Classification of EgyptSat-1 Images Using Deep Learning Methods

摘要

Background: Deep Learning (DL) neural network methods have become a hotspot subjectof research in the remote sensing field. Classification of aerial satellite images depends on spectralcontent, which is a challenging topic in remote sensing.Objective: With the aim to accomplish a high performance and accuracy of Egyptsat-1 satellite imageclassification, the use of the Convolutional Neural Network (CNN) is raised in this paper becauseCNN is considered a leading deep learning method. CNN is developed to classify aerial photographsinto land cover classes such as urban, vegetation, desert, water bodies, soil, roads, etc. In our work, acomparison between MAXIMUM Likelihood (ML) which represents the traditional supervised classificationmethods and CNN method is conducted.Conclusion: This research finds that CNN outperforms ML by 9%. The convolutional neural networkhas better classification result, which reached 92.25% as its average accuracy. Also, the experimentsshowed that the convolutional neural network is the most satisfactory and effective classificationmethod applied to classify Egyptsat-1 satellite images.