Data Fusion to Improve the Accuracy of Multi-Modal Traffic Counts
This study investigated the use of data fusion of two different traffic counting and classification methods. While sensor level fusion using thermal and optical images was investigated, it was not found useful by our approaches. The decision-level fusion method for pneumatic tube and infrared video is presented. The method was validated at three different locations in South Carolina. Errors in vehicle counts and vehicle classification were calculated using manual data collection from recorded videos as the baseline. In all locations, the results of data fusion are more accurate in both vehicle counts and vehicle classification when compared to either of the methods alone.
Language
- English
Project
- Status: Completed
- 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 20590Center for Connected Multimodal Mobility
Clemson University
Clemson, SC United States 29634University of South Carolina, Columbia
502 Byrnes Building
Columbia, SC United States 29208 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 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