Land-Water Classification for Satellite Images

Abstract

Satellite image analysis plays a crucial role in fields such as environmental monitoring, urban planning, agriculture, and disaster management. This project presents a machine learning-based methodology for the automated segmentation and classification of objects in satellite images. The proposed system employs a two-step algorithm: (1) K-Means clustering for unsupervised segmentation of satellite images into meaningful clusters, and (2) Support Vector Machine (SVM) for supervised classification of the segmented regions into predefined categories such as land, water, and vegetation. A Flask-based web application is developed to provide a userfriendly interface for uploading satellite images and visualizing classified results. The backend is supported by a structured SQL database to manage image metadata and classification outputs efficiently. The system is designed to handle large datasets, ensuring robustness and scalability. Experimental results on benchmark datasets demonstrate high accuracy in object detection and classification, highlighting the system\'s potential to support real-world decision-making in environmental and infrastructural domains.

Introduction

Summary:

Satellite image analysis is vital for applications like environmental monitoring, urban planning, agriculture, and disaster management. Traditional methods struggle with the complexity and large data volume of satellite images, prompting the use of advanced machine learning techniques.

This project proposes a two-step machine learning approach combining K-Means clustering and Support Vector Machine (SVM) classification for accurate segmentation and classification of satellite images. First, K-Means performs unsupervised segmentation by grouping pixels into clusters based on similarity, simplifying the image into meaningful regions such as land, water, and vegetation. Then, an SVM classifier assigns these segments to predefined categories with high accuracy.

The system is implemented as a Flask-based web application with a user-friendly interface for uploading images and visualizing results. A structured SQL database manages metadata and classification outcomes, ensuring scalability and efficient data handling.

The workflow includes preprocessing steps (resizing, color conversion, noise reduction), feature extraction (texture, color, edges), and model training/testing. Experimental results demonstrate strong performance metrics like accuracy, precision, recall, and F1-score, making the system suitable for real-world applications requiring fast, reliable satellite image interpretation.

Conclusion

The proposed K-Means and SVM-based classification system provides an effective approach for satellite image analysis by combining unsupervised segmentation and supervised classification. The K-Means clustering algorithm efficiently segments satellite images into distinct land cover types, while the Support Vector Machine (SVM) classifier accurately categorizes these regions into predefined classes such as land, water, and vegetation. Through feature extraction techniques like GLCM, LBP, and edge detection, the system enhances classification precision, ensuring high accuracy, scalability, and robustness. The experimental results demonstrate the model’s ability to handle complex satellite imagery, making it highly applicable for environmental monitoring, disaster management, and urban planning.

References

[1] Zaaj I.,Brahim C.Khalil ,Extraction of building in satellite image THR using feature detection, International Journal of Computer Applications, vol.181, No.10,pp. 23-27, 2018. [2] Sharma P., Computer Vision Tutorial: A Stepby-Step Introduction to Image Segmentation Techniques.,https://www.analyticsvidhya.com/bl og/2019/04/introductionimage-segmentationtechniques, 2019. [3] Yin, S., Zhang, Y., & Karim, S. Large scale remote sensing image segmentation based on fuzzy region competition and gaussian mixture model, IEEE Access, vol 6,pp. 26069- 26080, 2018. [4] W. Wu, H. Li, L. Zhang, X. Li, and H. Guo, “High-resolution PolSAR scene classification with pretrained deep convnets and manifold polarimetric parameters,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 10, pp. 6159–6168, Oct. 2018. [5] Fawwaz, I., Zarlis, M. & Rahmat R. F, The edge detection enhancement on satellite image using bilateral filter. IOP Conference Series: Materials Science and Engineering,vol.308,no.1,p. 012052, 2018 [6] Chethan K.S., Sinchana G.S.,Dr. Nataraj K.R.,Dr.Choodarathnakara A.L., Analysis of image quality using sobel filter, International Conference on Inventive Systems and Control IEEE Explore Part Number CFP19J06- ART,pp.526-531, 2019.

Copyright

Copyright © 2025 D. V. Ravi Kumar, V.V.V. Lakshman, M. Trylokya, M. Lakshman Rao, K. Bhagya Sri. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.