Multi-spectral remote sensing images feature coverage classification based on improved convolutional neural network

Yufeng Li; Chengcheng Liu; Weiping Zhao; Yufeng Huang; Yufeng Li; Chengcheng Liu; Weiping Zhao; Yufeng Huang

doi:10.3934/mbe.2020245

Mathematical Biosciences and Engineering

2020, Volume 17, Issue 5: 4443-4456. doi: 10.3934/mbe.2020245

Previous Article Next Article

Research article Special Issues

Multi-spectral remote sensing images feature coverage classification based on improved convolutional neural network

Key Laboratory of Aerospace Information Perception and Intelligent Processing, College of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110122, China

Received: 03 April 2020 Accepted: 14 June 2020 Published: 23 June 2020

With the continuous development of the earth observation technology, the spatial resolution of remote sensing images is also continuously improved. As one of the key problems in remote sensing images interpretation, the classification of high-resolution remote sensing images has been widely concerned by scholars at home and abroad. With the improvement of science and technology, deep learning has provided new ideas for the development of image classification, but it has not been widely used in remote sensing images processing. In the background of remote sensing huge data, the remote sensing images classification based on deep learning proposed in the study has more research significance and application value. The study proposes a high-resolution remote sensing images classification method based on an improved convolutional neural network. The traditional convolutional neural network framework is optimized and the initial structure is added. The actual classification results of radial basis functions and support vector machine are compared horizontally. The classification results of hyperspectral images were presented that the improved method can perform better in overall accuracy and Kappa coefficient. The commission errors of support vector machine classification method are more than 6 times of that of the improved convolutional neural network classification method and the overall accuracy of the improved convolutional neural network classification method has reached 97% above.
- convolutional neural network,
- support vector machine,
- radial basis function,
- remote sensing images classification,
- inception
Citation: Yufeng Li, Chengcheng Liu, Weiping Zhao, Yufeng Huang. Multi-spectral remote sensing images feature coverage classification based on improved convolutional neural network[J]. Mathematical Biosciences and Engineering, 2020, 17(5): 4443-4456. doi: 10.3934/mbe.2020245

Related Papers:

Abstract

With the continuous development of the earth observation technology, the spatial resolution of remote sensing images is also continuously improved. As one of the key problems in remote sensing images interpretation, the classification of high-resolution remote sensing images has been widely concerned by scholars at home and abroad. With the improvement of science and technology, deep learning has provided new ideas for the development of image classification, but it has not been widely used in remote sensing images processing. In the background of remote sensing huge data, the remote sensing images classification based on deep learning proposed in the study has more research significance and application value. The study proposes a high-resolution remote sensing images classification method based on an improved convolutional neural network. The traditional convolutional neural network framework is optimized and the initial structure is added. The actual classification results of radial basis functions and support vector machine are compared horizontally. The classification results of hyperspectral images were presented that the improved method can perform better in overall accuracy and Kappa coefficient. The commission errors of support vector machine classification method are more than 6 times of that of the improved convolutional neural network classification method and the overall accuracy of the improved convolutional neural network classification method has reached 97% above.

