Management of Traffic Dynamically Using Yolo

Mahesh Goyal, Saiyam Jain , Ms. Gurpreet

Computer Science Department

Mahavir Swami Institute of Technology

Guru Gobind Singh Indraprastha University, New Delhi

                     ABSTRACT

Traffic congestion is rampant in the world today. Traffic congestion is increasing daily, and the normal way of handling world traffic is not enough. If the number is low. Only in that particular situation where the normal approach works well. In some cases, traffic congestion on the other side of the road may be increased, or the former road system may fail if traffic on one side of the road is too high. Because we live in a fast-paced era, no one wants to wait long hours at any cost, and everyone chooses high-speed roads. Therefore, control measures should be put in place to reduce traffic congestion. We are launching a CNN (Convolutional Neural Network) strategy based on Image Processing to control traffic signals and avoid traffic congestion. The number of vehicles caught in traffic is calculated using the CNN (Convolutional Neural Network) classifiers. As a result, we aim to redesign the traffic signal system now that changes the stationary mode so that the signal changes. The difference in signal time is calculated by the precise image sensor for heavy traffic. This will be an effective practice for the immediate release of tight traffic.

Keywords: Image Processing, CNN, Yolo, Traffic Congestion.