A Systematic Study of Various Techniques of Obstacle Detection and Traffic Sign Detection used in Self Driving Car Application of IOT

Abstract

Due to the advancement in smart technologies like Artificial Intelligence (AI), Machine Learning (ML), Internet of Things (IoT), and sophisticated sensors, self-driving cars are emerging as a significant innovation in the automotive sector. Accurately detecting obstacles and traffic signs is a critical component of autonomous driving. However, there are a number of difficulties with this method, including variations in lighting and weather conditions, sensor limits, and the requirement for fast real-time processing. Accidents or poor driving choices may result from a self-driving car's inability to accurately detect barriers or traffic signs.

Present-day approaches for detecting obstacles and traffic signs in self-driving car application of IOT make use of deep learning-based models, LiDAR, and image processing. Nevertheless, these approaches have drawbacks such as high processing requirements, trouble identifying signs in low light, and sensor limits. This research focuses on studying different techniques of Obstacle and road traffic sign detection used in self- driving car, comparing their strengths and weaknesses, and exploring ways to improve their efficiency. The goal is to develop a more reliable detection system that enhances the safety and performance of self-driving cars.