Automating LiDAR Data to Develop and Manage Active Transportation Asset Inventories

This research explores the capabilities of both mobile lidar data and aerial photogrammetric data and develops automated algorithms and efficient workflows to extract pedestrian crosswalks, bike lanes, and medians with important attributes such that they can be used in asset management, transportation safety, and maintenance applications. Specifically, the primary objectives of this research are to: (1) Investigate state-of-the-art machine learning and object detection algorithms for extraction of transportation assets from mobile lidar and photogrammetric data. (2) Develop procedures for extracting pedestrian crosswalks, bike lanes, and medians from Oregon DOT’s mobile lidar data. (3) Produce a geographic information system (GIS) geodatabase for several pilot corridors identifying the locations of bike lanes, crosswalks, and medians to support decision making and integrate data analysis results into Oregon DOT’s overall workflows. These corridors will be selected from urban and rural regions with varying levels of complexity. (4) Evaluate benefits (e.g., time or cost savings, inventory completeness, and improved accuracy) associated with the developed approaches compared with current processes.

Language

• English

Project

• Status: Active
• Funding: $250000
• Contract Numbers:

  SPR 850

• Sponsor Organizations:

  Federal Highway Administration

  1200 New Jersey Avenue, SE
  Washington, DC  United States  20590
• Managing Organizations:

  Oregon Department of Transportation

  555 13th Street NE
  Salem, OR  United States  97301
• Project Managers:

  Roll, Josh

• Performing Organizations:

  Oregon State University, Corvallis

  101 Kearney Hall
  Corvallis, OR  United States  97331
• Principal Investigators:

  Olsen, M. J.

• Start Date: 20211015
• Expected Completion Date: 20240831
• Actual Completion Date: 0
• USDOT Program: Transportation, Planning, Research, and Development

Subject/Index Terms

• TRT Terms: Bicycle lanes; Crosswalks; Data collection; Laser radar; Medians; Photogrammetry
• Subject Areas: Data and Information Technology; Highways; Pedestrians and Bicyclists;

Filing Info

• Accession Number: 01829814
• Record Type: Research project
• Source Agency: Oregon Department of Transportation
• Contract Numbers: SPR 850
• Files: RIP, USDOT, STATEDOT
• Created Date: Dec 10 2021 1:29PM