Corridor-Wide Surveillance Using Unmanned Aircraft Systems [Policy Brief]

Details

• Creators:
  Zhang, Yu ; Kourtellis, Achilleas ; Post, Joseph ; Tang, Hualong ; Yelchuri, Keerthana ; Porter, Brian
• Corporate Creators:
  University of South Florida. National Institute for Congestion Reduction
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  • Unmanned aircraft systems
  • Drones
  • Traffic
  • Transportation
  • Incident management
  • Applications
  • Experiments
  • Machine learning
  • Traffic data
  • Literature reviews
  More +
• Resource Type:
  Brief
• Geographical Coverage:
  United States
• Edition:
  Policy Brief
• Corporate Publisher:
  University of South Florida. National Institute for Congestion Reduction
• Abstract:
  The main objective was to provide the outcome in traffic engineering terms that can be used by the TMC, the team needed to translate the traffic congestion recorded into Level of Service (LOS), and traffic density, or occupancy. The team enhanced the algorithm developed in Phase I by following a specific framework and pieces of algorithm to perform different tasks as described here:1)Training and testing of You Only Look Once (YOLO) model for object detection, which included training YOLO v4 on videos collected via the UAS in the Tampa Bay area. The model was trained on detecting vehicles of varied sizes using both the Red-Green-Blue (RGB) video and the infrared (thermal) video. The model was then tested on untrained video to establish accuracy and was tuned to detect moving vehicles in the videos.2)The algorithm was then expanded to extract traffic features from the video to establish parameters for traffic monitoring. Vehicle speed including median speed, max speed, and standard deviation of speed were calculated. Traffic density was then calculated based on the road segment available in the video.
• Format:
  PDF
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/89336/dot_89336_DS1.pdf
• File Type:
  [PDF - 267.88 KB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; University Transportation Centers
• Main Document Checksum:
  urn:sha-512:c14d955543ef096e4f4834b4fe55052ed25584b4e4c0fc717b7e4d8a55074edea5ee4822bc57a9d949d4c43da563cc04cadb19ab9526fffedc60222a1365ecfb