Urban Traffic Management: Detect Vehicles Categories using Modified YOLO Model

Authors

Vandana Machhi, Yuvraj Chauhan, Jenil Gohil, Khushali Pandya, Dhaval Nimavat

Abstract

The “significant rise in congestion on traffic lanes is one of the most significant challenges that slows the growth of a metropolitan metropolis. The reason for this is that there are a growing number of cars on the roadways, which is causing significant delays at junctions where traffic is concentrated. Throughout the years, a variety of strategies and approaches have been developed to find a solution to this issue and to make the systems that manage traffic more dynamic. Static traffic control systems relied on predetermined timings that were assigned to each traffic lane and could not be modified in any way. These timings were used to govern the flow of traffic. In addition, there was not a system for the counting and detection of vehicle with different categories, nor was there a facility for the identification of emergency vehicles while they were moving through traffic. In this research article, we will review different machine learning and deep learning models for the detection of vehicles. We will assess the viability of these models in terms of cost, dependability, accuracy, and efficiency, and we will also add some new features to improve the overall performance of the current detection” system.

Keywords

Multi-categories Vehicle, Traffic Management, Transfer Learning, You Only Look Once (YOLO), Convolutional Neural Network

Urban Traffic Management: Detect Vehicles Categories using Modified YOLO Model. Vandana Machhi, Yuvraj Chauhan, Jenil Gohil, Khushali Pandya, Dhaval Nimavat. 2024. IJIRCT, Volume 10, Issue 2. Pages 1-8. https://www.ijirct.org/viewPaper.php?paperId=2403035