed method over several state-of-the-art HSI classification methods, especially when training samples are limited.
Similar content being viewed by others
References
Gevaert CM, Suomalainen J, Tang J, Kooistra L (2015) Generation of spectral–temporal response surfaces by combining multispectral satellite and hyperspectral UAV imagery for precision agriculture applications. IEEE J Sel Top Appl Earth Obs Remote Sens 8(6):3140–3146
Yuen PW, Richardson M (2013) An introduction to hyperspectral imaging and its application for security, surveillance and target acquisition. J Photogr Sci 58(5):241–253
Zhang CY, Cheng HF, Chen ZH, Zheng WW (2008) The development of hyperspectral remote sensing and its threatening to military equipments. Electro-Opt Technol Appl 23(1):10–12
Sandidge JC, Holyer RJ (1998) Coastal bathymetry from hyperspectral observations of water radiance. Remote Sens Environ 65(3):341–352
Gao HM, Yang Y, Li CM, Zhou H, Qu XY (2018) Joint alternate small convolution and feature reuse for hyperspectral image classification. ISPRS Int J Geo-Inf 7(9):349
Chen Y, Nasrabadi NM, Tran TD (2013) Hyperspectral image classification via kernel sparse representation. IEEE Trans Geosci Remote Sens 51(1):217–231
Qian Y, Ye M, Zhou J (2013) Hyperspectral image classification based on structured sparse logistic regression and three-dimensional wavelet texture features. IEEE Trans Geosci Remote Sens 51(4):2276–2291
Melgani F, Bruzzone L (2004) Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Remote Sens 42(8):1778–1790
Li J, Du Q, Li W et al (2015) Optimizing extreme learning machine for hyperspectral image classification. J Appl Remote Sens 9(1):097296
Zhang X, Song Q, Gao Z et al (2017) Spectral–spatial feature learning using cluster-based group sparse coding for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 9(9):4142–4159
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: International conference on neural information processing systems. Curran Associates Inc., pp 1097–1105
Mou L, Ghamisi P, Zhu XX (2017) Deep recurrent neural networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens 55(7):3639–3655
Zhang ZW, Sun Z, Liu JQ, Chen JW, Huo Z, Zhang X (2016) Deep recurrent convolutional neural network: improving performance for speech recognition. arXiv:1611.07174v2
Xie S, Girshick R, Dollar P, Tu ZW, He KM (2017) Aggregated residual transformations for deep neural networks. arXiv:1611.05431v2
Young T, Hazarika D, Poria S, Cambria E (2018) Recent trends in deep learning based natural language processing. arXiv:1708.02709v6
Yu SQ, Jia S, Xu CY (2016) Convolutional neural networks for hyperspectral image classification. Neurocomputing 219:88–98
Ren SQ, He KM, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: International conference on neural information processing systems. MIT Press, pp 91–99
Makantasis K, Karantzalos K, Doulamis A, et al (2015) Deep supervised learning for hyperspectral data classification through convolutional neural networks. In: Geoscience and remote sensing symposium (IGARSS), 2015 IEEE international. IEEE
Gao HM, Yang Y, Lei S, Li CM, Zhou H, Qu XY (2019) Multi-branch fusion network for hyperspectral image classification. Knowl-Based Syst 2019(167):11–25
Chen YS, Zhu L, Ghamisi P, Jia XP, Li GY, Tang L (2017) Hyperspectral images classification with gabor filtering and convolutional neural network. IEEE Geosci Remote Sens Lett 14(12):2355–2359
Liang H, Li Q (2016) Hyperspectral imagery classification using sparse representations of convolutional neural network features. Remote Sens 8(2):99
Lee H, Kwon H (2017) Going deeper with contextual CNN for hyperspectral image classification. IEEE Trans Image Process 26(10):4843–4855
Paoletti ME, Haut JM, Plaza J, Plaza A (2018) A new deep convolutional neural network for fast hyperspectral image classification. ISPRS J Photogramm Remote Sens 145:120–147. https://doi.org/10.1016/j.isprsjprs.2017.11.021
Cao X, Zhou F, Xu L et al (2018) Hyperspectral image classification with Markov random fields and a convolutional neural network. IEEE Trans Image Process 27(5):2354–2367
Zhong Z, Li J, Luo Z et al (2018) Spectral–spatial residual network for hyperspectral image classification: a 3-D deep learning framework. IEEE Trans Geosci Remote Sens 56(2):847–858
Song W, Li S, Fang L et al (2018) Hyperspectral image classification with deep feature fusion network. IEEE Trans Geosci Remote Sens 56(6):3173–3184
Ma Xiaorui Fu, Anyan Wang Jie et al (2018) Hyperspectral image classification based on deep deconvolution network with skip architecture. IEEE Trans Geosci Remote Sens 56(8):4781–4791
Fang B, Li Y, Zhang HK et al (2019) Hyperspectral images classification based on dense convolutional networks with spectral-wise attention mechanism. Remote Sens 11(2):159
He KM, Zhang XY, Ren SQ, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. arXiv:1502.01852v1
Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: International conference on international conference on machine learning. Omnipress, pp 807–814
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167v3
Fang L, Liu G, Li S et al (2019) Hyperspectral image classification with squeeze multibias network. IEEE Trans Geosci Remote Sens 57(3):1291–1301
Shu L, Mcisaac K, Osinski GR (2018) Hyperspectral image classification with stacking spectral patches and convolutional neural networks. IEEE Trans Geosci Remote Sens 56(10):5975–5984
Zhi L, Yu XC, Li B et al (2019) A dense convolutional neural network for hyperspectral image classification. Remote Sens Lett 10(1):59–66
Huang G, Liu Z, Maaten LVD, Weinberger KQ (2017) Densely connected convolutional networks. arXiv:1608.06993v3
He KM, Zhang XY, Ren SQ, Sun J (2015) Deep residual learning for image recognition. arXiv:1512.03385v1
Acknowledgements
This work was supported by National Natural Science Foundation of China (No. 61701166), National Key R&D Program of China (No. 2018YFC1508106), China Postdoctoral Science Foundation (No. 2018M632215), Fundamental Research Funds for the Central Universities (No. 2018B16314), Science Fund for Distinguished Young Scholars of Jiangxi Province under Grant (No. 2018ACB21029), Young Elite Scientists Sponsorship Program by CAST (No. 2017QNRC001), National Science Foundation for Young Scientists of China (Nos. 51709271, 41601435).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gao, H., Yang, Y., Li, C. et al. Convolutional neural network for spectral–spatial classification of hyperspectral images. Neural Comput & Applic 31, 8997–9012 (2019). https://doi.org/10.1007/s00521-019-04371-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-019-04371-x