Traffic Sign Classification Comparison Between Various Convolution Neural Network Models

Abstract

Fast detection and accurate classification of traffic signs is one of the major aspects of advance driver assistance system (ADAS) and intelligent transport systems (ITS), this paper presents a comparison between an 8-Layer convolutional neural network (CNN), and some state of the Arts model such as VGG16 and Resnet50, for traffic sign classification on The GTSRB. using a GPU to increase processing time, the design showed that with various augmentation applied to the CNN, our 8-layer Model was able to outperform the State of the Arts models with a higher test Accuracy, 50 times lesser training parameters, and faster training time our 8 -layer model was able to achieve 96% test accuracy.