With the rapid development of driverless technology, traffic sign recognition, as a key link in the intelligent transportation system, has attracted much attention. However, traditional traffic sign recognition methods have problems such as long training time, high model complexity and low accuracy, which are difficult to meet the needs of practical applications. To this end, this paper designs a lightweight traffic sign recognition model for this problem, which is characterized by the introduction of a new attention mechanism to achieve effective capture of key image features. The model shows satisfactory performance after being tested on the Chinese Traffic Sign Database (TSRD) dataset, achieving an optimal recognition accuracy of 99.83% with only 0.05 MB of parametric quantities (Params). The effectiveness of our proposed method is demonstrated through comparative experiments. In addition, this paper is not only in proposing an effective lightweight model, but also in providing new ideas and guidance for the research and practice in the field of traffic sign recognition, which has important theoretical and practical significance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Traffic Sign Recognition Based on Lightweight Multi-Scale Spatial Attention


    Contributors:
    Chen, Zidan (author) / Wei, Yan (author)


    Publication date :

    2024-06-28


    Size :

    1217122 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A lightweight network for traffic sign recognition based on multi-scale feature and attention mechanism

    Wei, Wei / Zhang, Lili / Yang, Kang et al. | Elsevier | 2024

    Free access

    Multi-scale traffic sign detection model with attention

    Fan, Bei Bei / Yang, He | SAGE Publications | 2021


    Road traffic sign recognition based on lightweight neural network

    Li, Le-yang / Yue, Qin / Luo, Rui-wen | SPIE | 2021


    A Novel Lightweight Traffic Sign Recognition Model Based on YOLOv5

    Li, Wenju / Zhang, Gan / Cui, Liu | ASCE | 2023


    Traffic Sign Detection Using a Multi-Scale Recurrent Attention Network

    Tian, Yan / Gelernter, Judith / Wang, Xun et al. | IEEE | 2019