Benchmarking Computer Vision-Based Approaches To Derive Engineering-Oriented Condition From Existing UDOT Assets Data

Details

• Creators:
  Pandey, Shailaja Ratna ; Esteghamati, Mohsen Zaker
• Corporate Creators:
  Utah State University. Department of Civil and Environmental Engineering
• Corporate Contributors:
  Utah. Department of Transportation. Research and Innovation Division ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  Algorithms Assessments Assets Benchmarks Cameras Computer Vision Data Analysis Delamination Evaluation MUTCD Object Detection Optical Devices Performance Traffic Sign Condition Assessment Traffic Signs Transformers Vision Transformers YOLO11

  More +
• Publication/ Report Number:
  UT- 26.03
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States ; Utah
• Edition:
  Final Report: July 2024 to Dec 2025
• Corporate Publisher:
  Utah Department of Transportation
• Abstract:
  Condition assessment of how transportation infrastructure supports safe and reliable road and highway operation. Departments of Transportation across the country rely heavily on manual inspections, which are time-consuming and costly. This study evaluated whether modern computer vision (CV) methods can support traffic sign condition assessment along Utah highways. High-resolution roadway images collected using a camera-mounted vehicle were curated and annotated for three sign types (regulatory, warning, and guide) and four defect conditions (fading, delamination, missing letters/symbols, and broken signs) based on the Manual on Uniform Traffic Control Devices (MUTCD) standards. This study compared two different CV algorithms of YOLO11 and RT-DETR for traffic-sign detection and defect classification. Overall, the CV models showed promising performance for defect cases where an adequate number of training data existed. For example, for fading, YOLO11 and RT-DETR achieved 75% F1 on the validation. Binary classification of delamination (i.e., delamination versus no delamination) yielded similar performance for both models (68% F1). In contrast, the models showed poor performance to identify missing letters/symbols due to texture overlap with delamination and a limited number of annotated sign images with such defects. The results suggested that data quality and label definition had a greater impact on model performance than the choice of algorithms for the studied models.
• Format:
  PDF
• Funding:
  25-8073
• Collection(s):
  Federal Highway Administration
• Main Document Checksum:
  urn:sha-512:24d6ce16470239891e9577d1e9be9e64767c540cc0ca30acc65b9b4a148c85ae9243fd7e3543c230f48bb9124ef6990b1e20e2ede72c14ef4ed88d4759bbe8f2
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/89723/dot_89723_DS1.pdf
• File Type:
  [PDF - 3.64 MB ]