The invention discloses a traffic light control method based on multi-channel vehicle detection and three-dimensional feature labeling, and belongs to the field of vehicle detection and traffic light control, and the method comprises the steps: collecting the vehicle information of an intersection through a vehicle detection model; space-time two-dimensional road congestion importance coefficients are introduced into important road sections and intersections to form road network traffic flow three-dimensional feature marks; and establishing a traffic light control system based on a fuzzy neural network, and taking the obtained regional road network traffic state congestion index as the input of the fuzzy neural network to obtain predicted traffic light control information. According to the traffic light control method based on multi-channel vehicle detection and three-dimensional feature marking, influence factors of multiple intersections, multiple lanes and vehicle space-time distribution conditions on traffic light control are considered, fuzzy information processing is carried out through a neural network technology, fuzzy rules are automatically extracted, and fuzzy membership functions are generated, so that the traffic light control accuracy is improved. And a visualization method is provided for observing and researching evolution of the network traffic state.

    本发明公开了一种基于多通道车辆检测与立体特征标注的交通灯控制方法,属于车辆检测和交通灯控制领域,该方法包括利用车辆检测模型采集交叉路口车辆信息;在重要的路段和交叉口引入时空双维度的道路拥堵重要性系数,形成路网交通流立体特征标注;建立基于模糊神经网络的交通灯控制系统,将得到的区域路网交通状态拥挤指数作为模糊神经网络的输入,获得预测出的交通灯控制信息。本发明提供的基于多通道车辆检测与立体特征标注的交通灯控制方法,考虑多路口、多车道、车辆时空分布情况对交通灯控制的影响因素,通过神经网络技术来进行模糊信息处理,并自动提取模糊规则以及生成模糊隶属函数,为观察和研究网络交通状态的演化提供了可视化方法。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic light control method based on multi-channel vehicle detection and three-dimensional feature labeling


    Weitere Titelangaben:

    基于多通道车辆检测与立体特征标注的交通灯控制方法


    Beteiligte:
    DING FEI (Autor:in) / ZHANG NAN (Autor:in) / ZHU YUE (Autor:in) / DO BYUNG-GAB (Autor:in) / ZHAO ZHENG (Autor:in) / ZHANG DENGYIN (Autor:in) / ZHU HONGBO (Autor:in)

    Erscheinungsdatum :

    2023-01-03


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06V



    TRAFFIC LIGHT DETECTION AUTO-LABELING AND FEDERATED LEARNING BASED ON VEHICLE-TO-INFRASTRUCTURE COMMUNICATIONS

    CHEN KUN-HSIN / PILLAI SUDEEP / KAKU SHUNSHO et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Traffic light detection auto-labeling and federated learning based on vehicle-to-infrastructure communications

    CHEN KUN-HSIN / PILLAI SUDEEP / KAKU SHUNSHO et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    THREE DIMENSIONAL TRAFFIC SIGN DETECTION

    BEN YAACOV EREZ / PLAUT ELAD / SHLOMO BAT EL | Europäisches Patentamt | 2022

    Freier Zugriff