Abstract
The satellite image classification is categorization of objects available on earth surface using the satellite images. It is one of the very important areas of satellite images processing to understand the changes on the earth surface. So, the main intention behind the following work is to apply the decision trees and radial basis function network-based supervised classification techniques to understand the land cover and land used area in Mumbai. The classifiers are implemented using the MATLAB simulation toolbox. Here the IRS P6 LISS-III satellite image of Mumbai region is used to classify the areas of Mumbai. The different areas of Mumbai region are classified such as the area is covered by water, forest, wetland, and development areas. Decision tree and RBFN classification techniques are trained with the same set of training data and applied on the same set of the testing data set. So, the experimental result of our classifiers shows that the classification accuracy of the RBFN-based satellite image classification is higher than decision tree-based satellite image classification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tao, X., Michel, H.E.: Classification of multispectral satellite image data using improved NRBF neural networks, Proc. SPIE 5267, Intelligent Robots and Computer Vision XXI: Algorithms, Techniques and Active Vision, 311, October, 2003 doi:10.1117/12.518551
Kene, Y.V., Wadkar S.: Object Based Image Analysis of High Resolution Satellite Image using Radial Basis Function Neural Network and Curvelet Transform. European J. Adv. Eng. Techno. 2(5), 103–107 (2015). ISSN: 2394-658X
Keshtkar, H.R., Azarnivand, H., Arzani, H., Alavipanah, S.K., Mellati, F.: Land Cover Classification Using IRS-1D Data and a Decision Tree Classifier. Desert 17(2), 137–146 (2013)
Sharma, R., Aniruddha, G., Joshi, P.K.: Decision tree approach for classification of remotely sensed satellite data using open source support. J. Earth Syst. Sci. 122(5), 1237–1247 (2013)
Ghose, M.K., Pradhan, R., Ghose, S.S.: Decision Tree Classification of Remotely Sensed Satellite Data using Spectral Separability Matrix. Int. J. Adv. Comp. Sci. App. 1(5), 93–101 (2010)
Havyas, V.B., Choodarathnakara, A.L., Thribhuvan, R., Chethan, K.S.: Decision Tree Approach for Classification of Satellite Imagery. Int. J. Soft Computing Eng. (IJSCE) 5(2), (2015), ISSN: 2231–2307
Upadhyay, A., Singh, S.K.: Classification of IRS LISS-III images using PNN, Proceeding of the 9th INDIACom;2nd International conference on computing for sustainable global development, Organized by BVICAM, New Delhi, 11th–13th March, 2015, published in IEEEXplore, ISBN:978-93-80544-15-1
Acknowledgements
Thanks to NRSA, Hyderabad, Telangana, India for providing the LISS-III data sets free online.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Upadhyay, A., Singh, S.k., Gaikwad, S.K., Mukherjee, A.C. (2018). Classification and Comparative Study of IRS LISS-III Satellite Images Using RBFN and Decision Tree. In: Urooj, S., Virmani, J. (eds) Sensors and Image Processing. Advances in Intelligent Systems and Computing, vol 651. Springer, Singapore. https://doi.org/10.1007/978-981-10-6614-6_25
Download citation
DOI: https://doi.org/10.1007/978-981-10-6614-6_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6613-9
Online ISBN: 978-981-10-6614-6
eBook Packages: EngineeringEngineering (R0)