The target detection algorithm is mainly affected by multiple factors such as illumination, clarity, overlap, target size, detection accuracy, and speed decrease greatly in adverse weather conditions. In order to solve these problems, we test the detection performance of YOLOv3 for pedestrians and vehicles with fogged photos. The fogging method is based on the airlight model. The results are shown that the YOLOv3 algorithm can be used for pedestrian and vehicle detection in haze environments, which may be a useful guideline for developing and improving related traffic safety detection systems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vehicle Detection Based on YOLOv3 in Adverse Weather Conditions


    Beteiligte:
    Xia, Jia'er (Autor:in) / Chen, Tianxiang (Autor:in) / Qiao, Jiangrong (Autor:in)


    Erscheinungsdatum :

    2022-10-12


    Format / Umfang :

    1689336 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Vehicle detection method based on improved YOLOv3

    Qi, Cheng / Shen, Xizhong | IEEE | 2022


    Vehicle Detection Based on Improved Yolov3 Algorithm

    Zhao, Shuai / You, Fucheng | IEEE | 2020


    Vehicle Detection Method Based on ADE-YOLOV3 Algorithm

    Yunxiang Liu, Guoqing Zhang, Yuanyuan Zhang: SIT, Shanghai | BASE | 2020

    Freier Zugriff

    Vehicle Detection in Aerial Images Based on YOLOv3

    Hu, Ruiheng / Chen, Bingcai / Tang, Tiantian | Springer Verlag | 2021


    Improving Performance of YOLOv3 for Vehicle Detection

    Prihatmaja, Pratamamia A. / Widyantoro, Dwi H. | IEEE | 2019