Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network

Rui Chen,Lei Hei,Yi Lai

doi:10.1109/access.2020.3032581

Abstract

A neural network model based on deep learning is utilized to explore the traffic sign recognition (TSR) and expand the application of deep intelligent learning technology in the field of virtual reality (VR) image recognition, thereby assessing the road traffic safety risks and promoting the construction of intelligent transportation networks. First, a dual-path deep CNN (TDCNN) TSR model is built based on the convolutional neural network (CNN), and the cost function and recognition accuracy are selected as indicators to analyze the training results of the model. Second, the recurrent neural network (RNN) and long-short-term memory (LSTM) RNN are utilized to assess the road traffic safety risks, and the prediction and evaluation effects of them are compared. Finally, the changes in safety risks of road traffic accidents are analyzed based on the two key influencing factors of the number of road intersections and the speed of vehicles traveling. The results show that the learning rate of the network model and the number of hidden neurons in the fully-connected layer directly affect the training results, and there are differences in the choices between the early and late training periods. Compared with RNN, the LSTM network model has higher evaluation accuracy, and its corresponding root square error (RSE) is 0.36. The rational control of the number of intersections and the speed of roads traveled has a significant impact on improving the safety level and promoting road traffic efficiency. The VR image recognition algorithm and safety risk prediction method based on a neural network model positively affect the construction of an intelligent transport network.

Highlights

As society develops, cities continue to expand, accompanied by the increase in transportation and the increase in road traffic pressure [1,2]
Zeng et al (2017) proposed a traffic sign recognition (TSR) method based on the core extreme learning machine of deep perception according to the influence of color space on the learning of Convolutional Neural Network (CNN); the results suggested that the method based on deep learning
Kamal et al (2020) proposed a method based on deep convolutional neural network (CNN) and TSR; the VGG-16 architecture was adopted for signal classification, and the model was trained on the CURE-TSD dataset; the results revealed that the accuracy of the network reached 94.60% and the recall rate reached 80.21%, proving the applicability and robustness of deep CNN in the TSR of autonomous vehicles [9]

Summary

Introduction

Cities continue to expand, accompanied by the increase in transportation and the increase in road traffic pressure [1,2]. Scholars have achieved some research results in TSR. Research on TSR in China has started later. While investigating the TSR and detection algorithms, scholars have proposed a cascade detection method [4] and a radial symmetry detector algorithm [5]. Such detection tools have a vast calculation amount and numerous data to be processed. Zeng et al (2017) proposed a TSR method based on the core extreme learning machine of deep perception according to the influence of color space on the learning of Convolutional Neural Network (CNN); the results suggested that the method based on deep learning

Methods

Results

Conclusion