本发明实施例公开了一种基于深度学习的车辆压线违章判断方法、装置及存储介质,方法包括:获取交通摄像头所拍摄的视频数据;采用基于多特征融合的方法检测所述视频数据中的车道线,并根据所述车道线划定车道线区域;采用基于深度学习的目标检测和目标跟踪方法检测所述视频数据中的目标车辆及所述目标车辆的车辆边框;根据所述车辆边框确定目标车辆的车辆位置,并根据所述车辆位置对所述目标车辆进行跟踪;跟踪过程中,根据所述车道线区域和车辆边框判断所述目标车辆是否压线;若所述目标车辆压线,则对所述目标车辆进行车牌识别。本方法可自动判定车辆违章压线行为,满足了在交通审核中的高效和高准确率的要求。

    The embodiment of the invention discloses a vehicle line pressing violation judgment method and device based on deep learning and a storage medium. The method comprises the steps of acquiring video data shot by a traffic camera; detecting a lane line in the video data by adopting a method based on multi-feature fusion, and delimiting a lane line area according to the lane line; detecting a targetvehicle in the video data and a vehicle frame of the target vehicle by adopting a target detection and target tracking method based on deep learning; determining a vehicle position of a target vehicleaccording to the vehicle frame, and tracking the target vehicle according to the vehicle position; in the tracking process, judging whether the target vehicle presses a line according to the lane line area and a vehicle frame; and if the target vehicle presses the line, performing license plate recognition on the target vehicle. According to the method, the violation line pressing behavior of thevehicle can be automatically judged, and the requirements of high efficiency and high accuracy in traffic auditing are met.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    基于深度学习的车辆压线违章判断方法、装置及存储介质


    Erscheinungsdatum :

    2023-12-15


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06V / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS