• Mrs. Swati Vishwakarma
• Mr. Rajneesh Pachouri
• Mr. Anurag Jain
• Mrs. Monali Sahoo
• Ms. Shruti Jain

These days, road congestion is a big issue. Urban cities are the ones most impacted by it, even if it seems to be everywhere. Furthermore, due to its constantly growing nature, real-time knowledge of the road traffic density is essential for improved signal control and efficient traffic management. Traffic congestion can be caused by a variety of factors, including excessive red light waits, unregulated demand, and insufficient capacity. Unrestrained demand and inadequate capacity are somewhat related, although the corresponding light's delay is hardcoded and independent of traffic. Thus, in order to better handle this growing demand, traffic control needs to be optimized and simulated. One of the major issues in metropolitan areas is traffic congestion, which must be resolved to enhance traffic management and operation. The current traffic system is timer-based and functions regardless of traffic volume or the presence of emergency vehicles such as fire engines and ambulances. It seems that vehicle flow detection is a crucial component of the traffic control and operation systems used in the modern world. In order to enhance traffic flow and expedite emergency response times, this design suggests a revolutionary smart traffic system that makes use of real-time Average Vehicle Area and Emergency vehicle recognition. This system uses a pre-trained convolutional neural network model called YOLOv4 and MobileNet V2 to precisely determine the average vehicle area, the number of cars on the road, and the identity of emergency vehicles in real time. With the use of this data, the system may redirect traffic and dynamically modify traffic signals to reduce congestion and provide emergency vehicles priority access. This system appears to be a promising option for contemporary traffic management and emergency services, as experimental findings demonstrate considerable reductions in average travel times and emergency response times.

Image Processing, YOLOv4, MobileNet V2, Convolutional neural network, Emergency Vehicle Detection, Average Vehicle Area

"Dynamic Signal Control: Real-time Traffic Estimation and Signal Timing Adjustment Using Video Analysis ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.d809-d822, May-2024, Available :http://www.jetir.org/papers/JETIR2405393.pdf

"Dynamic Signal Control: Real-time Traffic Estimation and Signal Timing Adjustment Using Video Analysis ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppd809-d822, May-2024, Available at : http://www.jetir.org/papers/JETIR2405393.pdf