本发明提供了一种基于深度学习的动态交通闯红灯识别方法,应用于闯红灯自动识别技术领域,包括:采集车辆行进信息、行人信息以及交通标志线信息;采用深度学习模型交通标志线信息进行检测,并提取交通标志线;根据交通信号灯的控制时间,获取多个待检测图像;获得分割图像,并对分割图像按照时间顺序进行编号;将编号后的分割图像分别输入至深度学习模型中,通过所述深度学习模型进行识别车道线的车辆,并识别车辆对应的车牌号;基于时间顺序所对应的编号,确定处于非行驶时间内进入斑马线的车牌号,并将该车牌号所对应的车辆确定为交通闯红灯车辆。应用本发明实施例,实现了自动进行交通动态闯红灯的识别,提高车辆闯红灯的识别效率。

    The invention provides a dynamic traffic red light running identification method based on deep learning, which is applied to the technical field of red light running automatic identification and comprises the following steps: collecting vehicle traveling information, pedestrian information and traffic sign line information; detecting traffic sign line information by adopting a deep learning model,and extracting a traffic sign line; acquiring a plurality of to-be-detected images according to the control time of the traffic lights; obtaining segmented images, and numbering the segmented imagesaccording to a time sequence; respectively inputting the numbered segmented images into a deep learning model, identifying vehicles of lane lines through the deep learning model, and identifying license plate numbers corresponding to the vehicles; and based on the numbers corresponding to the time sequence, determining the license plate number entering the zebra crossing in the non-driving time, and determining the vehicle corresponding to the license plate number as the traffic red light running vehicle. According to the method of the invention, the method achieves the automatic recognition of the traffic dynamic red light running, and improves the recognition efficiency of the red light running vehicle.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    一种基于深度学习的动态交通闯红灯识别方法


    Erscheinungsdatum :

    2024-02-27


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06V / 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