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

Tiwari, Sushant; Rashidi, Abbas; Markovic, Nikola

i

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

2023-07-01
By Tiwari, Sushant ; Rashidi, Abbas ; Markovic, Nikola

File Language:

English

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:

Automatic Incident Detection Automatic Tracking Automation Computer Vision Ramp Performance Data Processing Operations Deep Learning Image Analysis Image Processing Machine Learning Queue Delay Queue Length Queuing Ramp Metering Ramps
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
Collection(s):

US Transportation Collection
Main Document Checksum:

urn:sha-512:3b04dc6bfe47859c80bcdab5c310a0a9e76a312484e4fcd4354efc1ea9d56bf49bba712b9932697ad79d126976f5f1ed17624e120330671ebead9c9166415bbd
Download URL:

https://rosap.ntl.bts.gov/view/dot/72506/dot_72506_DS1.pdf
File Type:

[PDF - 4.49 MB ]

File Language:

English

ON THIS PAGE

Details

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.