The present invention relates to a method for monitoring a freezing-prone and slippery area. The method includes: a step in which a data processing unit generates a multi-channel image vector by embedding a LiDAR image obtained by a LiDAR sensor scanning a monitoring region, an infrared filter image obtained by an infrared filter camera imaging the monitoring region, and a thermal infrared image obtained by a thermal infrared camera imaging the monitoring region; a step in which a detection unit inputs the multi-channel image vector to a detection model; a step in which the detection model performs calculations to which interlayer learned weights are applied with respect to the multi-channel image vector and outputs the probability of existence of a section box specifying a region where freezing is estimated and freezing in the region specified by the section box; and a step in which the detection unit recognizes freezing occurrence and transmits a freezing occurrence notification message when the probability is equal to or higher than a preset threshold.

    본 발명의 상습 결빙 및 미끄러움 위험 지역 모니터링을 위한 방법은 데이터처리부가 모니터링 영역을 라이다센서를 통해 스캔한 라이다 영상, 상기 모니터링 영역을 적외선필터카메라로 촬영한 적외선필터 영상, 상기 모니터링 영역을 열적외선 카메라로 촬영한 열적외선 영상을 임베딩하여 멀티채널영상벡터를 생성하는 단계와, 검출부가 상기 멀티채널영상벡터를 검출모델에 입력하는 단계와, 상기 검출모델이 상기 멀티채널영상벡터에 대해 복수의 계층 간 학습된 가중치가 적용되는 복수의 연산을 수행하여 결빙 발생이 추정되는 영역을 특정하는 구획박스 및 상기 구획박스가 특정하는 영역에 결빙이 존재할 확률을 출력하는 단계와, 상기 확률이 기 설정된 임계치 이상이면, 상기 검출부가 결빙이 발생한 것으로 인식하고, 결빙 발생을 알리는 메시지를 전송하는 단계를 포함한다.


    Access

    Download


    Export, share and cite



    Title :

    Apparatus for monitoring habitual freezing and slippery areas using deep learning model and method therefor


    Additional title:

    심층학습 모델을 이용한 상습 결빙 및 미끄러움 위험 지역 모니터링을 위한 장치 및 이를 위한 방법


    Contributors:
    JI TAEK SOO (author) / KIM JIN SUL (author) / KIM CHI HUN (author) / JANG JAE HYEOK (author)

    Publication date :

    2021-08-09


    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 / G01S RADIO DIRECTION-FINDING , Funkpeilung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / H04N PICTORIAL COMMUNICATION, e.g. TELEVISION , Bildübertragung, z.B. Fernsehen



    DEVICE FOR MONITORING AREA PRONE TO FREEZING AND RISK OF SLIPPAGE USING DEEP LEARNING MODEL, AND METHOD THEREFOR

    JI TAEK SOO / KIM JIN SUL / KIM CHI HUN et al. | European Patent Office | 2022

    Free access

    APPARATUS FOR CALCULATING HABITUAL SHADED AREAS ACCORDING TO ROAD FACILITIES

    YI CHAEYEON / KWON HYUKGI / YANG HOJIN et al. | European Patent Office | 2022

    Free access

    VehSense: Slippery Road Detection Using Smartphones

    Hou, Yunfei / Gupta, Abhishek / Guan, Tong et al. | ArXiv | 2017

    Free access

    VehSense: Slippery Road Detection Using Smartphones

    Hou, Yunfei / Gupta, Abhishek / Guan, Tong et al. | IEEE | 2017