Abstract
With the rapid development of hyper-spectral imaging techniques, hyper-spectral image classification has been applied to many tasks such as monitoring, astronomy and substance exploration. Hyper-spectral Images with rich spatial and spectral content is more difficult to be classified than common images with RGB channels. Many deep learning methods have ignored the context between spectral features when extracting spectral-spatial features of hyper-spectral images. So we implemented a 3D Convolution Neural Network model to extract correlated and effective features and improve the performance for Hyper-spectral Images classification. The hyper-spectral data set we use is the University of Pavia which has less training samples. So we exploited dropout and cross validation methods in the training process to avoid over fitting and we have extended the training samples by some transformation. The results of our experiments have shown that our model can generally get better results than some of the state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Scholkopf, B., Smola, A.J.: Learning With Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2001)
Krishnapuram, B., Carin, L., Figueiredo, M.A.T., Hartemink, A.J.: Sparse multinomial logistic regression: fast algorithms and generalization bounds. IEEE Trans. Pattern Anal. Mach. Intell. 27(6), 957–968 (2005)
Benediktsson, J.A., Palmason, J.A., Sveinsson, J.R.: Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Trans. Geosci. Remote Sens. 43(3), 480–491 (2005)
Camps-Valls, G., Gomez-Chova, L., Muoz-Mar, J., Vila-Francs, J.: Composite kernels for hyperspectral image classification. IEEE Geosci. Remote Sens. Lett. 3(1), 93–97 (2006)
Chen, Y., Nasrabadi, N.M., Tran, T.D.: Hyperspectral image classification using dictionary based sparse representation. IEEE Trans. Geosci. Remote Sens. 49(10), 3973–3985 (2011)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings Advances in Neural Information Processing Systems, pp. 1907–1105 (2012)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings IEEE Conference Computer Vision and Pattern Recognition, pp. 1–9, June 2015
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings IEEE Conference Computer Vision and Pattern Recognition, pp. 770–778, June 2016
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. https://arxiv.org/abs/1409.1556 (2014)
Li, J., et al.: Multiple feature learning for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 53(3), 1592–1606 (2015)
Le Cun, Y., et al.: Handwritten digit recognition with a backpropagation network. In: Proceedings Advances in Neural Information Processing Systems, pp. 396–404 (1990)
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Li, Y., Zhang, H., Shen, Q.: Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens. 9(1), 67 (2017)
Lee, H., Kwon, H.: Going deeper with contextual cnn for hyperspectral image classification. IEEE Trans. Image Process. 26(10), 4843–4855 (2016)
Li, J., Plaza, A., Jia, X., Bioucas-Dias, J.M.: A discontinuity preserving relaxation scheme for spectral-spatial Hyperspectral image classification. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 9(2), 625–639 (2016)
Chen, Y., Jiang, H., Li, C., et al.: Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans. Geosci. Remote Sens. 54(10), 6232–6251 (2016)
Yang, X., Ye, Y., Li, X., et al.: Hyperspectral image classification with deep learning models. IEEE Trans. Geosci. Remote Sens. PP(99), 1–16 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mei, Z., Wang, L., Guo, C. (2019). Hyper-spectral Images Classification Based on 3D Convolution Neural Networks for Remote Sensing. In: Yu, Q. (eds) Space Information Networks. SINC 2018. Communications in Computer and Information Science, vol 972. Springer, Singapore. https://doi.org/10.1007/978-981-13-5937-8_21
Download citation
DOI: https://doi.org/10.1007/978-981-13-5937-8_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-5936-1
Online ISBN: 978-981-13-5937-8
eBook Packages: Computer ScienceComputer Science (R0)