The invention discloses a road traffic target tracking method based on a deep convolutional neural network. License plate and feature input is carried out on a target vehicle needing to be searched through a monitoring terminal, a convolutional neural network carries out command capturing on road cameras, feature vehicles are screened and checked through the road cameras to determine the target vehicle, and the target vehicle is searched through mutual cooperation of multiple groups of road cameras. The real-time positioning real-time image and video of the target vehicle are transmitted to the monitoring terminal for tracking display, and the monitoring terminal can determine and deny the target vehicle, so that the positioning and tracking accuracy of the target vehicle is improved; vehicles which are negatively screened can be automatically excluded, so that the target vehicle capturing efficiency is effectively improved, and time waste caused by repeated capturing of the system is avoided; the target vehicle can be quickly and effectively captured and tracked through the intelligence of the convolutional neural network, the locking timeliness is improved, the locking speed is increased, and the effect of preventing the target vehicle from being lost is achieved.

    本发明公开了基于深度卷积神经网络的道路交通目标跟踪方法。通过监控终端对需要查找的目标车辆进行车牌和特征输入,使卷积神经网络对道路摄像头进行捕捉命令,通过道路摄像头对特征车辆进行筛选和排查确定出目标车辆,再通过多组道路摄像头相互配合,将目标车辆的实时定位实时图像和视频传输给监控终端进行追踪显示,且监控终端能够对目标车辆进行确定和否定,从而增加了目标车辆的定位和追踪的精准度;通过对车辆否定筛选掉的车辆会进行自动排除,有效提高了对目标车辆捕捉的效率,避免系统重复捕捉而造成时间的浪费;通过卷积神经网络的智能性能够对目标车辆进行快速有效的捕捉和追踪,增加锁定的及时性和速率,具有防止目标车辆丢失的效果。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Road traffic target tracking method based on deep convolutional neural network


    Weitere Titelangaben:

    基于深度卷积神经网络的道路交通目标跟踪方法


    Beteiligte:
    LI DECHENG (Autor:in) / DONG DONG (Autor:in) / WU XIAOFENG (Autor:in) / WANG LEI (Autor:in) / TONG ZHE (Autor:in)

    Erscheinungsdatum :

    2022-11-01


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06V / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Road traffic target attribute identification method based on deep convolutional neural network

    HU CUIYUN / ZHONG JIANBIN / CHEN MANNA et al. | Europäisches Patentamt | 2022

    Freier Zugriff


    Road network dynamic traffic distribution method based on Encoder-Decoder deep neural network

    XIA JINGXIN / CHENG MIN / WANG YINPU et al. | Europäisches Patentamt | 2021

    Freier Zugriff


    Large road network traffic signal control method based on deep Q learning neural network

    FANG ZHONGLIANG / ZHANG ZHAN / WANG ZHEBING et al. | Europäisches Patentamt | 2021

    Freier Zugriff