Research Article
Adaptive Traffic Signal Control using Real-Time Video Processing and Vehicle Detection
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357769, author={Kumareshan N and Kaviyabharathi V and Kirubhakar P and Manipradeep S and Nithish P A}, title={Adaptive Traffic Signal Control using Real-Time Video Processing and Vehicle Detection}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part I}, publisher={EAI}, proceedings_a={ICITSM PART I}, year={2025}, month={10}, keywords={adaptive traffic control yolov4-tiny vehicle detection real-time processing multi-agent system smart traffic management}, doi={10.4108/eai.28-4-2025.2357769} }- Kumareshan N
Kaviyabharathi V
Kirubhakar P
Manipradeep S
Nithish P A
Year: 2025
Adaptive Traffic Signal Control using Real-Time Video Processing and Vehicle Detection
ICITSM PART I
EAI
DOI: 10.4108/eai.28-4-2025.2357769
Abstract
Vehicle traffic between cities has grown dramatically as a result of the fast rate of urbanization. As a result, a number of traffic-related issues have surfaced, including gridlock and an overabundance of different kinds of cars. It is crucial to collect road data in order to address traffic issues. Thus, the ultimate aim is to create a traffic control system that uses a convolutional neural network (CNN) and the maxim "you only look once" (YOLO) to find traffic volume and gather vehicle information from the road. This system uses YOLO to identify vehicles first, then combines it with a vehicle-counting technique to determine traffic flow. In order to regulate traffic light signals according to traffic density, adaptive traffic signals that can monitor in real time are therefore required. By capturing pictures of each lane at a junction, proposed solution suggested an adaptive traffic light management system that effectively controls traffic using image processing and image matching techniques.
