Classification of EgyptSat-1 Images Using Deep Learning Methods

Author(s): Hatem Keshk*, Xu-Cheng Yin

Journal Name: International Journal of Sensors, Wireless Communications and Control

Volume 10 , Issue 1 , 2020

Become EABM
Become Reviewer
Call for Editor

Graphical Abstract:


Background: Deep Learning (DL) neural network methods have become a hotspot subject of research in the remote sensing field. Classification of aerial satellite images depends on spectral content, which is a challenging topic in remote sensing.

Objective: With the aim to accomplish a high performance and accuracy of Egyptsat-1 satellite image classification, the use of the Convolutional Neural Network (CNN) is raised in this paper because CNN is considered a leading deep learning method. CNN is developed to classify aerial photographs into land cover classes such as urban, vegetation, desert, water bodies, soil, roads, etc. In our work, a comparison between MAXIMUM Likelihood (ML) which represents the traditional supervised classification methods and CNN method is conducted.

Conclusion: This research finds that CNN outperforms ML by 9%. The convolutional neural network has better classification result, which reached 92.25% as its average accuracy. Also, the experiments showed that the convolutional neural network is the most satisfactory and effective classification method applied to classify Egyptsat-1 satellite images.

Keywords: Classification, convolutional neural network, deep learning, maximum likelihood, satellite image, accuracy.

McGovern EA, Holden NM, Ward SM, Collins JF. Remote sensed satellite imagery as an information source for industrial peat lands management. Resour Conserv Recycling 2000; 20: 67-83.
Rathore MMU, Paul A, Ahmad A, Chen BW, Huang B, Ji W. Real-Time big data analytical architecture for remote sensing application. IEEE J Sel Top Appl Earth Obs Remote Sens 2016; 8: 4610-21.
Mustapha MR, Lim HS, Jafri MZ. Comparison of neural network and maximum likelihood approaches in image classification. J Appl Sci 2010; 10: 2847-54.
Xiang D, Tang T, Ban Y, et al. Unsupervised polarimetric SAR urban area classification based on model-based decomposition with cross scattering. ISPRS J Photogramm Remote Sens 2016; 116: 86-100.
Wu Q, Zhong R, Zhao W, Fu H, Song K. A comparison of pixel-based decision tree and object-based support vector machine methods for land-cover classification based on aerial images and airborne lidar data. Int J Remote Sens 2017; 38(23): 7176-95.
Basu S, Ganguly S, Mukhopadhyay S, DiBiano R, Karki M, Nemani R. DeepSat: a learning framework for satellite imagery. In: Proc 23rd SIGSPATIAL Int Conf Adv Geograp Info Syst NY. USA. 2015; p. 37.
Arel I, Rose DC, Karnowski T. Deep learning- a new frontier in artificial intelligence research. IEEE Comput Intell Mag 2010; 5(4): 13-8.
Dong W, Zhang L, Shi G. Centralized sparse representation for image restoration IEEE Int Conf Comp Vision. ICCV 2011; pp. 1259-66.
Yang J, Wright J, Huang T, Ma Y. Image super-resolution as sparse representation of raw image patches. IEEE Conf Comp Vision Pattern Recogn (CVPR) 2008; 1-8.
Lu X, Yuan H, Yan P, Yuan Y, Li X. Geometry constrained sparse coding for single image super-resolution. IEEE Conf Comp Vision Pattern Recogn (CVPR) 2012; 1648-55.
Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Comput 2006; 18(7): 1527-54.
Hatem MK, Xu-Cheng Y. Satellite super-resolution images depending on deep learning methods: a comparative study IEEE Int Conf Signal Process, Commun Comput. ICSPCC 2017.
[PMID: 10.1109/ICSPCC.2017.8242625]
Chen S, Wang H, Xu F, et al. Target Classification using the deep convolutional networks for SAR images. IEEE Trans Geosci Remote Sens 2016; 54(8): 4806-17.
Hsieh YT, Chen CT, Chen JC. Applying object based image analysis and knowledge-based classification to ADS-40 digital aerial photographs to facilitate complex forest land cover classification. J Appl Remote Sens 2017; 11(1)015001
Hou B, Luo X, Wang S, et al. Polarimetric SAR images classification using deep belief networks with learning features. IEEE Int Geosci Remote Sensing Symp (IGARSS) IEEE 2015; 2366-9.
Guo Y, Wang S, Gao C, et al. Wishart RBM based DBN for polarimetric synthetic radar data classification. IEEE Int Geosci Remote Sensing Symp (IGARSS) IEEE 2015; 1841-4.
Liu F, Jiao L, Hou B, et al. POL-SAR image classification based on wishart DBN and local spatial information. IEEE Trans Geosci Remote Sens 2015; 54(6): 3292-308.
Janoth J, Gantert S, Schrage T, et al. Terrasar next generation- mission capabilities. IEEE Int Geosci Remote Sensing Symp IEEE 2013; pp. 2297-300.
Juel A, Groom GB, Svenning JC, Ejrnaes R. Spatial application of random forest models for fine-scale coastal vegetation classification using object based analysis of aerial ortho-photo and DEM data. Int J Applied Earth Observ Geoform 2015; 42: 106-14.
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521(7553): 436-44.
eCognition user guider 4, Definies Imaging 2003.
Qu JY, Sun X, Gao X. Remote sensing image target recognition based on CNN. Foreign Electron Measure Tech 2016; 8: 45-50.
Sameen MI, Pradhan B, Aziz OS. Classification of very high resolution aerial photos using spectral-spatial convolutional neural networks. J Sens 2018; 20187195432
Boureau Y, Ponce J, Le Cun Y. A theoretical analysis of feature pooling in visual recognition. ICML 2010; pp. 111-8.
Shin-Jye L, Tonglin C, Lun Y, Chin-Hui L. Image classification based on the boost convolutional neural network. IEEE Acess Translat Content Mining 2018; pp. 2169-3536.
[PMID: 10.1109/ACCESS.2018.2796722]
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. JMLR 2014; 15(1): 1929-58.
Abien FM. Agarap, deep learning using rectified linear units (ReLU). 2018. arXiv:1803.08375v1 [cs.NE].
Duarte D, Nex F, Kerle N, Vosselmana G. Satellite image classification of building damages using airborne and satellite image samples in a deep learning approach. ISPRS Annals Photogramm. Remote Sensing Spatial Info Sci 2018; IV-2
Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. ICML 2010; pp. 807-14.
Tso B, Mather PM. Classification methods for remotely sensed data. 1st ed. Taylor and Francis London 2001.

Rights & PermissionsPrintExport Cite as

Article Details

Year: 2020
Published on: 07 February, 2020
Page: [37 - 46]
Pages: 10
DOI: 10.2174/2210327909666190207153858
Price: $25

Article Metrics

PDF: 10
PRC: 1