Machine Learning with Roadside LiDAR for Efficient Signalized Intersection Operations: Improved Vulnerable Road User (VRU) Detection

Roadside LiDAR devices have significantly improved the detectability of multimodal traffic in real time at intersections. Such high-fidelity observations of traffic and vulnerable road users (VRU) are critical in providing safe and efficient operation of signalized intersections. However, roadside LiDARs have some drawbacks that limit their application in adaptive traffic control such as massive data volume, data complexity, sensor malfunctions, and occlusion. Improved machine learning algorithms along with sensor fusion capabilities are needed to provide robust detection of traffic and other VRUs. In this research initiation project, California State University Long Beach (CSULB) will conduct site selection, sampling, and measurement of the traffic data in different real-world scenarios to assess the prospects for LiDAR to identify VRUs.

• Record URL:
  https://metrans.org/research/machine-learning-with-roadside-lidar-for-efficient-signalized-intersection-operations

Language

• English

Project

• Status: Programmed
• Funding: $39993
• Contract Numbers:

  69A3552348309

  65A0674

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  METRANS Transportation Consortium

  University of Southern California
  Los Angeles, CA  United States 
• Project Managers:

  Hong, Jennifer

  Bruner, Britain

• Principal Investigators:

  Tanvir, Shams

• Start Date: 20250101
• Expected Completion Date: 20260630
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers

Subject/Index Terms

• TRT Terms: Detectors; Laser radar; Machine learning; Signalized intersections; Traffic safety; Vulnerable road users
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Pedestrians and Bicyclists; Safety and Human Factors;

Filing Info

• Accession Number: 01928607
• Record Type: Research project
• Source Agency: Pacific Southwest Region University Transportation Center
• Contract Numbers: 69A3552348309 , 65A0674
• Files: UTC, RIP
• Created Date: Aug 24 2024 10:52AM