The invention aims to provide application of computer vision in the traffic field so as to overcome the defects that in the prior art, a system is poor in detection accuracy and low in sensitivity, and illegal vehicles cannot be accurately detected. Compared with the prior art, the method has the beneficial effects that the recognition accuracy and sensitivity of traffic violation are effectively improved by utilizing the YOLOv4 neural network, the accuracy can reach 98% of recognition rate and the accuracy of license plates can reach 92% in the aspect of vehicle recognition, pedestrian and zebra crossing recognition is further realized, the detection efficiency is improved and the detection function is expanded when the detection of the red light running and the vehicle not giving way to the pedestrian is carried out.

    本发明的目的在于提供一种利用计算机视觉在交通领域的应用,以解决现有技术中系统的检测准确度差,灵敏度低,无法准确地对违规车辆进行检测的缺陷。与现有技术相比,本发明所达到的有益效果:利用YOLOv4神经网络有效的提高了交通违章的识别准确率与灵敏度,在车辆识别方面,精确度可以达到98%的识别率,车牌的正确率也高达92%,更进一步实现了行人与斑马线识别,闯红灯与车辆不礼让行人的检测在提高了检测效率的同时扩展了检测功能。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Application of computer vision in traffic field


    Weitere Titelangaben:

    一种利用计算机视觉在交通领域的应用


    Beteiligte:
    WANG CHENYANG (Autor:in)

    Erscheinungsdatum :

    2021-09-28


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Computer vision application: Real time smart traffic light

    Serrano, Angel / Conde, Cristina / Rodriguez-Aragon, Licesio J. et al. | Tema Archiv | 2005


    Computer vision-aided road traffic monitoring

    Ali,A.T. / Dagless,E.L. / Univ.of Bristol,GB | Kraftfahrwesen | 1991


    Computer Vision based Intelligent Traffic Management System

    Darwhekar, Kshitij / Patil, Amey / Ghodke, Sankalp et al. | IEEE | 2022


    Traffic control system based on computer vision

    XIAO JIE / XIAO LINGXIANG / XIE DONG et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Computer-vision-based traffic light control method

    CHEN ZHI / WANG FENG / YUE WENJING | Europäisches Patentamt | 2015

    Freier Zugriff