The invention discloses a target distance detection method based on deep learning. The method comprises the following steps of: acquiring driving images of a target vehicle in a detection area, and aleft vehicle and a right vehicle in a lane adjacent to the target vehicle in the same direction as the target vehicle and adopting the driving images as to-be-analyzed images; determining land touching points of a left front wheel and a right front wheel of the target vehicle, a right rear wheel of the left side vehicle and a left rear wheel of the right side vehicle in a world coordinate system according to a deep learning neural network model and the to-be-analyzed images; determining the distance between the target vehicle and the left side vehicle according to the land touching points of the left front wheel of the target vehicle and the right rear wheel of the left side vehicle, and marking the distance as a first distance; and determining the distance between the target vehicle and the right side vehicle according to the land touching point of the right front wheel of the target vehicle and the land touching point of the left rear wheel of the right side vehicle, and marking thedistance as a second distance. According to the method, vehicle driving states can be analyzed in a targeted manner, and the traffic safety is improved.

    本发明公开了一种基于深度学习的目标距离检测方法。获取检测区域内目标车辆、与目标车辆同向相邻车道中左侧车辆和右侧车辆的行驶图像,作为待分析图像;根据深度学习的神经元网络模型和所述待分析图像,确定在世界坐标系中所述目标车辆的左前轮和右前轮、所述左侧车辆的右后轮、所述右侧车辆的左后轮的着地点;根据所述目标车辆的左前轮与所述左侧车辆的右后轮的着地点,确定所述目标车辆与所述左侧车辆之间的距离,并标记为第一距离;根据所述目标车辆的右前轮与所述右侧车辆的左后轮的着地点,确定所述目标车辆与所述右侧车辆之间的距离,并标记为第二距离。本方法能够针对性对车辆行驶状态进行分析,有利于提高交通安全性。


    Access

    Download


    Export, share and cite



    Title :

    Target distance detection method based on deep learning


    Additional title:

    一种基于深度学习的目标距离检测方法


    Contributors:
    ZHANG ZHONG (author) / ZHANG XING (author) / ZHANG JINFEI (author)

    Publication date :

    2021-03-19


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G01C Messen von Entfernungen, Höhen, Neigungen oder Richtungen , MEASURING DISTANCES, LEVELS OR BEARINGS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Maritime Target Detection Method Based on Deep Learning

    Fu, Huixuan / Li, Yuan / Wang, Yuchao et al. | British Library Conference Proceedings | 2018



    Vehicle dense target detection method based on deep learning

    WU XIAO / ZHANG JI / XIANG CHONGYANG et al. | European Patent Office | 2021

    Free access


    Research on Target Detection Based on Deep Learning

    Liao, Pengjun / Xu, Jinxiang / Guo, Shangkun et al. | Springer Verlag | 2022