DEEP LEARNING APPLICATION IN TRAFFIC SIGNS RECOGNITION AND DETECTION IN NIGERIA

Abstract

Mobility is an element that is highly related to the development of society and the quality of individual life. The increase in demand for automobile production and traffic infrastructure construction, advanced countries have reached a high degree of individual mobility. In order to increase the efficiency, convenience and safety of mobility, advanced traffic infrastructure construction and transportation systems for automobiles should be developed. Among all the systems for modern automobiles, cameras-based assistance systems are one of the most important components. Recently, with the development of driver assistance systems and autonomous cars, detection and recognition of traffic sign objects based on computer vision become more and more indispensable. On the other hand, the deep learning methods, in particular convolutional neural networks have achieved excellent performance in a variety of computer vision tasks. This thesis mainly presents the contributions to the computer vision and deep learning methods for traffic signs detection and recognition. The System uses deep CNN in detecting and recognizing traffic sign image. The German Traffic Sign Recognition Benchmark was used to train in the CNN model in a supervised way. Pre-processing and segmentation are tested to make the training more robust and the network is able to generate more independent features. Experimental results show that the proposed CNN architecture achieved an accuracy of 95.5%, thus higher than those achieved in similar previous studies. This project is implemented with the OpenCV tool, Convolution Neural Network, TensorFlow and the Python programming language