Deep Learning-Enabled Semantic Inference of Individual Building Damage Magnitude from Satellite Images
Natural disasters are phenomena that can occur in any part of the world. They can cause massive amounts of destruction and leave entire cities in great need of assistance. The ability to quickly and accurately deliver aid to impacted areas is crucial toward not only saving time and money, but, most...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/13/8/195 |
| _version_ | 1797558431550275584 |
|---|---|
| author | Bradley J. Wheeler Hassan A. Karimi |
| author_facet | Bradley J. Wheeler Hassan A. Karimi |
| author_sort | Bradley J. Wheeler |
| collection | DOAJ |
| description | Natural disasters are phenomena that can occur in any part of the world. They can cause massive amounts of destruction and leave entire cities in great need of assistance. The ability to quickly and accurately deliver aid to impacted areas is crucial toward not only saving time and money, but, most importantly, lives. We present a deep learning-based computer vision model to semantically infer the magnitude of damage to individual buildings after natural disasters using pre- and post-disaster satellite images. This model helps alleviate a major bottleneck in disaster management decision support by automating the analysis of the magnitude of damage to buildings post-disaster. In this paper, we will show our methods and results for how we were able to obtain a better performance than existing models, especially in moderate to significant magnitudes of damage, along with ablation studies to show our methods and results for the importance and impact of different training parameters in deep learning for satellite imagery. We were able to obtain an overall F1 score of 0.868 with our methods. |
| first_indexed | 2024-03-10T17:30:25Z |
| format | Article |
| id | doaj.art-24e80bdedd7a4868aacc0fdf3b1ed581 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-10T17:30:25Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-24e80bdedd7a4868aacc0fdf3b1ed5812023-11-20T10:01:11ZengMDPI AGAlgorithms1999-48932020-08-0113819510.3390/a13080195Deep Learning-Enabled Semantic Inference of Individual Building Damage Magnitude from Satellite ImagesBradley J. Wheeler0Hassan A. Karimi1Geoinformatics Laboratory, School of Computing and Information, University of Pittsburgh, Pittsburgh, PA 15213, USAGeoinformatics Laboratory, School of Computing and Information, University of Pittsburgh, Pittsburgh, PA 15213, USANatural disasters are phenomena that can occur in any part of the world. They can cause massive amounts of destruction and leave entire cities in great need of assistance. The ability to quickly and accurately deliver aid to impacted areas is crucial toward not only saving time and money, but, most importantly, lives. We present a deep learning-based computer vision model to semantically infer the magnitude of damage to individual buildings after natural disasters using pre- and post-disaster satellite images. This model helps alleviate a major bottleneck in disaster management decision support by automating the analysis of the magnitude of damage to buildings post-disaster. In this paper, we will show our methods and results for how we were able to obtain a better performance than existing models, especially in moderate to significant magnitudes of damage, along with ablation studies to show our methods and results for the importance and impact of different training parameters in deep learning for satellite imagery. We were able to obtain an overall F1 score of 0.868 with our methods.https://www.mdpi.com/1999-4893/13/8/195computer visionartificial intelligencedisaster managementremote sensingdamage magnitudesatellite imaging |
| spellingShingle | Bradley J. Wheeler Hassan A. Karimi Deep Learning-Enabled Semantic Inference of Individual Building Damage Magnitude from Satellite Images Algorithms computer vision artificial intelligence disaster management remote sensing damage magnitude satellite imaging |
| title | Deep Learning-Enabled Semantic Inference of Individual Building Damage Magnitude from Satellite Images |
| title_full | Deep Learning-Enabled Semantic Inference of Individual Building Damage Magnitude from Satellite Images |
| title_fullStr | Deep Learning-Enabled Semantic Inference of Individual Building Damage Magnitude from Satellite Images |
| title_full_unstemmed | Deep Learning-Enabled Semantic Inference of Individual Building Damage Magnitude from Satellite Images |
| title_short | Deep Learning-Enabled Semantic Inference of Individual Building Damage Magnitude from Satellite Images |
| title_sort | deep learning enabled semantic inference of individual building damage magnitude from satellite images |
| topic | computer vision artificial intelligence disaster management remote sensing damage magnitude satellite imaging |
| url | https://www.mdpi.com/1999-4893/13/8/195 |
| work_keys_str_mv | AT bradleyjwheeler deeplearningenabledsemanticinferenceofindividualbuildingdamagemagnitudefromsatelliteimages AT hassanakarimi deeplearningenabledsemanticinferenceofindividualbuildingdamagemagnitudefromsatelliteimages |