Drexel researchers create AI system to spot cracks in infrastructure

An article from
site logo

Dive Brief

The team wants to use the same technology leveraged in facial recognition and drug development to flag warning signs in aging public works.

Published Feb. 7, 2024

A robot sits on a bed of concrete. It's sleek and off-white, with a visual lens on the front.

A research team at Drexel University created a system that uses a robot scanner, computer vision and machine learning programs to identify, model and monitor cracks in concrete.

Courtesy of Drexel University

This audio is auto-generated. Please let us know if you have feedback.

Dive Brief:

  • A team of researchers from Drexel University in Philadelphia created an AI-based system to inspect roads and bridges that can flag and monitor cracks before they develop into bigger issues.
  • The research team wants to augment visual inspection technologies with a new machine learning approach that combines computer vision, which allows machines to recognize and understand objects, with a deep-learning algorithm to pinpoint problem areas, according to a Drexel press release. Combined with autonomous robots, researchers said the approach could help efficiently inspect and identify problem areas in infrastructure.
  • Once an issue is spotted, the process then conducts a series of laser scans of the region to create a digital twin of the structure that humans can use to assess and monitor the damage, including tracking crack growth over time, according to the release.

Dive Insight:

Drexel’s method, which researchers published in the journal Automation in Construction, uses a high-resolution stereo-depth camera to record images of a structure before feeding them into a deep-learning program called a convolutional neural network. 

These systems can spot the finest of patterns and discrepancies in massive volumes of data, researchers said, with applications previously used in drug development, deepfake detection and facial recognition technology.

Arvin Ebrahimkhanlou, an assistant professor at Drexel’s College of Engineering and a member of the research team, told Construction Dive that the team has been in contact with the National Academy of Building Inspection Engineers throughout the design process. 

“The neural network has been trained on a dataset of sample cracks, and it can identify crack-like patterns in the images that the robotic system collects from the surface of a concrete structure,” Ebrahimkhanlou said in the release. “We call regions containing such patterns, regions of interest.” 

While the technology has been tested in a lab setting, Ebrahimkhanlou told Construction Dive the team needs a partner to test it in the field, which will take at least a few years.

In its latest assessment of America’s infrastructure, the American Society of Civil Engineers found a $786 billion backlog on road and bridge repairs alone.

Note: This article have been indexed to our site. We do not claim legitimacy, ownership or copyright of any of the content above. To see the article at original source Click Here

Related Posts
Bitenc ruled the former Mobitel center on Vilharjeva thumbnail

Bitenc ruled the former Mobitel center on Vilharjeva

Čas branja: 2 min 05.01.2022  14:00 Telekom je obdržal le manjši del prostorov v kleti stavbe, kjer ima serverje Foto: Aleš Beno Celotni članek je na voljo le naročnikom. Nepremičnine so vroča tema! Omogočite si dostop do vseh vsebin! Na Financah redno spremljamo dogajanje na nepremičninskem trgu, objavljamo analize in nasvete. 3 MESECI FINANC ŽE…
Read More
Again, FG Seeks $400m W’Bank Loan to Fund 15m Households thumbnail

Again, FG Seeks $400m W’Bank Loan to Fund 15m Households

The Federal Government has applied for a fresh loan of $400m for the conditional cash transfer to 15 million households as one of the measures to cushion the effects of the removal of petrol subsidy. The $400m World Bank loan will bring to $1.2bn the amount that the Federal Government is borrowing from the World
Read More
Vsi »čeji« Facebooka thumbnail

Vsi »čeji« Facebooka

Čas branja: 2 min 08.02.2022  12:00  Dopolnjeno: 08.02.2022 12:17 Če bodo Irci odločili proti Meti, če se ne bodo več mogli zanašati na standardne pogodbene klavzule, če nove zakonodajne podlage za prenos podatkov ne bo, če … No, potem Meta morda zapušča EU. Celotni članek je na voljo le naročnikom. 3 MESECI FINANC ŽE ZA…
Read More
Index Of News
Total
0
Share