AI Simulating Human Eye will find cracks in bridges

Ural Federal University specialists have developed a neural network capable of detecting cracks in bridges, roads, buildings and other important structures in a matter of seconds.

Building a new AI world: Russia begins another digital breakthrough

But the legislative framework and human resources are not keeping pace with the dynamics of innovation.

For better work when analyzing video data collected from unmanned aerial vehicles (UAVs), artificial intelligence (AI) reproduces the principle of focusing the human gaze. When analyzing, the system will also take into account infrared images, which will enable it to find defects that are invisible during normal shooting. The invention has already confirmed the accuracy of 88.7% on real footage from Russia and China.

Today, the condition of infrastructure facilities is monitored manually. At least three specialists will be involved in the inspection of one large structure.

"The inspection of a large structure requires a lot of time. And not all areas can be reached by a person, so you have to use additional body kits and even attract climbers. In some cases, they try to use drone footage. However, you still have to watch large amounts of video later. Our technology will replace hours—long manual inspections, reduce the risk of accidents and save the budget on infrastructure maintenance," said Zoya Belyaeva, Head of the UrFU Department of Building Structures and Soil Mechanics.

UrFU technology will make it easier for many employees to work, she stressed.