Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Traffic congestion is a major issue in cities, leading to longer travel times, unnecessary fuel consumption, and higher pollution levels. Traditional traffic management systems fail to make adjustments in response to the real-time nature of road traffic, resulting in poor traffic flow and long waiting times. They depend on fixed-timer signals. In this paper, an adaptive traffic control system using YOLOv8-based object recognition and real-time picture processing for optimized traffic management is proposed. The proposed system utilizes surveillance cameras to capture live feed of the traffic flow and employs advanced deep-learning techniques for processing
the captured data. To accurately recognize and count vehicles in real time, YOLOv8, a state-of-the-art object detection model, is employed. It automatically adapts the timing of traffic lights, optimizing traffic flow
responsive to the situation to make it more effective. To enhance computational efficiency and reduce decision-making latency, edge computing techniques are also applied. When the adaptive system was compared to conventional fixed-timer systems, simulations as well as actual testing showed that total traffic efficiency
increased by approximately 23 percentage due to significant reduction in time spent with signals on red and vehicles on approach to the signals waiting to cross. From the results, it can be inferred that the proposed approach outperforms both conventional traffic management systems, with a significant computational efficiency, as well as the recent adaptive traffic management systems by applying it to the smart city infrastructures.
Keywords:
Traffic management, Intelligent transportation system, YOLOv8, Deep learning, Real-time processing, Edge computing, Adaptive traffic control
Cite Article:
"Real-Time Traffic Optimization Using Reinforcement and Deep Leaning", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 5, page no.c468-c475, May-2025, Available :http://www.ijrti.org/papers/IJRTI2505255.pdf
Downloads:
000439
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator