Intelligent Queue Length Estimation on Ramps Using Computer Vision and Machine Learning Algorithms

Details

• Creators:
  Tiwari, Sushant ; Rashidi, Abbas ; Markovic, Nikola
• Corporate Creators:
  University of Utah. Department of Civil and Environmental Engineering
• Corporate Contributors:
  Utah Department of Transportation ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  • Ramp metering
  • Ramps
  • Queuing
  • Automation
  • Automatic incident detection
  • Automatic tracking
  • Machine learning
  • Data processing operations
  • Image analysis
  • Computer vision
  More +
• Publication/ Report Number:
  UT-23.16
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  August 2022 to March 2023
• Corporate Publisher:
  Utah Department of Transportation
• Abstract:
  Traffic sensors are utilized to capture real-time traffic parameters. Many Departments of Transportation in the United States use inductance loops. Induction loops often fail to give accurate results during highly congested periods, which is the most crucial time for ramp metering operations. Image processing and computer vision may provide an alternative with better accuracy. This research employs video captured by existing traffic cameras to measure ramp performance using object detection and tracking in combination with queuing theory.
• Format:
  PDF
• Funding:
  23-8344
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/72506/dot_72506_DS1.pdf
• File Type:
  [PDF - 4.49 MB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; US Transportation Collection
• Main Document Checksum:
  urn:sha-512:3b04dc6bfe47859c80bcdab5c310a0a9e76a312484e4fcd4354efc1ea9d56bf49bba712b9932697ad79d126976f5f1ed17624e120330671ebead9c9166415bbd