It wasn’t long after Hurricane Laura hit the Gulf Coast Thursday that people began flying drones to record the damage and posting videos on social media. Those videos are a precious resource, say researchers at Carnegie Mellon University, who are working on ways to use them for rapid damage assessment.
By using artificial intelligence, the researchers are developing a system that can automatically identify buildings and make an initial determination of whether they are damaged and how serious that damage might be.
“Current damage assessments are mostly based on individuals detecting and documenting damage to a building,” said Junwei Liang, a Ph.D. student in CMU’s Language Technologies Institute (LTI). “That can be slow, expensive and labor-intensive work.”
Satellite imagery doesn’t provide enough detail and shows damage from only a single viewpoint — vertical. Drones, however, can gather close-up information from a number of angles and viewpoints. It’s possible, of course, for first responders to fly drones for damage assessment, but drones are now widely available among residents and routinely flown after natural disasters.
“The number of drone videos available on social media soon after a disaster means they can be a valuable resource for doing timely damage assessments,” Liang said.
Xiaoyu Zhu, a master’s student in AI and Innovation in the LTI, said the initial system can overlay masks on parts of the buildings in the video that appear damaged and determine if the damage is slight or serious, or if the building has been destroyed.
The team will present their findings at the Winter Conference on Applications of Computer Vision (WACV 2021), which will be held virtually next year.
The researchers, led by Alexander Hauptmann, an LTI research professor, downloaded drone videos of hurricane and tornado damage in Florida, Missouri, Illinois, Texas, Alabama and North Carolina. They then annotated the videos to identify building damage and assess the severity of the damage.
The resulting dataset — the first that used drone videos to assess building damage from natural disasters — was used to train the AI system, called MSNet, to recognize building damage. The dataset is available for use by other research groups via Github.
The videos don’t include GPS coordinates — yet — but the researchers are working on a geolocation scheme that would enable users to quickly identify where the damaged buildings are, Liang said. This would require training the system using images from Google Streetview. MSNet could then match the location cues learned from Streetview to features in the video.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Natural disaster damage assessment
- Vexcel to Provide Catastrophe Analytics on Properties After Major Weather Events and Natural Disasters
End users get quick insights to property damage with the world’s largest aerial imagery program CENTENNIAL, Colo., May 23, 2022 /PRNewswire/ -- Vexcel Data Program announced today a new product to ...
- Ontario, Quebec storm leaves at least nine dead, hundreds of thousands without power
The storm, known as a ‘derecho,’ triggered several emergency alerts. It was the first time Environment Canada used its broadcast-interrupting weather alert system for a thunderstorm ...
- Displaced Gaylord families find shelter in church after tornado
The American Red Cross set up the emergency shelter Friday after the tornado swept through Gaylord. A 211 line was activated Saturday, May 21 to connect people with available resources.
- Flood cleanup continues two weeks later
Damage assessment following flash flooding in the area a couple weeks ago is still underway. On May 6, about 4.5 inches of rain fell in south Huntington and the surrounding area. Since then, residents ...
- What's your home's 'wildfire threat score?' A new tool lets you find out
For the seventh consecutive year, insured losses from wildfires in 2021 eclipsed $2 billion nationwide, and that total is expected only to increase, according to a new study. Researchers are ...
Go deeper with Google Headlines on:
Natural disaster damage assessment
Go deeper with Bing News on:
Rapid damage assessment
- Guidewire’s Insurtech Vanguards Program Reaches Growth Milestone, Connecting 25 New P&C Industry Insurtechs with Insurers
Guidewire announced that its Insurtech Vanguards program has reached a growth milestone with 25 members offering digital solutions to insurers.
- Vexcel to Provide Catastrophe Analytics on Properties After Major Weather Events and Natural Disasters
Damage Assessment is part of Vexcel's Elements product line which uses machine learning (ML) to deliver rapid property insights. Providing this level of detail goes hand in hand with Vexcel's ...
- Damage To Railway Lines, Assets In Assam Being Assessed With Drones, Satellite Data
Specialists from North Eastern Space Applications Centre (NESAC), a subsidiary of the Indian Space Research Organisation ...
- Damage to railways, other assets in Assam assessed with drones, satellite data
Guwahati: Specialists from North Eastern Space Applications Centre (NESAC), a subsidiary of the Indian Space Research Organisation (ISRO), are using drones and satellite data for conducting rapid ...
- A better Lake Street? A daring hope for riot-torn corridor
Though state aid has been slow coming, Minneapolis' support for the riot-damaged cultural corridor keeps hope alive for a better future.