In the aftermath of a disaster, engineers must quickly document damage to structures such as buildings, bridges and pipelines before crucial data are destroyed. Researchers are now harnessing “deep learning” algorithms and computer vision technology to dramatically reduce the time it takes to assess the damage to buildings that is captured photographically after floods, tornadoes and earthquakes.

A photo from a 2016 earthquake in Taiwan is identified using a new automated system that outlines damage within green boxes for easy reference. Image credit: Purdue University/Alana Wilbee.“These teams of engineers take a lot of photos, perhaps 10,000 images per day, and these data are critical to learn how the disaster affected structures,” says Shirley Dyke, Purdue University professor of mechanical and civil engineering. “Every image has to be analyzed by people, and it takes a tremendous amount of time for them to go through each image and put a description on it so that others can use it.”

To speed that process, Dyke and Purdue colleagues have developed an automated system using advanced computer vision algorithms, which they say is the first-ever implementation of deep learning for these types of images. The researchers have to train the algorithms to recognize scenes and locate objects in the images.

To test the system, the team used a large set of data containing approximately 8,000 images, with labels on photographs showing building components that were either collapsed or not collapsed and areas affected by spalling, where concrete chips off structural elements due to large tensile deformations. The technology was able to automatically classify images based on whether spalling was present or not and also to pinpoint specifically where it was located within the image. The photos show damage to specific parts of buildings outlined within green boxes for easy reference.

The researchers have gathered approximately 90,000 digital images from recent earthquakes in Nepal, Chile, Taiwan and Turkey to continue training the algorithms and hone the technology for future use.