Point Cloud Feature Extraction for ADA Ramp Compliance Assessment

Details

• Creators:
  Ghafourian, Amin ; Lee, Andrew ; Gao, Dechen ; Beer, Tyler ; Yen, Kin ; Soltani, Iman
• Corporate Creators:
  University of California, Davis. Dept. of Mechanical and Aerospace Engineering
• Corporate Contributors:
  California Department of Transportation. Division of Research, Innovation and System Information
• Subject/TRT Terms:
  Americans With Disabilities Act Cloud Computing Compliance Data Collection Laser Radar Lidar Mobile Terrestrial Laser Scanning Ramps Surveys
• Publication/ Report Number:
  CA25-4189
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report, 11/2022-1/2025
• Corporate Publisher:
  California. Department of Transportation
• Abstract:
  Automation can play a prominent role in improving efficiency, accuracy, and scalability in infrastructure surveying and assessing construction and compliance standards. This report presents a comprehensive framework for automation of geometric measurements and compliance assessment using point cloud data. The proposed approach integrates deep learning-based detection and segmentation with classical geometric and signal processing techniques to automate surveying tasks. The framework is applied to assess Americans with Disabilities Act (ADA) compliance of curb ramps, demonstrating the utility of point cloud (PC) data for automatic ramp extraction, segmentation, and calculation of geometric measurements. The method leverages a new large, annotated dataset of ramps, facilitating robust deep model training and evaluation. Experimental results, including manual field-based and PC-based measurements of several ramps, validate the accuracy and reliability of the proposed method across various scenarios, highlighting its potential to significantly reduce manual effort and improve consistency in infrastructure assessment. Beyond ADA compliance, the proposed framework establishes a foundation for broader applications in surveying and automated evaluation of construction infrastructure, paving the way for more widespread adoption of point cloud data in engineering automation.
• Format:
  PDF
• Funding:
  65A0749, Task 4189
• Collection(s):
  US Transportation Collection
• Main Document Checksum:
  urn:sha-512:cbb15ec1f1a847914a65e9efd18825ac0467948991982a2d130d3e45ce529bf1944370aad0ce84a6afcc802f0ef4f29a59675e75ed737c5db2cfed3b5cc33da4
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/85001/dot_85001_DS1.pdf
• File Type:
  [PDF - 2.95 MB ]