The invention discloses a traffic flow anomaly detection method based on a graph contrast learning network, and belongs to the technical field of traffic flow monitoring. According to the method, an urban road network structure and traffic flow occupancy rate, speed and flow information are taken as road section characteristics, an area clustering algorithm is designed to form urban area representation, and an urban road section graph structure and an urban area graph structure are constructed; on the basis of two urban traffic map structures, a space-time encoder-decoder network with shared parameters is designed, the network is composed of a space-time attention module composed of a map volume machine layer and a time self-attention layer and a designed flow change extraction comparison learning layer, and traffic congestion and abnormal road sections are efficiently detected in different time and dynamic environments. According to the method, the traffic condition can be efficiently modeled in different time and dynamic environments, so that the spatial-temporal characteristics of urban traffic can be better understood; the real-time and dynamic change of urban traffic can be processed, and the effectiveness of traffic management is improved.

    本发明公开了一种基于图对比学习网络的交通流异常检测方法,属于交通流量监测技术领域。本发明以城市路网结构和交通流的占有率、速度和流量信息为路段特征,设计区域聚类算法形成城市区域表示,构建城市路段图结构和城市区域图结构;基于两个城市交通图结构,设计参数共享的时空编码器‑解码器网络,网络由图卷机层和时间自注意力层组成的时空注意力模块,和设计的流量变化提取对比学习层组成,在不同时间和动态环境下高效检测交通拥堵和异常路段。本发明可以在不同时间和动态环境下高效地对交通情况进行建模,有助于更好地理解城市交通的时空特征;能够处理城市交通的实时和动态变化,提高了交通管理的实效性。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow anomaly detection method based on graph contrast learning network


    Additional title:

    一种基于图对比学习网络的交通流异常检测方法


    Contributors:
    MA JIAMAN (author) / WU YIZHENG (author) / LUO XILING (author)

    Publication date :

    2024-04-16


    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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Traffic anomaly detection method based on graph convolutional neural network auto-encoder

    LI XIAOJIE / REN ZHIYU / SHI CANGHONG et al. | European Patent Office | 2023

    Free access

    Graph neural network traffic flow prediction method based on deep learning

    CHENG XIAOHUI / HE YUHAO / LU QIU | European Patent Office | 2023

    Free access

    Traffic flow prediction method based on federated learning and graph neural network

    MI BO / ZENG RAN / HUANG DARONG et al. | European Patent Office | 2024

    Free access

    A Survey on Vehicular Traffic Flow Anomaly Detection Using Machine Learning

    Chew Jackel Vui Lung / Asli Mohammad Fadhli | DOAJ | 2024

    Free access

    Traffic Anomaly Detection Via Conditional Normalizing Flow

    Kang, Zhuangwei / Mukhopadhyay, Ayan / Gokhale, Aniruddha et al. | IEEE | 2022