University of Houston researchers developed an AI and radar-based method to detect hidden damage in cold-formed steel used in building structures.
Key Details
- 1System combines ground-penetrating radar (GPR) with AI to detect damage in concealed steel studs and joists.
- 2Cold-formed steel is used in 30–35% of nonresidential U.S. buildings.
- 3Traditional inspection is labor-intensive, requiring extensive wall removal.
- 4The AI model, InternImage, interprets radar images to locate and classify damage.
- 5A specialized radar image dataset and a training method (GPR-CutMix) improve detection robustness under real-world conditions.
- 6System enables targeted inspections, reducing costs and disruption for building maintenance and disaster assessment.
Why It Matters
The research presents a scalable, efficient non-invasive approach for assessing steel structures, with broader implications for AI-powered diagnostic imaging. These cross-disciplinary advancements can inform techniques and technologies used in radiological imaging AI.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.