Detecting and Counting different Vehicles in the real time Traffic Signal using deep learning

Kumar, Stephen Angelo (2023) Detecting and Counting different Vehicles in the real time Traffic Signal using deep learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (5MB) | Preview
Preview	PDF (Configuration manual) Download (17MB) | Preview

Abstract

Traffic congestion is a pressing global issue. This research proposes an ensemble approach to improve traffic management using traffic cameras, real-time video analysis, time series forecasting, and rules derived from traffic patterns. The project develops an algorithm to control green light duration and ensure efficient traffic f low. The ensemble approach optimizes green time using deep learning techniques for object detection and time series forecasting to predict traffic volumes. For real-time object detection, YOLOv4 achieved the highest mean Average Precision at 42.44%. The ensemble approach integrates video analysis and time series projections to dynamically manage traffic. This study demonstrates the potential of combining computer vision and predictive analytics to optimize traffic signals and reduce congestion.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Lugones, Diego UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TA Engineering (General). Civil engineering (General) T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	09 Oct 2024 17:27
Last Modified:	09 Oct 2024 17:27
URI:	https://norma.ncirl.ie/id/eprint/7085

Actions (login required)

View Item