IOT BASED SPEED CONTROL MONITORING AND ACCIDENT AVOIDANCE USING AI TRAFFIC SIGN DETECTION

Abstract

Revolutions occur everywhere in the world. Road mobility is the most crucial component of contemporary communication. Accidents and traffic congestion are becoming major problems as a result of the growing population. Generally speaking, people are unable to receive early alerts about traffic congestion. We later noticed a traffic bottleneck as we approached a particular location. Human-caused traffic accidents are not uncommon these days. Due to the growing number of vehicles and the lenient enforcement of traffic laws, human error plays a significant role in accidents and fatalities on Indian roads. In those mishaps, they also lose our lives and possessions. As a result, tired drivers who are not following the law are involved in traffic accidents. This study recommends using the Multi-tasking Convolutional Neural Network (MConNN) model to recognize traffic signs and vehicle characteristics including location and vibration. The driver's model is identified by physical attributes and traffic indications. These features have been modified to enable speed control and track the vehicle's condition. This paper presents a unique detection method, called MConNN, that can reliably detect speed in real time, identify small traffic signals, assess vehicle attributes, and detect whether a driver is under the influence of alcohol.