To extend a prediction target area to predict a degree of a collision injury in the event of a collision accident to a vehicle which is not mounted with an accident automatic notification device and a vulnerable road user.SOLUTION: A collision injury prediction method which predicts a degree of collision injury to an injury object person in the event of a collision accident comprises the following processes to: acquire external sensor data including external image data recorded before and after a traffic accident from a vehicle exterior sensor 10 mounted on a vehicle other than the vehicle of a person involved in the traffic accident after occurrence thereof; detect occurrence of the collision accident by inputting the external sensor data into a collision detection model M0 created through the execution of deep learning: predict a degree of collision injury of the injury object person by inputting the external sensor data into a first injury prediction model M1 created through the execution of the deep learning when detecting the occurrence of the collision accident; and obtain and output a determination level of the collision injury from the degree of the collision injury.SELECTED DRAWING: Figure 5

    【課題】衝突事故発生時において、衝突傷害程度を予測する予測対象範囲を、事故自動通報装置を備えていない車両や交通弱者にまで拡大すること。【解決手段】衝突事故発生時に受傷対象者の衝突傷害程度を予測する衝突傷害予測方法であって、下記の手順を有する。事故当事者の車両に搭載されていない車両外部センサー10から、交通事故発生の後、交通事故発生前後において記録されていた外部画像データを含む外部センサーデータを取得する。外部センサーデータを、深層学習の実施により作成された衝突検知モデルM0に入力することで衝突事故発生の有無を検知する。衝突事故発生が検知されると、外部センサーデータを、深層学習の実施により作成された第1傷害予測モデルM1に入力することで受傷対象者の衝突傷害程度を予測する。衝突傷害程度から衝突傷害の判定レベルを求め、判定レベルを出力する。【選択図】図5


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    COLLISION INJURY PREDICTION METHOD, COLLISION INJURY PREDICTION SYSTEM AND ADVANCED ACCIDENT AUTOMATIC NOTIFICATION SYSTEM


    Weitere Titelangaben:

    衝突傷害予測方法、衝突傷害予測システム及び先進事故自動通報システム


    Beteiligte:
    KUNITOMI SHOHEI (Autor:in) / TAKAYAMA SHINICHI (Autor:in) / ARAI YUJI (Autor:in)

    Erscheinungsdatum :

    06.09.2022


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Japanisch


    Klassifikation :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / H04N PICTORIAL COMMUNICATION, e.g. TELEVISION , Bildübertragung, z.B. Fernsehen / B60R Fahrzeuge, Fahrzeugausstattung oder Fahrzeugteile, soweit nicht anderweitig vorgesehen , VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G16Y




    Injury Prediction Model for Automatic Collision Notification Based on Japanese Accident Data

    Yoshida, S. / Hasegawa, T. / Tominaga, S. et al. | British Library Online Contents | 2012


    Development of injury prediction models for advanced automatic collision notification based on Japanese accident data

    Yoshida, S. / Hasegawa, T. / Tominaga, S. et al. | Taylor & Francis Verlag | 2016


    Injury Severity Prediction Algorithm Based on Select Vehicle Category for Advanced Automatic Collision Notification

    Ejima, Susumu / Goto, Tsukasa / Zhang, Peng et al. | British Library Conference Proceedings | 2022


    Injury Severity Prediction Algorithm Based on Select Vehicle Category for Advanced Automatic Collision Notification

    Ejima, Susumu / Goto, Tsukasa / Zhang, Peng et al. | British Library Conference Proceedings | 2022