Post flood assessment using deep learning techniques
Open Access
- 1 January 2023
- conference paper
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2917 (1)
Abstract
Numerous factors, such as a rapid urbanization, increased development and economic activity in flood plains, and climate change are responsible for floods. Utilizing satellite images to analyze the flood areas is an effective technique to accomplish flood area analysis. Houses with completely or partially surrounded by flooded water will help the rescue team to prioritize the rescue areas. Therefore, in this article two custom architectures based on convolutional neural networks (CNN) along with pretrained VGG16 and MobileNet architecture is evaluated for classifying the completely or partially surrounded houses. In this work, a new dataset is prepared from the xBD dataset that comprised of satellite images with flood affected houses. The results showed that MobileNet v4 architecture produces better results with an accuracy of 75%.Keywords
This publication has 18 references indexed in Scilit:
- Disaster Image Classification by Fusing Multimodal Social Media DataISPRS International Journal of Geo-Information, 2021
- Rapid and large-scale mapping of flood inundation via integrating spaceborne synthetic aperture radar imagery with unsupervised deep learningISPRS Journal of Photogrammetry and Remote Sensing, 2021
- BDANet: Multiscale Convolutional Neural Network With Cross-Directional Attention for Building Damage Assessment From Satellite ImagesIEEE Transactions on Geoscience and Remote Sensing, 2021
- Deep learning for post‐hurricane aerial damage assessment of buildingsComputer-Aided Civil and Infrastructure Engineering, 2021
- Unsupervised domain adaptation with self-attention for post-disaster building damage detectionNeurocomputing, 2020
- Deep Learning-Based Identification of Collapsed, Non-Collapsed and Blue Tarp-Covered Buildings from Post-Disaster Aerial ImagesRemote Sensing, 2020
- Structural Building Damage Detection with Deep Learning: Assessment of a State-of-the-Art CNN in Operational ConditionsRemote Sensing, 2019
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Detection of Urban Damage Using Remote Sensing and Machine Learning Algorithms: Revisiting the 2010 Haiti EarthquakeRemote Sensing, 2016
- Flood Assessment using Multi-temporal Modis Satellite ImagesProcedia Computer Science, 2016