Issue |
ITM Web Conf.
Volume 56, 2023
First International Conference on Data Science and Advanced Computing (ICDSAC 2023)
|
|
---|---|---|
Article Number | 02004 | |
Number of page(s) | 9 | |
Section | Data Science | |
DOI | https://doi.org/10.1051/itmconf/20235602004 | |
Published online | 09 August 2023 |
Land cover clustering and classification of satellite images
1 Electronics & Telecommunication, MKSSS’s Cummins College of Engineering for Women, Pune, India
2 Hydraulic Instrumentation, Central Water and Power Research Station (CWPRS), Pune, India
* corresponding author: vaishnavi.kharat@cumminscollege.in
Land cover classification refers to the process of using remote sensing data to categorize different types of land cover like vegetation, water bodies and soil. This is helpful for gaining key information about the surface of the Earth and for the future interactions between human activities and the environment. These predicted interactions lead to the development of sustainable land use practices along with the protection of natural resources. This paper deals with classifying the land cover using unsupervised and supervised methods. The unsupervised method includes land cover detection using a K-means clustering algorithm and the supervised classification is done using random forest classifier. The evaluation parameter values are calculated and compared for the input and output images.
Key words: classification / remote sensing / multiband satellite imagery / rescaling / segmentation
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.