Publication Type : Conference Paper
Publisher : 4th International Conference on Information and Communication Technology for Intelligent Systems
Source : 4th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2020, Smart Innovation, Systems and Technologies, Springer Singapore, Volume 195, Singapore, p.703-713 (2021)
Url : https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096499236&doi=10.1007%2f978-981-15-7078-0_70&partnerID=40&md5=c264c958a090f41b392d094cf50a7652
ISBN : 9789811570780
Keywords : classification, Convolutional neural network, Eurosat, Image preprocessing, LANDSAT, Satellite image, Unused area, Used area
Year : 2021
Abstract : In this work, we are creating a system to classify satellite images in order to extract information using image processing techniques. Classification of satellite images into used and unused areas and also subclassing of each of the classes into four different classes has been carried out. Used satellite images further classified into residential, industries, highways, crop lands, and unused images are classified further into forest, river, deserts, and beaches. Manual classification by using image interpretation technique requires more time and field experts. So in our work, we focused with efficient automatic satellite image classification. Convolutional neural network is used for feature extraction and classification of satellite images. CNN is a deep neural networks which is most suitable when we deal with images. CNN will help to provide higher classification accuracy. Confusion matrix is used to estimate the overall classification accuracy.
Cite this Research Publication : N. Manohar, Pranav, M. A., Aksha, S., and Mytravarun, T. K., “Classification of Satellite Images”, in 4th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2020, Smart Innovation, Systems and Technologies, Singapore, 2021, vol. 195, pp. 703-713.