Insights of Deep Convolutional Neural Network for Traffic Sign Detection in Autonomous Vehicle

Abstract

This Traffic Sign Recognition (TSR) plays a vital role in disciplining drivers and managing traffic on the road, which helps to prevent road accidents, damage, fatalities and property injury. Traffic sign recognition and management with automatic detection are critical components of any Smart Transportation System (STS). Throughout this era of autonomous vehicles, automated detection as well as identification of traffic signs are a must. This research discusses a self-directed traffic sign identification system in India that is based on deep learning. Automatic traffic sign identification as well as recognition was created utilizing Convolutional Neural Network (CNN) learning from the ground up. Deep Convolutional Neural Networks are now used to an increasing number of object recognition applications. Convolutional neural networks(CNN) have improved both current and new computer vision tasks due to their high detection rate and superior performance. This study proposes a strategy for identifying traffic signals that makes use of deep convolution neural network. This research study compares many CNN designs against one another. TensorFlow, a prominent machine learning framework is built by utilizing the massively parallel multithreaded programming of CUDA architecture for deep neural network training. The trial findings validated the effectiveness of the created computer vision system. The proposed model attained an accuracy of 97.08%, which is superior to the present approach of traffic sign detection.