The invention discloses a non-motor vehicle helmet wearing detection method based on an improved YOLOv3 algorithm, and the method comprises the steps: obtaining a traffic monitoring video stream, carrying out the processing and data enhancement, and building a training data set; constructing an improved YOLOv3 target detection model; training the improved YOLOv3 algorithm model by using the training data set, and loading the optimal weight file after training to the model to obtain a non-motor vehicle helmet detection network; reading a traffic monitoring video frame image to be detected, and outputting a corresponding helmet detection result by adopting the non-motor vehicle helmet detection network. The non-motor vehicle helmet wearing detection method solves the problem that a traditional manual detection method is low in efficiency, and improves the speed and accuracy of non-motor vehicle helmet wearing detection.

    本发明公开一种基于改进YOLOv3算法的非机动车头盔佩戴检测方法,包括:获取交通监控视频流,进行加工、数据增强建立训练数据集;构建改进的YOLOv3目标检测模型;使用训练数据集对改进的YOLOv3算法模型进行训练,将训练后最佳的权重文件加载至模型得到非机动车头盔检测网络;读入待检测的交通监控视频帧图像,采用所述非机动车头盔检测网络输出对应的头盔检测结果。本发明解决了传统人工检测方法效率低的问题,提高了非机动车头盔佩戴检测的速度和准确度。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Non-motor vehicle helmet wearing detection method based on improved YOLOv3 algorithm


    Weitere Titelangaben:

    基于改进YOLOv3算法的非机动车头盔佩戴检测方法


    Beteiligte:
    ZHENG SHUIHUA (Autor:in) / XU YILUN (Autor:in) / SUN ZENAN (Autor:in) / LIN WEI (Autor:in)

    Erscheinungsdatum :

    2021-11-02


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS