Water Detection Based On Classical Computer Vision Remote Sensing Images

The ability to detect water bodies is a major operation in remote sensing image processing, as it is critical in flood control, water resources, environmental change, farm irrigation planning and ecological conservation. As satellite imaging resolution continues to improve, it has become more difficult to extract water regions with robust and accurate results on complicated backgrounds. In spite of the impressive performance over the past years, the deep learning-based segmentation methods have a limited range of practical use due to their dependence on large-scale labeled datasets, high computational cost, and inability to be interpreted. Conversely, the classical methods of computer vision are still appealing because of their transparency, low level of computation, and little data dependency. This paper suggests a classical image processing-based system of detecting water bodies and generating standard binary masks. The suggested technique combines the Normalized Differences Water Index (NDWI) and blue-channel augmentation to generate a water likelihood map as probabilities of water occurrence. Gaussian smoothing, adaptive thresholding and morphological refinement are used with the aim of maintaining spatial consistency and structural integrity of the water regions that have been detected. The whole system is in the MATLAB and it allows interactive and continuous input of images.
Four RGB scenes from Lake Van, Lake Tana, Hongze Lake, and the Zaling–Eling Lake region were used as a small feasibility set, and the estimated water coverage ranged from 15.85% to 41.26%. Because the exported images do not retain native sensor metadata and no independent pixel-level reference masks were available, these results are treated as a feasibility demonstration rather than a complete accuracy benchmark. The method therefore provides a transparent and training-free baseline, while broader claims of accuracy and generalization require evaluation on georeferenced imagery with independent ground truth

generalization , Water Detection, remote sensing

1. McFeeters, S. K. (1996). The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7), 1425–1432. https://doi.org/10.1080/01431169608948714 [Google Scholar] [Crossref]

2. Xu, H. (2006). Modification of normalized difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14), 3025–3033. https://doi.org/10.1080/01431160600589179 [Google Scholar] [Crossref]

3. Feyisa, G. L., Meilby, H., Fensholt, R., & Proud, S. R. (2014). Automated Water Extraction Index: A new technique for surface water mapping using Landsat imagery. Remote Sensing of Environment, 140, 23–35. https://doi.org/10.1016/j.rse.2013.08.029 [Google Scholar] [Crossref]

4. Du, Z., Li, W., Zhou, D., Tian, L., Ling, F., Wang, H., & Gui, Y. (2016). Analysis of Landsat-8 OLI imagery for land surface water mapping. Remote Sensing Letters, 7(9), 873–882. https://www.mdpi.com/2072-4292/16/11/1984 [Google Scholar] [Crossref]

5. Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62–66. https://ieeexplore.ieee.org/document/4310076 [Google Scholar] [Crossref]

6. Soille, P. (2003). Morphological Image Analysis: Principles and Applications. Springer. https://link.springer.com/book/10.1007/978-3-662-05088-0 [Google Scholar] [Crossref]

7. Gonzalez, R. C., & Woods, R. E. (2018). Digital Image Processing (4th ed.). Pearson. https://books.google.com/books/about/Digital_Image_Processing.html?id =0F05vgAACAAJ [Google Scholar] [Crossref]

8. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention, 234–241. https://link.springer.com/chapter/10.1007/978-3-319-24574-4_28 [Google Scholar] [Crossref]

9. Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). DeepLab: Semantic image segmentation with deep convolutional nets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834–848. https://doi.org/10.1109/TPAMI.2017.2699184 [Google Scholar] [Crossref]

10. Zhang, Y., Wang, Q., & Li, J. (2020). Water body extraction from remote sensing imagery based on improved spectral index. Remote Sensing, 12(4), 652. https://doi.org/10.3390/rs12040652 [Google Scholar] [Crossref]

11. Li, J., Wang, S., & Zhang, Y. (2019). Automatic water detection in remote sensing images using morphological processing. ISPRS Journal of Photogrammetry and Remote Sensing, 154, 20–35. https://doi.org/10.1016/j.isprsjprs.2019.05.011 [Google Scholar] [Crossref]

12. Tao, Z., Yang, Y., & Chen, X. (2021). Classical and deep learning-based methods for water extraction: A comparative study. Remote Sensing, 13(5), 901. https://doi.org/10.3390/rs13050901 [Google Scholar] [Crossref]

13. Google. (2025). Google Earth [Computer software and imagery platform]. https://earth.google.com/ [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet