Metrics
185 Record Views
Conference proceeding
Towards UAV-Based Post-Disaster Damage Detection and Localization: Hurricane Sally Case Study
AIAA SCITECH 2022 Forum
AIAA SciTech 2022 (San Diego, USA, 01/03/2022–01/07/2022)
01/03/2022
Abstract
In this study, we investigate the feasibility of detecting post-disaster damages through camera images obtained onboard an Unmanned Aerial Vehicle (UAV). Aerial footage from the University of West Florida (UWF) campus after being hit by hurricane Sally in 2020 is used in our study. Our goal is to automatically locate and identify all the roof damages caused by Sally on the university campus using a Convolutional Neural Network (CNN) based object detection approach. We utilize a TensorFlow Object Detection API model retrained on images hand annotated by our team to demonstrate the damage detection capabilities of CNN. The aim of this study is to propose a framework towards UAV-based post-disaster damage detection and localization to aid the effort of damage recovery after hurricanes.
Related links
Details
- Title
- Towards UAV-Based Post-Disaster Damage Detection and Localization: Hurricane Sally Case Study
- Publication Details
- AIAA SCITECH 2022 Forum
- Resource Type
- Conference proceeding
- Conference
- AIAA SciTech 2022 (San Diego, USA, 01/03/2022–01/07/2022)
- Publisher
- American Institute of Aeronautics and Astronautics
- Format
- link
- Copyright
- © 2022 by Hakki Erhan Sevil.
- Identifiers
- 99380168793806600
- Academic Unit
- Institute for Human and Machine Cognition; Intelligent Systems and Robotics; Hal Marcus College of Science and Engineering
- Language
- English