Data Fusion to Improve the Accuracy of Multi-Modal Traffic Counts

Description: Current traffic counting systems often only measure one transportation mode accurately. In this project, the research team will improve the reliability and accuracy of video-based traffic counting technology by augmenting the video data with information extracted from other sensing technology. Additional data can originate from tube counters, magnetic loops, radar, vibration, and laser measurements. The project will use the raw data from the augmented sensors (with transient tube pressure signals) to count and classify vehicle types (FHWA 13 types, bicycles, and pedestrian traffic). Intellectual Merit: This project will evaluate the use of combined raw data from the tube-based vehicle counting/classification method and an integrated artificial neural network (ANN) to classify vehicle types with better accuracy than existing methods using data from one type of sensor. Broader Impacts: Improved data on the multi-modal movement of people and freight will provide transportation planners with better quantitative information on use of the existing system. Technology Transfer Plan: This research will be generating an implementation-ready hybrid traffic data collection tool for DOTs.

Language

• English

Project

• Status: Active
• Funding: $108524
• Contract Numbers:

  69A3551747117

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590

  Center for Connected Multimodal Mobility

  Clemson University
  Clemson, SC  United States  29634

  University of South Carolina, Columbia

  502 Byrnes Building
  Columbia, SC  United States  29208

  Benedict College

  1600 Harden Street
  Columbia, South Carolina  United States  29204
• Managing Organizations:

  University of South Carolina, Columbia

  502 Byrnes Building
  Columbia, SC  United States  29208
• Project Managers:

  Mullen, Robert

• Performing Organizations:

  University of South Carolina, Columbia

  502 Byrnes Building
  Columbia, SC  United States  29208

  Benedict College

  1600 Harden Street
  Columbia, South Carolina  United States  29204
• Principal Investigators:

  Mullen, Robert

  Comert, Gurcan

  Huynh, Nathan

• Start Date: 20181201
• Expected Completion Date: 20220531
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers

Subject/Index Terms

• TRT Terms: Data analysis; Planning; Traffic; Video imaging detectors
• Subject Areas: Data and Information Technology; Planning and Forecasting; Transportation (General);

Filing Info

• Accession Number: 01690758
• Record Type: Research project
• Source Agency: Center for Connected Multimodal Mobility
• Contract Numbers: 69A3551747117
• Files: UTC, RIP
• Created Date: Jan 11 2019 4:20PM