The present embodiment relates to a sound-based road accident automatic-detection system using accident sound deep learning. In accordance with one aspect, the sound-based road accident automatic-detection system using accident sound deep learning includes: a sound collection unit collecting sound information on a road; an accident analysis unit determining whether an accident occurs on the road through the sound information; and an accident handling unit providing a handling solution based on the information determined by the accident analysis unit. The accident handling unit includes: DBSAVE storing the sound information in a database per minute; StreamGW delivering real-time sound information; and ADSS detecting the accident by analyzing the sound information, wherein an accident analysis algorithm in the ADSS is formed through a convolution neural network (CNN) or a recurrent neural network (RNN). Therefore, the present invention is capable of more quickly and more accurately identifying and handling an accident on a road.

    본 실시예는 사고음 딥러닝을 통한 음향기반 도로 사고 자동 검지 시스템에 관한 것이다. 일 측면에 따른 사고음 딥러닝을 통한 음향기반 도로 사고 자동 검지 시스템은, 도로 상의 음향 정보를 수집하는 음향수집부; 상기 음향 정보를 통해 도로 상의 사고 여부를 판별하는 사고분석부; 및 상기 사고분석부에서 판별된 정보에 기포하여, 처리 방안을 제공하는 사고처리부를 포함하며, 상기 사고처리부는, 상기 음향 정보를 1분 단위로 데이터 베이스에 저장하는 DBSAVE; 실시간 음향 정보를 전달하는 StreamGW; 및 상기 음향 정보를 분석하여 사고를 감지하는 ADSS를 포함하며, 상기 ADSS 내 사고 분석 알고리즘은 CNN(Convolution Neural Network) 또는 RNN(Recurrent Neural Network)을 통해 이루어진다.


    Access

    Download


    Export, share and cite



    Title :

    Acoustic accident detection system through accident sound deep learning


    Additional title:

    사고음 딥러닝을 통한 음향기반 도로 사고 자동 검지 시스템


    Contributors:

    Publication date :

    2022-12-07


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Korean


    Classification :

    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



    Acoustic accident detection system through accident sound deep learning

    KIM KYU HYUN | European Patent Office | 2022

    Free access

    Accident Detection Using Deep Learning

    Yadav, Durgesh Kumar / Renu / Ankita et al. | IEEE | 2020


    Acoustic Tunnel Accident Detection System

    KIM HONG KOOK / KWAK CHAN WOONG / KIM NAM KYUN et al. | European Patent Office | 2019

    Free access

    Acoustic Tunnel Accident Detection System

    European Patent Office | 2020

    Free access

    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

    Free access