Int J Performability Eng ›› 2019, Vol. 15 ›› Issue (8): 2182-2189.doi: 10.23940/ijpe.19.08.p18.21822189

Previous Articles     Next Articles

Deep Convolutional Neural Network and Its Application in Image Recognition of Road Safety Projects

Lingling Wanga,b, Wenyin Gonga,*, and Xiang Lia   

  1. a School of Computer Science and Technology, China University of Geosciences, Wuhan, 430000, China
    b School of Information Engineering, Wuhan University of Engineering Science, Wuhan, 430000, China
  • Submitted on ;
  • Contact: * E-mail address:
  • About author:Lingling Wang is a doctoral student in the School of Computer Science and Technology at the China University of Geosciences. She received her master's degree from the China University of Geosciences in 2013. Her current research interests include computer networks, security, and machine learning. Wenyin Gong is a professor and doctoral supervisor. His main research interests include intelligent computing and its applications. He is currently the deputy secretary general of the Hubei Computer Society and the editor of the international SCI journal Memetic Computing. He has presided over two projects of the National Natural Science Foundation and one of the new Teachers' Funds for Doctoral Programs under the Ministry of Education. Xiang Li is an associate professor at the China University of Geosciences and studies geoscience information engineering.

Abstract: Road safety projects constitute an important part of road safety facilities. Assessing the safety of these projects is important for assessing the safety of roads. In recent years, road safety problems have caused enormous losses to the country and its people. Traditional inspection and maintenance of road safety projects mainly involve manual inspection and on-site maintenance; however, manual inspection is time-consuming and laborious, and it cannot be used to identify safety issues in large areas. This paper focuses on the application of the deep convolutional neural network algorithm, a deep learning algorithm, for the recognition of road safety projects. Comparative analysis of the experimental results shows that both the convolutional neural network models VGG16 and InceptionV3 can identify the pre-processed data sets of the road safety projects; however, the accuracy of the test set model InceptionV3 is higher than that of VGG16, reaching 93.3%.

Key words: deep learning, deep convolutional neural network, image recognition, road safety project