AI-Enabled Vision System for Intersection Analytics

Adu-Gyamfi, Yaw; Tanner, Muturi

i

AI-Enabled Vision System for Intersection Analytics

2025-09-01
By Adu-Gyamfi, Yaw ; Tanner, Muturi

File Language:

English

Details

Creators:

Adu-Gyamfi, Yaw ; Tanner, Muturi
Corporate Creators:

University of Missouri--Columbia. Department of Civil and Environmental Engineering
Corporate Contributors:

Missouri. Department of Transportation. Construction and Materials Division ; United States. Department of Transportation. Federal Highway Administration
Subject/TRT Terms:

Artificial Intelligence Automatic Data Collection Systems Closed Circuit Television Computer Vision Deep Learning Infrastructure Intersections Machine Learning Metrics (Quantitative Assessment) Performance Signal Phase And Timing (SPaT) Traffic Data Traffic Signal Intervals Traffic Signal Timing Turning Movement Counts Turning Traffic
Publication/ Report Number:

cmr 25-012
Resource Type:

Tech Report
Geographical Coverage:

United States
Edition:

Final Report (September 2024-September 2025)
Corporate Publisher:

Missouri. Department of Transportation. Construction and Materials Division
Abstract:

This project developed and demonstrated an AI-enabled vision system for intersection analytics capable of automatically generating Turning Movement Counts (TMCs) and integrating them with Signal Phase and Timing (SPaT) data to evaluate traffic signal performance. Using existing Missouri Department of Transportation (MoDOT) CCTV (Closed Circuit Television) infrastructure, the system eliminated the need for manually placed detection zones and significantly reduced the labor traditionally required for data collection.
Format:

PDF
Funding:

TR202506
Collection(s):

US Transportation Collection
Main Document Checksum:

urn:sha-512:da061584ae3da639346b8969cda4230a5e6de0e34192320332bd9ce39e08fc5a261e1574188ac66d74ba7590d6a88d5e09143a448cb9418a6294b68054edfdc0
Download URL:

https://rosap.ntl.bts.gov/view/dot/86975/dot_86975_DS1.pdf
File Type:

[PDF - 2.22 MB ]

File Language:

English

ON THIS PAGE

Details Related Documents

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.