Traffic Sign Detection Based on Deep Learning Methods

Abstract

This article gives a brief overview of a few current research on traffic signs detection, which briefly reviews the concept and structure of traffic signs detection in the last decade. The methodology varies in different ways which is generally separated into two exact dimensions. The first one is the traditional method using the theory of computer vision with machine learning to detect the traffic signs, while the other one uses deep learning to train the model to detect the objects. In recent years, the methods based on deep learning have gradually replaced the traditional methods since they can extract features from traffic signs better and do predictions. Therefore, this paper mainly focuses on the deep learning methods for traffic signs detection and reviews previous work and their corresponding datasets and performance. The results based on different methods are compared. Finally, we made a conclusion based on this review.

ROAD: Robotics-Assisted Onsite Data Collection and Deep Learning Enabled Robotic Vision System for Identification of Cracks on Diverse Surfaces

“…They evaluate the performance of these methods using two benchmark datasets and show that their CNN-based method outperforms other methods. A technique for identifying crack deterioration in engineering structures using unmanned aerial vehicle images and a deep learning model that has already been trained was proposed by Huang et al [23]. The CNN used by the authors is fine-tuned with their own data of UAV images after being pre-trained on the ImageNet dataset.…”