Traffic signs play a crucial role in preventing accidents and bottlenecks in traffic. Traffic symbols are visual representations of various information that drivers must be able to understand and obey. Traffic signs are essential for controlling traffic, enforcing driving ehaviour, and preventing accidents, injuries, and fatalities. Recognizing traffic signs in a real-time environment is essential for automated driving cars. We propose a Zero Short Learning-based traffic sign recognition model to address this challenge. The proposed framework uses the self-supervised model to recognize and detect traffic signs without prior training data. The proposed study enhances the zero-short learning method to recognize traffic signs in Lower-brightness situations. Using semantic links, zero-shot learning allows the model to generalize to previously undiscovered classes. This increases its efficiency and adaptability in dynamic contexts and guarantees it can recognize changing traffic laws without requiring continuous retraining—a critical benefit for autonomous vehicles and intelligent transportation networks. The proposed methodology has used the standard German Traffic Sign Recognition Benchmark (GTSRB) dataset. The simulation of the proposed methodology demonstrates the accurate recognition of traffic signs in various scenarios, and the proposed architecture has achieved 99.36 % validation accuracy on the GSTSRB dataset. The authors have also compared the proposed methodology with other self-supervised learning models.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Traffic Sign Recognition Framework Using Zero-Shot Learning


    Weitere Titelangaben:

    Lect. Notes in Networks, Syst.


    Beteiligte:
    Kumar, Sandeep (Herausgeber:in) / Hiranwal, Saroj (Herausgeber:in) / Garg, Ritu (Herausgeber:in) / Purohit, S. D. (Herausgeber:in) / Shah, Prachi (Autor:in) / Patel, Parmanand (Autor:in) / Kothadiya, Deep (Autor:in)

    Kongress:

    International Conference on Communication and Computational Technologies ; 2023 ; Jaipur, India January 28, 2023 - January 29, 2023



    Erscheinungsdatum :

    05.12.2024


    Format / Umfang :

    12 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    SeqNet: Sequential Networks for One-Shot Traffic Sign Recognition With Transfer Learning

    Abdi, Nariman / Parvaresh, Farzad / Farzan Sabahi, Mohamad | IEEE | 2024


    TRAFFIC SIGN RECOGNITION DEVICE AND TRAFFIC SIGN RECOGNITION METHOD

    MIYASATO KAZUHIRO / KOYASU TOSHIYA | Europäisches Patentamt | 2023

    Freier Zugriff

    TRAFFIC SIGN RECOGNITION DEVICE AND TRAFFIC SIGN RECOGNITION METHOD

    SHINOMIYA TERUHIKO | Europäisches Patentamt | 2017

    Freier Zugriff

    Traffic Sign Detection and Recognition using Deep Learning

    Oza, Rudri Mahesh / Geisen, Angelina / Wang, Taehyung | IEEE | 2021


    Traffic Sign Detection and Recognition Using Deep Learning

    Kumar, P. Puneeth / Kishen, R. C. / Ravikumar, M. | Springer Verlag | 2022