The invention provides a traffic accident prediction method and device based on deep learning, and relates to the technical field of deep learning, and the method comprises the steps: obtaining a monitoring video corresponding to a target traffic scene; performing feature extraction on the monitoring video to obtain target image features; the target image features comprise RGB image global features, RGB image local features, depth image global features and depth image local features; obtaining association information between different features in the target image features by using a collaborative attention mechanism, and fusing the features in the target image features based on the association information to obtain a target fusion feature; and inputting the target fusion feature into a trained GRU network model, and outputting to obtain a traffic accident prediction probability corresponding to the target traffic scene. Through cascade combination of the collaborative attention layers, complementary perception fusion of multiple features is realized, and then a GRU module is utilized to predict whether traffic accidents occur in the future, so that the traffic accidents are reduced.

    本发明提供一种基于深度学习的交通事故预测方法和装置,涉及深度学习技术领域,包括:获取目标交通场景对应的监控视频;对所述监控视频进行特征提取,得到目标图像特征;所述目标图像特征包括RGB图全局特征、RGB图局部特征、深度图全局特征和深度图局部特征;利用协同注意力机制获取所述目标图像特征中不同特征之间的关联信息,并基于所述关联信息将所述目标图像特征中的各个特征进行融合,得到目标融合特征;将所述目标融合特征输入至训练好的GRU网络模型,输出得到所述目标交通场景对应交通事故预测概率。通过协同注意力层的级联组合,以实现多特征的互补感知融合,进而利用GRU模块预测未来是否会发生交通事故,从而减少交通事故的发生。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic accident prediction method and device based on deep learning


    Weitere Titelangaben:

    一种基于深度学习的交通事故预测方法和装置


    Beteiligte:
    LIU WEI (Autor:in) / LI YAFEI (Autor:in) / GAO YIXIANG (Autor:in) / ZHANG TAO (Autor:in) / WEI LONGSHENG (Autor:in)

    Erscheinungsdatum :

    10.12.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06V / 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



    Road traffic accident risk prediction deep learning algorithm

    YU ZHIQING / YAO HUI / LI KUN et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Traffic accident severity prediction based on interpretable deep learning model

    Pei, Yulong / Wen, Yuhang / Pan, Sheng | Taylor & Francis Verlag | 2025


    Towards Deep Learning based Traffic Accident Analysis

    Naseer, Atif / Nour, Mohamed K. / Alkazemi, Basem Y. | IEEE | 2020


    Training method of traffic accident prediction model and traffic accident prediction method and device

    WANG NIANMING / CHEN YANG / ZHOU MINGKE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Multisource Accident Datasets-Driven Deep Learning-Based Traffic Accident Portrait for Accident Reasoning

    Chun-Hao Wang / Yue-Tian-Si Ji / Li Ruan et al. | DOAJ | 2024

    Freier Zugriff