• Version
• Download 4
• File Size 262.85 KB
• File Count 1
• Create Date 24 March 2026
• Last Updated 24 March 2026

Flood Area Detection and Image Segmentation using Deep Learning for Disaster Monitoring

Dr. K. Satyam1, Salapakshi Bhavana2
1Associate Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati,Andhra Pradesh, India.
2 Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, AndhraPradesh, India.

Abstract:One of the most damaging natural disasters, floods seriously harm human lives, infrastructure, and agriculture. Effective disaster response and management depend on the early identification of flood-affected areas. Conventional flood monitoring techniques mostly rely on satellite analysis and human observation, which can be ineffective and slow in emergency conditions. This study suggests a deep learning-based flood picture segmentation system that automatically identifies flooded areas from aerial photos in order to solve this problem. The suggested method creates binary masks that depict flooded areas by identifying flood areas using a segmentation model based on convolutional neural networks. An overlay visualization that prominently displays the flooded areas is created by combining the predicted masks with the original image. Additionally, a web-based interface is created that enables users to upload photographs and receive real-time prediction results. The highlighted flood areas, the original image, and the anticipated segmentation mask are all shown by the system. The suggested method may successfully identify flood-affected areas and produce useful visual outputs, according to experimental results. During emergency response activities, this device can help disaster management authorities monitor flood conditions and make quicker choices.
Keywords: Flood Detection, Deep Learning, Image Segmentation, Semantic Segmentation, Disaster Management,Computer Vision, Flood Area Detection, Remote Sensing