Submit Manuscript  

Article Details

Classification of EgyptSat-1 Images Using Deep Learning Methods


Hatem Keshk* and Xu-Cheng Yin  


The deep learning neural network is a recent development that has become the subject of research in the remote sensing filed. Classification of aerial satellite images depending decently on spectral content, which is a challenging topic in remote sensing. In order to achieve high precision classification performance of the satellite images, convolutional neural network (CNN), a kind of representative deep learning method applied in this paper. CNN developed to classify aerial photographs into land cover classes such as urban, vegetation, desert, waterbody, barren land, road, etc. Compared with the traditional supervised classification methods, such as minimum distance and maximum likelihood, the CNN method obtained better classification result with 92.24% average accuracy. The experiments demonstrate that the CNN is an effective and favorable classification method for aerial satellite image classification.


Deep Learning, Classification, Satellite image, Convolutional Neural Network


Data Reception, Analysis, receiving and station affairs, National Authority for Remote Sensing and Space Science, Cairo, Pattern Recognition and Image Processing, School of Engineering and Computer Science, University of Science and Technology Beijing, Beijing

Full Text Inquiry