An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial Imagery
Efficient and robust search and rescue actions are always required when natural or technical disasters occur. Empowered by remote sensing techniques, building damage assessment can be achieved by fusing aerial images of pre- and post-disaster environments through computational models. Existing metho...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/19/7167 |
| _version_ | 1797477018427719680 |
|---|---|
| author | Junchi Bin Ran Zhang Rui Wang Yue Cao Yufeng Zheng Erik Blasch Zheng Liu |
| author_facet | Junchi Bin Ran Zhang Rui Wang Yue Cao Yufeng Zheng Erik Blasch Zheng Liu |
| author_sort | Junchi Bin |
| collection | DOAJ |
| description | Efficient and robust search and rescue actions are always required when natural or technical disasters occur. Empowered by remote sensing techniques, building damage assessment can be achieved by fusing aerial images of pre- and post-disaster environments through computational models. Existing methods pay over-attention to assessment accuracy without considering model efficiency and uncertainty quantification in such a life-critical application. Thus, this article proposes an efficient and uncertain-aware decision support system (EUDSS) that evolves the recent computational models into an efficient decision support system, realizing the uncertainty during building damage assessment (BDA). Specifically, a new efficient and uncertain-aware BDA integrates the recent advances in computational models such as Fourier attention and Monte Carlo Dropout for uncertainty quantification efficiently. Meanwhile, a robust operation (RO) procedure is designed to invite experts for manual reviews if the uncertainty is high due to external factors such as cloud clutter and poor illumination. This procedure can prevent rescue teams from missing damaged houses during operations. The effectiveness of the proposed system is demonstrated on a public dataset from both quantitative and qualitative perspectives. The solution won the first place award in International Overhead Imagery Hackathon. |
| first_indexed | 2024-03-09T21:12:00Z |
| format | Article |
| id | doaj.art-57892e32acd3431d9aaee39b83f6cd4c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:12:00Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-57892e32acd3431d9aaee39b83f6cd4c2023-11-23T21:44:29ZengMDPI AGSensors1424-82202022-09-012219716710.3390/s22197167An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial ImageryJunchi Bin0Ran Zhang1Rui Wang2Yue Cao3Yufeng Zheng4Erik Blasch5Zheng Liu6School of Engineering, Okanagan Campus, University of British Columbia, Kelowna, BC V1V 1V7, CanadaSchool of Engineering, Okanagan Campus, University of British Columbia, Kelowna, BC V1V 1V7, CanadaSchool of Engineering, Okanagan Campus, University of British Columbia, Kelowna, BC V1V 1V7, CanadaSchool of Engineering, Okanagan Campus, University of British Columbia, Kelowna, BC V1V 1V7, CanadaDepartment of Data Science, University of Mississippi Medical Center, Jackson, MS 39216, USAMOVEJ Analytics, Dayton, OH 45324, USASchool of Engineering, Okanagan Campus, University of British Columbia, Kelowna, BC V1V 1V7, CanadaEfficient and robust search and rescue actions are always required when natural or technical disasters occur. Empowered by remote sensing techniques, building damage assessment can be achieved by fusing aerial images of pre- and post-disaster environments through computational models. Existing methods pay over-attention to assessment accuracy without considering model efficiency and uncertainty quantification in such a life-critical application. Thus, this article proposes an efficient and uncertain-aware decision support system (EUDSS) that evolves the recent computational models into an efficient decision support system, realizing the uncertainty during building damage assessment (BDA). Specifically, a new efficient and uncertain-aware BDA integrates the recent advances in computational models such as Fourier attention and Monte Carlo Dropout for uncertainty quantification efficiently. Meanwhile, a robust operation (RO) procedure is designed to invite experts for manual reviews if the uncertainty is high due to external factors such as cloud clutter and poor illumination. This procedure can prevent rescue teams from missing damaged houses during operations. The effectiveness of the proposed system is demonstrated on a public dataset from both quantitative and qualitative perspectives. The solution won the first place award in International Overhead Imagery Hackathon.https://www.mdpi.com/1424-8220/22/19/7167aerial imagerybuilding damage assessmentinformation fusionrobust operationmodel efficiency |
| spellingShingle | Junchi Bin Ran Zhang Rui Wang Yue Cao Yufeng Zheng Erik Blasch Zheng Liu An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial Imagery Sensors aerial imagery building damage assessment information fusion robust operation model efficiency |
| title | An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial Imagery |
| title_full | An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial Imagery |
| title_fullStr | An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial Imagery |
| title_full_unstemmed | An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial Imagery |
| title_short | An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial Imagery |
| title_sort | efficient and uncertainty aware decision support system for disaster response using aerial imagery |
| topic | aerial imagery building damage assessment information fusion robust operation model efficiency |
| url | https://www.mdpi.com/1424-8220/22/19/7167 |
| work_keys_str_mv | AT junchibin anefficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT ranzhang anefficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT ruiwang anefficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT yuecao anefficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT yufengzheng anefficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT erikblasch anefficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT zhengliu anefficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT junchibin efficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT ranzhang efficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT ruiwang efficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT yuecao efficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT yufengzheng efficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT erikblasch efficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery AT zhengliu efficientanduncertaintyawaredecisionsupportsystemfordisasterresponseusingaerialimagery |