Green Corridor Implementation and Real Time Adaptive Traffic Regulation using Machine Learning and Image Processing

Abstract

Traditional traffic light control systems rely on traffic light intervals that are set in stone. Because they use technology that operates according to a system that lacks the flexibility of real-time, traditional fixed traffic light controllers have restrictions and are less efficient. The set time intervals between green and red as a result of the fixed time intervals between green and red. There is excessive and unnecessary traffic congestion, and automobiles consume more gasoline. This eventually causes environmental issues as well as a variety of health issues for people. The rise in the number of personal automobiles has a negative impact on the environment. The goal of this project is to develop a traffic system that adapts to current traffic conditions in a lane. In most cases, the average waiting time for all lanes is set. This idea proposes that the number of vehicles in a lane be monitored to reduce the average waiting time. A predictive model will also be implemented, which will make decisions based on prior traffic patterns, mostly at habitually congested crossings. Emergency vehicles will also be identified, and a faster route will be established for them.