UH Engineers Develop Radar and AI to Detect Hidden Cold-Steel Damage

New technology can identify potential issues in concealed construction materials without tearing down walls.

Published on Mar. 6, 2026

Got story updates? Submit your updates here. ›

Researchers at the University of Houston have created a new method using ground-penetrating radar and artificial intelligence to automatically detect damage in concealed cold-formed steel construction materials like studs and joists, without having to remove walls. This allows for faster, more efficient, and less disruptive building inspections and assessments.

Why it matters

As the use of cold-formed steel in construction has increased over the past decade, traditional inspection methods that require partially or fully removing walls have become inefficient and costly. This new radar and AI-based approach provides a faster, more reliable, and less disruptive way to identify potential issues in these concealed structural elements.

The details

The new framework combines ground-penetrating radar scans with an AI tool called InternImage that can analyze the radar images to detect the presence of steel, identify any damage like buckling, and assess the severity. This allows inspectors to only verify the flagged problem areas instead of opening up entire walls. The researchers also developed a specialized dataset of radar images of cold-formed steel behind common wall materials to help train the AI model.

  • The research was published in the Journal of Computing in Civil Engineering in March 2026.

The players

Vedhus Hoskere

Kaspar J. Willam Assistant Professor of Civil and Environmental Engineering at the University of Houston, who developed the new radar and AI-based inspection method.

Muhammad Taseer Ali

First author of the research and a graduate student in Hoskere's lab, with 10 years of prior industry experience in cold-formed steel structure design.

Got photos? Submit your photos here. ›

What they’re saying

“To address these limitations, we introduce a new framework that combines a quick radar scan with AI that reads the radar images and points to where the steel is, where damage is likely and the severity and type of damage.”

— Vedhus Hoskere, Kaspar J. Willam Assistant Professor of Civil and Environmental Engineering (Journal of Computing in Civil Engineering)

“The radar sends pulses into the wall and listens for echoes from what's behind it. Hidden steel creates a recognizable pattern in the radar scan image. If the steel is damaged (for example, buckled), it can create a small gap/void that changes the echo pattern in a consistent way.”

— Vedhus Hoskere, Kaspar J. Willam Assistant Professor of Civil and Environmental Engineering (Journal of Computing in Civil Engineering)

“These findings highlight the potential of our framework to advance the concealed cold-formed steel structural inspection methods by providing a rapid, reliable and scalable approach for damage detection, ultimately improving building maintenance and rehabilitation.”

— Muhammad Taseer Ali, Graduate Student (Journal of Computing in Civil Engineering)

What’s next

The researchers plan to further refine and test their radar and AI-based inspection system to improve its accuracy and reliability for real-world applications in building maintenance and post-disaster assessments.

The takeaway

This new technology provides a faster, less disruptive, and more scalable way to inspect concealed cold-formed steel construction materials, which make up a significant portion of nonresidential buildings. By combining radar scans with AI analysis, it allows inspectors to quickly identify potential issues without having to open up entire walls.