The invention relates to the technical field of traffic data processing, in particular to a holographic traffic state data set construction method based on multi-source information fusion, which comprises the following steps: acquiring an original data set, constructing a directed road network diagram and an undirected road network diagram according to a road network topological relation, performing imaging processing on traffic information by the road network diagram according to a color matching equation, and constructing a holographic traffic state data set. The method comprises the following steps: constructing an adjacent-order matrix, carrying out preliminary correction and completion on original traffic characteristic data through a space-time information compensation network in combination with a traffic information graph, establishing an iterative completion generative adversarial network (IGANI) model, generating a completion data set, constructing a weighted directed graph based on a road physical connection relation model established by the adjacent-order matrix and a directed road network graph, and carrying out data processing on the weighted directed graph. And predicting traffic state data in a period through a GE-LSTM traffic state prediction model to generate a prediction data set, and constructing a holographic traffic state data set, thereby effectively overcoming the problem of data missing caused by equipment damage and aging faults, and effectively improving the control effect of a traffic control system.

    本发明涉及交通数据处理技术领域,尤其涉及一种基于多源信息融合的全息交通状态数据集构建方法,包括获取原始数据集,根据路网拓扑关系构造有向路网图与无向路网图,路网图根据颜色匹配方程为交通信息进行图像化处理,构造邻阶矩阵,结合交通信息图经过空间‑时间信息补偿网络对原始交通特征数据进行初步修正补全,建立迭代补全生成式对抗性网络IGANI模型,生成补全数据集,基于邻阶矩阵与有向路网图建立的道路物理连接关系模型搭建加权有向图,经GE‑LSTM交通状态预测模型预测出周期内交通状态数据生成预测数据集,构建全息交通状态数据集,本发明有效克服由于设备损坏老化故障问题造成的数据缺失问题,有效提升交通控制系统的控制效果。


    Access

    Download


    Export, share and cite



    Title :

    Holographic traffic state data set construction method based on multi-source information fusion


    Additional title:

    一种基于多源信息融合的全息交通状态数据集构建方法


    Contributors:
    WANG PANGWEI (author) / HE XINZE (author) / WANG TIANREN (author) / LIU CHENG (author)

    Publication date :

    2023-06-23


    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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Construction method of traffic knowledge graph based on multi-source data fusion

    ZHENG CHUNJUN / JIA NING / LI YINGQIU et al. | European Patent Office | 2023

    Free access

    Traffic state estimation method and device based on multi-source information fusion

    GUO YUQI / LI BIN / LI HONGHAI et al. | European Patent Office | 2021

    Free access

    Urban expressway traffic state estimation method based on multi-source data fusion

    LONG KEJUN / LIU YANG / WU WEI et al. | European Patent Office | 2021

    Free access

    Multi-source traffic information fusion method and device

    ZHANG DONGBO / LI LI / ZHANG YU et al. | European Patent Office | 2020

    Free access

    Traffic control approach based on multi-source data fusion

    Wang, Pu / Wang, Chengcheng / Lai, Jiyu et al. | IET | 2019

    Free access