Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network
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 constru...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9233325/ |
id |
doaj-9660983627d349719a70c01cb4d7697d |
---|---|
record_format |
Article |
spelling |
doaj-9660983627d349719a70c01cb4d7697d2021-03-30T04:12:37ZengIEEEIEEE Access2169-35362020-01-01820179920180510.1109/ACCESS.2020.30325819233325Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural NetworkRui Chen0https://orcid.org/0000-0001-5292-3374Lei Hei1Yi Lai2https://orcid.org/0000-0002-2653-4348School of Communications and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an, ChinaInstitute of Xi’an Aerospace Solid Propulsion Technology, Xi’an, ChinaSchool of Communications and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an, ChinaA 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.https://ieeexplore.ieee.org/document/9233325/TDCNNimage recognitionRNNLSTMsecurity riskassessment |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rui Chen Lei Hei Yi Lai |
spellingShingle |
Rui Chen Lei Hei Yi Lai Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network IEEE Access TDCNN image recognition RNN LSTM security risk assessment |
author_facet |
Rui Chen Lei Hei Yi Lai |
author_sort |
Rui Chen |
title |
Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network |
title_short |
Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network |
title_full |
Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network |
title_fullStr |
Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network |
title_full_unstemmed |
Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network |
title_sort |
image recognition and safety risk assessment of traffic sign based on deep convolution neural network |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
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. |
topic |
TDCNN image recognition RNN LSTM security risk assessment |
url |
https://ieeexplore.ieee.org/document/9233325/ |
work_keys_str_mv |
AT ruichen imagerecognitionandsafetyriskassessmentoftrafficsignbasedondeepconvolutionneuralnetwork AT leihei imagerecognitionandsafetyriskassessmentoftrafficsignbasedondeepconvolutionneuralnetwork AT yilai imagerecognitionandsafetyriskassessmentoftrafficsignbasedondeepconvolutionneuralnetwork |
_version_ |
1724182218572562432 |