Deep Learning with LiDAR Point Cloud Data for Automatic Roadway Health Monitoring

Details

• Creators:
  Trinidad, Rafael ; Sherafat, Ardavan ; Ji, Hao ; Zhang, Yongping ; Cheng, Wen ; Mora, Omar
• Corporate Creators:
  Center for Understanding Future of Travel Behavior and Demand (TBD) National University Transportation Center (UTC) ; California State Polytechnic University, Pomona
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  • Data collection
  • Highways
  • Laser radar
  • Machine learning
  • Structural health monitoring
  • Point clouds
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States ; Southern California
• Edition:
  Final Report, 2024-2025
• Corporate Publisher:
  Center for Understanding Future of Travel Behavior and Demand (TBD) National University Transportation Center (UTC)
• Abstract:
  Maintaining roadway safety requires accurate monitoring of both pavement conditions and traffic sign infrastructure. Traditional methods, such as manual inspection or LiDAR-based systems, are costly, time-consuming, and difficult to scale. This work introduces a cost-effective, image-based framework that leverages dense 3D point cloud data, geometric modeling, and deep learning for automatic roadway health monitoring.
• Format:
  PDF
• Funding:
  69A3552344815 ; 69A3552348320
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/87064/dot_87064_DS1.pdf
• File Type:
  [PDF - 1.57 MB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; University Transportation Centers
• Main Document Checksum:
  urn:sha-512:ea36a4399f94285611ed5da666e2487b1ab0edfa130a52feb987e4470326b85de97ed7542a1da71656f6bf3c1eca019cae2e31f638ced0d6a7e2b0846df4bbe7