Rapid post-disaster assessment of residential buildings using Unmanned Aerial Vehicles
Bibliographic Data
| ID | 22028734 |
|---|---|
| Authors | Daniel Jozi (0009-0005-1115-3197, University of Alberta), Nima Shirzad-Ghaleroudkhani (0000-0002-8387-2036, University of Alberta, corresponding author), Garvit Luhadia (0009-0004-1836-8951, University of Alberta), Shaghayegh Abtahi (0000-0003-3322-5583, University of Alberta), Mustafa GÜL (0000-0001-7641-3256, University of Alberta) |
| Year | 2024 |
| Volume | 111 |
| Pages | 104707 |
| Publication date | 2024-09-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | International Journal of Disaster Risk Reduction (JOURNAL) |
| Journal identifiers | ISSN: 2212-4209 |
| Publisher | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.ijdrr.2024.104707 |
| OpenAlex | W4401075095 |
| Language | EN |
| Citations received | 1 |
| References cited | 31 |
Disasters impose significant costs on the built environment due to extensive damages. Accelerated by climate change, disasters such as hurricanes have recently become more frequent and destructive, underscoring the need for rapid post-disaster assessments toward swift search and rescue efforts and damage evaluations. In this regard, this study proposes an image-processing-based method employed on Unmanned Aerial Vehicle (UAV) imagery for automatic assessment of post-disaster damaged buildings. The proposed approach integrates texture-based features, including dissimilarity and homogeneity, along with edge-based features, for which Canny edge detection is employed. The edge-based features introduce novel indices representing the level of irregularity by assessing the entropy as well as the uniformity in the distribution of edge angles. The proposed features are fed into a Naïve Bayesian Classification process to classify damaged and undamaged classes, which makes it possible to account for the underlying uncertainties. The proposed method demonstrates a validation accuracy of 89.3 percent using real-life post-disaster images, effectively distinguishing between damaged and undamaged houses. The findings underscore the potential of employing UAV-captured images and advanced image processing techniques for rapid and accurate post-disaster damage assessment
Aeronautics · Civil engineering · Transport engineering · 3D Surveying and Cultural Heritage · Engineering · Environmental Science · Remote Sensing and LiDAR Applications · Robotics and Sensor-Based Localization
| Citations per year | 1 |
|---|---|
| Citation span | 2026 - 2026 (1) |
| Highly cited | No |