Texas State University researchers are paving the way for smarter highway maintenance across Texas’ 703,000 lane miles of highways. With continued Texas Department of Transportation (TxDOT) funding, a cross-disciplinary team led by Feng Wang, Ph.D., professor in the Ingram School of Engineering, and Jelena Tešić, Ph.D., associate professor of computer science, is developing an artificial intelligence (AI) system to detect road damage more accurately.
The project, "Artificial Intelligence for Pavement Condition Assessment from 2D/3D Surface Images," is now in its second phase, closer to statewide deployment with faster, more precise pixel-level detection of pavement damage than manual inspections.
Since launching in 2019, TXST’s civil engineering program has built technology into research infrastructure. Ingram School of Engineering investments in a state-of-the-art automated 2D/3D pavement laser scanner, a TxDOT-donated mobile research van, and support from the CREATE University Transportation Center and an earlier National Science Foundation project also helped prepare data for the TxDOT project.
“The combination of academic focus, equipment investment, and agency partnership helped lay the foundation for the research,” said Wang.
The cross-disciplinary research team also includes:
- Yongsheng Bai, Ph.D., a lecturer at the Ingram School of Engineering
- Xiaohua Luo, Ph.D., an assistant professor of instruction at the Ingram School of Engineering
- Haitao Gong, Ph.D., a former postdoctoral scholar at the Ingram School of Engineering
Under faculty guidance, students from both civil engineering and computer science use specialized computer vision tools to refine pavement defect detection and improve accuracy.
Addressing the challenge of Texas roads
Texas roads take a beating from extreme weather and heavy traffic, with more than 428,000 vehicle interactions per year accelerating pavement deterioration. Current data analysis still relies on manual review that slows the process and leaves room for errors. Wang and Tešić developed an AI-based computer vision framework that combines regular 2D intensity images with 3D range images for more accurate detection.
"From a civil engineering perspective, this project leverages AI to automate pavement condition assessment using massive volumes of vendor-collected imagery data, thereby reducing reliance on traditional human inspection, which is often subjective and costly," Wang said.
By pairing 2D photos with 3D depth maps, the system distinguishes real damage from stains, trace cracks, and prioritizes severe hazards like crumbling concrete over minor surface cracks.
How the technology works in practice
Built for real-world use, the system analyzes 2D and 3D data from the highway and generates prioritized repair reports for precise and objective observations to manage road maintenance.
For Texas drivers, this technology means safer roads, smoother commutes, and fewer pothole-related car repairs. For taxpayers, earlier detection can prevent road failures, save millions in maintenance dollars, and support more consistent repairs statewide.
"This project highlights Texas State University’s emergence as a premier center for applied AI and smart infrastructure," Tešić said. "Spearheaded by DataLab @ TXST and the Center for Analytics and Data Science, this research proves how breaking down academic silos between computer science and civil engineering yields solutions that neither discipline could achieve alone."
The data-centric AI and multimodal vision methods behind this project build on Tešić’s earlier research for the Department of Defense that developed techniques to identify and locate objects in satellite imagery.
Next, the team plans to improve detection of hairline cracks, automatically score damage severity for maintenance scheduling, and adapt the technology for different climates and road surfaces across Texas.