Enhancing Traffic Insights with Encrypted V2V Communication and Fine-Tuned YOLO

Effective traffic management is crucial for reducing congestion, improving road safety, efficiency, and urban planning, with vehicle data and V2V communication play a core role in such efforts. Most of today's systems and vehicle data collection techniques still apply archaic methods, which interfere with their ability to adapt and learn from real-time traffic changes. This, together with problems in v2v communication such as communication latency, security vulnerabilities, high infrastructure costs, and reliability issues in current V2V systems and onboard applications, hampers overall efficiency. Due to this traffic management systems fail to decide accurate signal timings and analyze accidents, increased accident rates, emergency response delays and inefficient use of infrastructure. This research proposes a dynamic, adaptive solution that incorporates real-time vehicle detection data and secure V2V communication to optimize traffic signal control and improve traffic management. Vehicle data are collected and analyzed by a fine-tuned YOLO model and corresponding algorithms, enhancing the detection accuracy. V2V communication is fortified with advanced security techniques and multi-hopping algorithms to ensure secure data exchanges. The Intelligent Traffic Lights Management and Control System (ITLMCS) adapts traffic signal timings and suggests speed limits to both vehicle drivers and automated vehicles, improving traffic flow and reducing congestion. In addition, the Trust Analysis Stability System (TASS) keeps track of communication packets to identify cyber-attacks, including spoofing or unauthorized manipulation, producing a trust value to ensure secure data exchange among connected vehicles. It ensures secure V2V communication with improved latency, accuracy, and cyberattack resistance.