The invention provides a road anomaly recognition method and system based on multi-modal perception, and relates to the technical field of anomaly recognition, and the method comprises the steps: connecting a multi-modal data storage library, downloading multi-modal perception data, then carrying out the data preprocessing of the multi-modal perception data, carrying out the data screening and filtering through an information theory coding operation mode, and carrying out the recognition of the multi-modal perception data. And then analysis is carried out from a data source angle, an anomaly type angle, an occurrence time dimension and an occurrence position angle, and finally, an anomaly identification result is obtained. The method mainly solves the problems that the object of image acquisition is inaccurate, extreme weathers such as heavy fog and heavy rain cannot be handled, the application scene is single, scene changes cannot be effectively handled, and abnormal recognition is inaccurate. According to the method, multi-modal sensing data is divided from multiple dimensions, and comprehensive analysis and processing are carried out, so that road anomalies can be identified more accurately.

    本申请提供多模态感知的道路异常识别方法及系统,涉及异常识别技术领域,所述方法包括:连接多模态数据存储库,下载多模态感知数据,然后对多模态感知数据进行数据预处理,通过信息论编码运算的方式进行数据筛选过滤,得到多模态感知预处理数据,然后从数据源角度、异常类型角度、发生时间维度、发生位置角度进行分别分析,最终获取异常识别结果。本申请主要解决了图像采集的物体不准确,不能应对大雾和大雨等极端天气,应用场景单一,无法有效地处理场景变化,对于异常的识别不准确的问题。利用多模态感知数据从多个维度进行划分,进行综合分析和处理,以更准确地识别道路异常。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Multi-modal sensing road anomaly identification method and system


    Weitere Titelangaben:

    多模态感知的道路异常识别方法及系统


    Beteiligte:
    YAN JUN (Autor:in) / HUO JIANJIE (Autor:in)

    Erscheinungsdatum :

    2024-04-12


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Improving multi-modal data fusion by anomaly detection

    Simanek, J. | British Library Online Contents | 2015



    MULTI-MODAL SENSING TRANSDUCERS

    LEE CHENG / LU CHEE | Europäisches Patentamt | 2018

    Freier Zugriff

    MULTI-MODAL SENSING TRANSDUCERS

    LEE CHENG SEONG / LU CHEE WAI | Europäisches Patentamt | 2021

    Freier Zugriff

    Road side sensing equipment abnormity identification method and road side sensing fusion system

    JIANG BIN / ZHANG HAOYU | Europäisches Patentamt | 2022

    Freier Zugriff