Traffic volume estimation from traffic camera imagery : toward real-time traffic data streams / by James Eckert and Ala'a Al-Habashna. : CS18-001/2022-1E-PDF

"Traffic monitoring in large urban areas remains a challenge for both practical and technical reasons. This paper presents a computer vision-based system to periodically extract vehicle counts from Canadian traffic camera imagery. The process started with research on available traffic camera programs in Canada. Then, a prototype system was developed to collect imagery from three traffic camera jurisdictions through use of their Application Programming Interfaces (APIs). Different classes of vehicles were detected from these images. Object detection was implemented using the open source You Only Look Once, Version 3 object-detection model that was trained on the Common Objects in Context dataset. The processing system pulls static images at high-frequency intervals from the traffic camera APIs and generates real-time counts of the detected vehicles (car, bus, motorcycle, etc.). Finally, different methods of estimating traffic volumes from the counts were implemented and assessed. An analysis of the output data shows that clear traffic patterns and trends can be detected, lending support to an expansion of this system to a full-scale statistical program on a real-time mobility data"--Summary, page 7.

Lien permanent pour cette publication :
publications.gc.ca/pub?id=9.914432&sl=1

• Format MARC XML
• Format MARC HTML

Demander des formats alternatifs