Artificial Intelligence for Pavement Condition Assessment From 2D/3D Surface Images [Technical Summary Report]

Details

• Creators:
  Wang, Feng ; Gong, Haitao ; Bai, Yongsheng ; Tesic, Jelena ; Luo, Xiahua
• Corporate Creators:
  Texas State University--San Marcos
• Corporate Contributors:
  Texas Department of Transportation. Research and Technology Implementation Office ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  • Automation
  • Pavements
  • Data collection
  • Data quality
  • Data management
  • Sampling
  • Quality assurance
  • Accuracy
  • Precision
  • Artificial intelligence
  More +
• Resource Type:
  Brief
• Geographical Coverage:
  United States ; Texas
• Edition:
  Project Summary Report
• Corporate Publisher:
  Texas Department of Transportation. Research and Technology Implementation Office
• Abstract:
  The project started with reviewing the literature of available datasets, established AI models and practices in the U.S. and other countries. The research team investigated the acquisition of high-resolution images with American Association of Highway and Transportation Officials (AASHTO) standard MP47 and created a tool for viewing the vendor's data and labeling different distresses on three pavement types (Asphalt Concrete Pavement (ACP), Jointed Concrete Pavement (JCP), and Continuously Reinforced Concrete Pavement (CRCP), respectively). 2D/3D images were selected carefully to include diverse pavement defects to be annotated. For each type, the selected images were labeled with bounding boxes to manually locate and mark the pavement surface distresses. Segmentation masks were provided for a small portion of images for potential applications. A comprehensive image library was established in the AASHTO standard data format, capturing diverse pavement conditions and surface types in Texas.
• Format:
  PDF
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/90512/dot_90512_DS1.pdf
• File Type:
  [PDF - 265.97 KB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; US Transportation Collection
• Main Document Checksum:
  urn:sha-512:3844982390c4c4770a6302b884af7d7ab713f01444fef47c85a260119cd90270ce5423642ba9dcedc33a3c881c8e65f5853dcec92d96a3b1ea17e15ef7f2bf46