With the rapid development of deep learning methods in the field of computer vision, the effective methods can be applied to the classification and positioning of traffic targets based on real traffic data. This paper studies the application of convolutional neural network in the real traffic information extraction field. The YOLOv3 target detection algorithm, the Faster RCNN target detection algorithm and the SSD target detection algorithm are used to detect vehicles in the images collected in same road condition, and generate the result graph of the target detection. The experimental results show that the YOLOv3 target detection algorithm, Faster RCNN target detection algorithm and SSD target detection algorithm can identify all traffic targets in the traffic road images. It reveals the three algorithms meet the detection needs, and help to achieve non-contact traffic flow collection and feature recognition. Meanwhile these algorithms can provide technical means for traffic supervision and safety improvement.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Research on Traffic Information Extraction Approach Based on Image Deep Learning


    Beteiligte:
    Lu, Manke (Autor:in) / He, Yi (Autor:in) / Cao, Bo (Autor:in) / Wang, Yihong (Autor:in) / Xu, Feng (Autor:in)


    Erscheinungsdatum :

    2021-10-22


    Format / Umfang :

    3073894 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Traffic distribution prediction method based on feature extraction and deep learning

    WANG WEI / YU WEIJIE / QIN SHAOYANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Deep learning based traffic flow prediction model on highway research

    Jia, Qingyang / Zang, Jingfeng / Liu, Shuanglin | SPIE | 2024


    Traffic Rule Violation Detection System: Deep Learning Approach

    Kathane, Mandar / Abhang, Shubham / Jadhavar, Abhishek et al. | Springer Verlag | 2022