The invention relates to the technical field of intelligent transportation, in particular to a deep learning retrograde motion detection method based on an embedded terminal, which comprises the following steps: setting a detector area in a vehicle retrograde motion multi-occurrence road section, and dividing the detector area into two continuous sub-areas; identifying whether a vehicle passes ornot is by analyzing and comparing the appearing time sequence of the two images in the detector; recognizing whether the vehicle has a retrograde motion behavior or not according to the relative motion direction of the moving vehicle, and inputting the vehicle as a sample into a deep learning neural network for learning training; and judging the occurrence of a vehicle retrograde motion behavior according to the vehicle driving direction, capturing a violation scene image, intercepting a violation video, and completing detection. According to the invention, by means of deep learning, boundarydetection is carried out by using a sobel operator, and a motion boundary formed in a background when a vehicle passes through a detector is identified, so that comprehensive judgment is enhanced, thejudgment accuracy is improved, real-time judgment of vehicle retrograde motion is realized, and a retrograde motion behavior of a traffic vehicle is relatively accurately and automatically identified.

    本发明涉及智能交通技术领域,具体涉及一种基于嵌入式终端的深度学习逆行检测方法,本发明在车辆逆行多发路段设置探测器区域,并将探测器区域分为两个连续子区域;通过对两幅图像的出现在探测器中时间先后的分析对比,识别是否有车辆通过;通过对运动车辆相对运动方向来识别车辆是否发生逆行行为,并作为样本输入深度学习神经网络进行学习训练;根据车辆行驶方向判断出车辆逆行行为的发生,并抓拍违章现场图像,截取违章视频,完成检测。本发明借助方深度学习,并用sobel算子进行边界检测,识别车辆通过探测器时在背景中形成的运动边界,以加强综合判断,提高判断准确率,实现了车辆逆行的实时判断,实现了较为准确的自动识别交通车辆的逆行行为。


    Access

    Download


    Export, share and cite



    Title :

    Deep learning retrograde motion detection method based on embedded terminal


    Additional title:

    一种基于嵌入式终端的深度学习逆行检测方法


    Contributors:
    ZHANG ZHONG (author) / GUI WANGSHENG (author) / HUANG JUNJIE (author)

    Publication date :

    2021-02-12


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    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 / G06K Erkennen von Daten , RECOGNITION OF DATA



    Deep learning non-motorized vehicle lane driving detection method based on embedded terminal

    ZHANG ZHONG / WANG DINGGUO | European Patent Office | 2020

    Free access


    Vehicle retrograde motion detection method and device,equipment and storage medium

    LIU BO / CAO HUO / LI ZHENG | European Patent Office | 2020

    Free access


    Congestion detection method based on embedded terminal

    ZHANG ZHONG / ZHAO PEI | European Patent Office | 2022

    Free access