The invention provides a traffic entity trajectory prediction method and system based on LSTM deep learning, and the method comprises the steps: receiving a prediction request for a to-be-predicted traffic entity, and obtaining the type of the to-be-predicted traffic entity and historical spatial data; inputting the historical spatial data into a pre-constructed and trained first prediction model based on LSTM to obtain a first trajectory prediction result; determining feature information of a to-be-detected traffic entity type corresponding to the first trajectory prediction result, and inputting the historical spatial data and the feature information into a pre-constructed and trained second prediction model based on LSTM to obtain a second trajectory prediction result; and embedding the second trajectory prediction result into a vector with the same length as the first trajectory prediction result to complete splicing, thereby obtaining a traffic entity trajectory prediction result. In the face of complex traffic environments and different types of traffic entities, the motion trails of the different types of traffic entities can be predicted more accurately, the applicability is higher, and the flexibility is higher.

    本申请提供一种基于LSTM深度学习的交通实体轨迹预测方法及系统,其中,方法包括:接收对待测交通实体的预测请求,获取待测交通实体类型和历史空间数据;将历史空间数据输入预先构建并训练得到的基于LSTM的第一预测模型,得到第一轨迹预测结果;确定第一轨迹预测结果对应的待测交通实体类型的特征信息,将历史空间数据和特征信息输入预先构建并训练得到的基于LSTM的第二预测模型,得到第二轨迹预测结果;将第二轨迹预测结果嵌入至与第一轨迹预测结果等长的向量中完成拼接,得到交通实体轨迹预测结果。面对复杂的交通环境和不同类型交通实体时,能够更加准确的预测不同类型交通实体的运动轨迹,适用性更高,灵活度更强。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic entity trajectory prediction method and system based on LSTM deep learning


    Weitere Titelangaben:

    基于LSTM深度学习的交通实体轨迹预测方法及系统


    Beteiligte:
    CHEN JINPENG (Autor:in) / YANG ZHENYE (Autor:in) / LI XIUYUN (Autor:in) / YU ZIYU (Autor:in) / HAN WANJIANG (Autor:in)

    Erscheinungsdatum :

    17.09.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion



    LSTM model-based vulnerable traffic participant trajectory prediction method

    ZHANG XI / YIN CHENGLIANG / CHEN HAO et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Pedestrian Trajectory Prediction Based on Deep Convolutional LSTM Network

    Song, Xiao / Chen, Kai / Li, Xu et al. | IEEE | 2021


    Transform and LSTM-based vehicle trajectory prediction method

    CHENG DENGYANG / GU XIANG / QIAN CONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Pedstrian Trajectory Prediction Based on LSTM

    Li, Shaosong / Jiang, Junchen / Zhou, Qingbin et al. | IEEE | 2023