Image Blending and Landslide Detection Using U-Net Convolutional Neural Network

DOI

10.2991/978-94-6463-662-8_21How to use a DOI?

Keywords

Image Blending; Landslide Detection; CNN; U-Net; OpenCV

Abstract

The paper develops a sophisticated image blending and landslide detection system specifically designed for aerial datasets captured by drones. Utilizing high-resolution drone imagery, the system leverages OpenCV to seamlessly blending multiple images, providing an accurate and comprehensive representation of the terrain. This blending imagery is crucial for analysing large areas, offering a unified view that allows for better assessment and monitoring of land conditions. The landslide detection component of the system employs U-Net, a convolutional neural network architecture that excels in image segmentation tasks. U-Net’s ability to accurately identify and delineate landslide regions within the fusion images ensures precise detection and analysis. This architecture is particularly well-suited for handling the complexities of aerial imagery, such as varying angles, lighting conditions, and terrain features. Real-time monitoring and disaster responses require the ability of the system to segregate landslide-affected and unaffected areas. In assessing the performance of the system, testing has been done on unseen datasets using metrics such as accuracy, precision, recall, and F1 score. These metrics will provide insight into the performance of the system for a wide range of conditions and datasets, ensuring its reliability and robustness. Continuous fine-tuning of the model enhances its adaptability to diverse landscapes and improves its overall detection capability. This research addresses a critical need for efficient analysis of aerial data, particularly in regions prone to natural disasters like landslides. By integrating advanced image blending with cutting-edge landslide detection algorithms, this system has potential applications in environmental monitoring, disaster management, urban planning, and infrastructure assessment, contributing to the innovative use of drone technology in various industries.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Y. Krupa Sagar
AU  - T. Mahesh Babu
AU  - S. Narasimha
AU  - Kalva Sudhakar
PY  - 2025
DA  - 2025/03/17
TI  - Image Blending and Landslide Detection Using U-Net Convolutional Neural Network
BT  - Proceedings of the International Conference on Advanced Materials, Manufacturing and Sustainable Development (ICAMMSD 2024)
PB  - Atlantis Press
SP  - 254
EP  - 273
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-662-8_21
DO  - 10.2991/978-94-6463-662-8_21
ID  - Sagar2025
ER  -