In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
Technology of Graphic & Image
|
App. Res. of Comp. Printed Article
Vol. 39, 2022 No. 5
1557-1562

Study on traffic sign recognition based on multi-scale convolutional neural network

Liu Wanjun
Li Jiaxin
Qu Haicheng
School of Software, Liaoning Technical University, Huludao Liaoning 125105, China
DOI: 10.19734/j.issn.1001-3695.2021.10.0457

Abstract

Traffic sign recognition has a wide application prospect in the field of automatic driving. In the actual scene, ligh-ting, geographical location, detection methods and other factors will affect the identification of small traffic signs, resulting in reduced identification accuracy. To solve these problems, this paper proposed a new multi-scale fusion convolutional neural network model(SF-RCNN). Firstly, it added multi-scale atrous spatial pyramid pooling(MASPP) to the basic feature extraction network. After multi-scale dilated convolution sampling, the amount of information under each feature was not changed. In this way, the loss of resolution could be reduced and the context information of the same image could be captured. Secondly, it increased two fast concat modules(F-concat) in the network. The fusion of high and low level information could not only enrich semantic information, but also realize the reuse of information at different scales. Finally, it increased a batch normalization layer(BN) before each maximum pooling layer. Although the addition of modules deepened the network depth, BN layer could accelerate the model convergence speed, so that the whole training time didn't not change greatly. Feature extraction is carried out on the CCTSDB data set. The experimental results show that this paper uses the new network structure SF-RCNN, extracts the features from CCTSDB dataset, and the average accuracy of traffic sign identification reaches 87.48%. The recognition accuracy of warning category is 89.93%, prohibition category is 89.25%, direction category is 81.08% and indication category is 89.66%.

Foundation Support

国家自然科学基金资助项目(42071351)
辽宁省教育厅基础研究项目(LJ2019JL010)
辽宁省教育厅科学研究项目(LJ2020QNL013)
辽宁工程技术大学学科创新团队资助项目(LNTU20TD-23)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2021.10.0457
Publish at: Application Research of Computers Printed Article, Vol. 39, 2022 No. 5
Section: Technology of Graphic & Image
Pages: 1557-1562
Serial Number: 1001-3695(2022)05-047-1557-06

Publish History

[2021-12-17] Accepted Paper
[2022-05-05] Printed Article

Cite This Article

刘万军, 李嘉欣, 曲海成. 基于多尺度卷积神经网络的交通标示识别研究 [J]. 计算机应用研究, 2022, 39 (5): 1557-1562. (Liu Wanjun, Li Jiaxin, Qu Haicheng. Study on traffic sign recognition based on multi-scale convolutional neural network [J]. Application Research of Computers, 2022, 39 (5): 1557-1562. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)