Traffic Analysis and Smart Traffic Management Using YOLO

Citation

Yap, Chia Hong and Goh, Kah Ong Michael and Law, Check Yee and Sek, Yong Wee (2025) Traffic Analysis and Smart Traffic Management Using YOLO. The Smart Life Revolution. pp. 45-63. ISSN 9781003509196

Full text not available from this repository.

Abstract

In recent years, the increasing number of vehicles has led to various traffic issues, including accidents and congestion, significantly undermining traffic efficiency. Addressing and preventing these problems is crucial. Nonetheless, most existing methods for detecting traffic incidents rely on manual judgement or image feature recognition. These methods often lack promptness and may result in secondary accidents. Therefore, an essential requirement is a method that can effectively detect traffic incidents. This project aims to develop a model capable of identifying the front and back of vehicles, discerning forward and backward movements, and detecting illegal directions. Through 3D detection testing, the accuracy of 3D bounding box rendering reaches 82.21% when applied to images or videos. Evaluating vehicle movement direction yields an average accuracy of 69.47%. Lastly, assessing restricted movement directions achieves accuracies from 71.11% to as high as 88.53%. This traffic incident detection model proves valuable for timely identification and can curtail the occurrence of secondary accidents.

Item Type: Article
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD28-70 Management. Industrial Management > HD30.2 Electronic data processing. Information technology. Including artificial intelligence and knowledge management
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 01 Jul 2025 01:20
Last Modified: 01 Jul 2025 01:20
URII: http://shdl.mmu.edu.my/id/eprint/14197

Downloads

Downloads per month over past year

View ItemEdit (login required)