The invention discloses an other-party vehicle track prediction method based on visual perception. The method specifically comprises the steps that 1, images around a main vehicle body are collected in real time; 2, based on the images around the vehicle body at the current moment, an improved target tracking algorithm is adopted to detect other vehicles around the main vehicle at the current moment, whether the other vehicles are newly appearing vehicles or not is judged, and if the other vehicles are newly appearing vehicles, the track of the vehicle is not predicted at the current moment; 3, the distances between other vehicles and the main vehicle at the current moment is calculated; and 4, the positions of other vehicles relative to the main vehicle at the next moment are predicted. According to the method, the calculation time and the calculation complexity are reduced, the real-time prediction effect can be efficiently achieved, and the method is suitable for most vehicles and intelligent driving scenes.

    本发明公开了一种基于视觉感知的他方车辆轨迹预测方法,具体为:步骤1:实时采集主车辆车身周围的图像;步骤2:基于当前时刻车身周围的图像,采用改进的目标跟踪算法检测出当前时刻主车辆周围的其他车辆,并判断该其他车辆是否是新出现的车辆,若是新出现的车辆,则当前时刻不对该车辆的轨迹进行预测;步骤3:计算当前时刻其他车辆与主车辆之间的距离;步骤4:预测下一个时刻其他车辆相对于主车辆的位置。本发明减少了计算时间和计算的复杂度,可高效的实现实时预测效果,适用于大部分车辆和智能驾驶场景。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Other-party vehicle track prediction method based on visual perception


    Weitere Titelangaben:

    一种基于视觉感知的他方车辆轨迹预测方法


    Beteiligte:
    ZHAO JIE (Autor:in)

    Erscheinungsdatum :

    26.03.2021


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Vehicle track prediction method based on intention perception space-time attention network

    GUO JINGHUA / WANG JINGYAO / HE ZHIFEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Vehicle track prediction method based on heterogeneous node time-space domain perception

    GAO MINGYU / ZENG XUEPU / YANG JUNJIE et al. | Europäisches Patentamt | 2023

    Freier Zugriff


    Vehicle track prediction model construction method and vehicle track prediction method and system

    CHEN ZHE / WANG YUEHAN / LIU HUAN et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Vehicle self-starting method based on visual perception

    ZOU SANCHUAN | Europäisches Patentamt | 2020

    Freier Zugriff