In today's scenario, congestion has become a major issue. Mainly the urban cities hit the hardest and its ever- increasing nature, real time knowledge of automobile road traffic density is essential for improved control of traffic signals and efficient management of traffic. The factors that contribute to traffic congestion are inadequate capacity, constrained demand, significant delays at red lights, etc. Capacity constraints and demand constraints are somehow related, but the delay for each signal is hard coded and traffic independent. So, to better meet this growing demand, the traffic control needs to be simulated and optimized. In recent times, image processing and surveillance systems are established in passenger information, access measurement and traffic control for real- time updates. Estimation of traffic bulkiness can also be performed using image processing. Tracing images of the moving automobiles can provide a quantitative explanation of traffic flow. This paper demonstrates how to utilize real-time live video feeds from cameras at intersections to perform instantaneous traffic bulkiness calculations using image processing and vehicle detection using EfficientDet architecture and TensorFlow lite. It also aims to reduce traffic jams and accidents by focusing on algorithms that switch signal lights on the basis of density of vehicles on the road and the priority set for specific emergency vehicles. In turn, it provides people with safe transportation, reduces fuel consumption and waiting times. Vehicle recognition is done by the system from images and not by using electronic sensors mounted on the roadway. Installation of camera is done next to the traffic light, which captures the video feed sent to the Raspberry Pi. The proposed algorithm aids to manage the timing of the traffic lights which in turn helps to achieve the goal of automatic control of traffic situations. © 2023 The Author(s)