References

[1]	W. J. Yan, D. H. Chen, L. Liu, Research progress of hyperspectral image classification, Opt. Precis. Eng., 27 (2019), 680-693.
[2]	S. Y. Chen, H. Z. Lin, X. Zhao, G. Wang, Deep learning-based classification of hyperspectral data, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 7 (2014), 2094-2107.
[3]	F. W. Fu, B. W. Zou, Review of remote sensing image classification based on deep learning, Appl. Res. Comput., 35 (2018), 3521-3525.
[4]	J. Zhao, Y. Zhong, H. Shu, L. P. Zhang, High-resolution image classification integrating spectral-spatial-location cues by conditional random fields, IEEE. Trans. Image Process. Publ. IEEE Signal Process. Soc., 25 (2016), 4033-4045.
[5]	A. B. Salberg, Detection of seals in remote sensing images using features extracted from deep convolutional neural network, Geosci. Remote Sens. Symp. IEEE, (2015), 1893-1896.
[6]	C. Cortes, V. Vapnik, Support-vector networks, Mach. Learn., 3 (1995), 273-297.
[7]	D. C. Feng, G. Chen, W. Y. Du, X. Y. Wu, K. L. Xiao, Remote sensing image classification based on minimum distance method, J. Beihua. Inst. Aerosp. Technol., 22 (2012), 1-3.
[8]	A. Ahmad, S. Hashmi, K-Harmonic means type clustering algorithm for mixed datasets, Appl. Soft Comput., (2016), 39-49.
[9]	Y. Zhang, H. T. Yang, C. H. Yuan, A survey of remote sensing image classification methods, J. Weapon Equip. Eng., 39 (2018), 108-112.
[10]	M. Volpi, D. Tuia, Dense semantic labeling of subdecimeter resolution images with convolutional neural networks, IEEE Trans. Geosci. Remote Sens., (2017), 1-13.
[11]	G. E. Hinton, R. R. Salakhutdinov, Reducing the dimensionality of data with neural networks, Sci., 313 (2006), 504-507.
[12]	W. Y. Pang, L. M. Sun, H. X. Jiang, L. X. Li, Convolution in convolution for network in network, IEEE Trans. Neural Networks. Learn. Syst., 29 (2018), 1587-1597.
[13]	A. S. Razavian, H. Azizpour, J. Sullivan, S. Carlsson, CNN features off-the-shelf: An astounding baseline for recognition, Comput. Vision Pattern Recognit. Workshops. IEEE, (2014), 512-519.
[14]	J. P. Zhao, W. W. Guo, S. Y. Cui, Z. H. Zhang, Convolutional neural network for SAR image classification at patch level, Geosci. Remote Sens. Symp. IEEE, (2016), 945-948.
[15]	H. B. Lyu, H. Lu, L. C. Mou, Learning a transferable change rule from a recurrent neural network for land cover change detection, Remote Sens., 8 (2016).
[16]	N. Kussul, M. Lavreniuk, S. V. Skakun, A. Y. Shelestov, Deep learning classification of land cover and crop types using remote sensing data, IEEE Geosci. Remote Sens. Lett., 14(2017), 778-782.
[17]	R. Marc, K. Marco, Multi-temporal land cover classification with sequential recurrent encoders, ISPRS Int. J. Geo-Inf., 7 (2018).
[18]	Y. Liu, Z. S. Liao, Multiple kernel learning with the generalized error bound of support vector machine, J. Wuhan Univ. (Nat. Sci. Ed.), 58 (2012), 149-156.
[19]	Q. J. Zhang, X. J. Zhang. Z. Zhao, Y. J. Wang, Classification of polarimetric SAR images based on multiscale segmentation and radial basis function neural network, Geomat. Spat. Inf. Technol., (2019), 67-71.
[20]	M. Zhou, Dimension reduction and classification of hyperspectral remote sensing image based on RBF neural network, Territ. Nat. Resour. Study, (2016), 14-16.
[21]	P. V. Arun, K. M. Buddhiraju, A. Porwal, CNN based sub-pixel mapping for hyperspectral images, Neurocomput., 311 (2018), 51-64.
[22]	A. Krizhevsky, I. Sutskever, G. Hinton, Image net classification with deep convolutional neural networks, NIPS, 60 (2017), 84-90.
[23]	C. Szegedy, V. Vanhoucke, S. Loffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, IEEE Conf. Comput. Vision Pattern Recognit., 2016.
[24]	Krizhevsky, Alex, Sutskever, Ilya, Hinton, E. Geoffrey, Image net classification with deep convolutional neural networks, Commun. ACM, 60 (2012), 84-90.
[25]	Q. Z. Gong, P. Zhong, Y. Yu, D. W. Hu, Diversity-promoting deep structural metric learning for remote sensing scene classification, IEEE Trans. Geosci. Remote Sens., (2017), 1-20.
[26]	X. Glorot, A. Bordes, Y. Bengio, Deep sparse rectifier neural networks, J. Mach. Learn. Res., 2011.
[27]	N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., (2014), 1929-1958.

Reader Comments

Your name:*

Email:*
© 2020 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)