Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Real-time multiple vehicle counter using background subtraction for traffic monitoring system

Rektorat UDINUS 2019 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2019
Goals
Record
4604ef35-82cc-4a16-9a9f-ad4f60032671
Published
2026-10-30

Universitas Dian Nuswantoro conducted research to build a traffic counter system for the city of Semarang, Indonesia. The activity involved researchers from UDINUS and focused on calculating vehicle volume through video processing as part of an intelligent transportation system. The video was obtained from a CCTV camera belonging to the Semarang city transportation office and could be accessed in real time through a URL link.

During the early stage of system construction, CCTV video from the Tugu Muda area was used. The source describes Tugu Muda as one of the most densely packed streets in Semarang. The area has a complicated form because an intersection connects five main streets. The video processing procedure used background subtraction, binary thresholding, morphology, object detection using contours, and object tracking to calculate vehicle volume. The system generated vehicle-volume reports that could be accessed directly in real time through a web-based application built with Python programming languages and OpenCV editors.

For accuracy testing, manual calculations were compared with system calculations using several video samples taken at different times, namely morning, day, and afternoon. The activity therefore addresses urban transportation monitoring through a system designed to calculate vehicle volume at a dense and complex intersection. It also relates to the stated goal concerning sustainable cities and communities through research on traffic monitoring in an urban setting. The source does not provide the numerical accuracy results of the comparison.

Reference https://www.scopus.com/pages/publications/85074914572?origin=resultslist