ACCIDENT PREDICTION DEVICE FOR PREVENTING TRAFFIC ACCIDENTS BY PREDICTING ACCIDENTS BY ASCERTAINING ROAD CONDITIONS INCLUDING BLACK ICE, POTHOLES, AND FOG IN MACHINE-LEARNING EDGE SERVER ENVIRONMENT, AND CONTROL METHOD THEREOF

An accident prediction device according to the present invention comprises a communication unit which receives public data and personal data, and a processor which: uses a machine-learning model to analyze a road image included in at least one of the public data or the personal data; ascertains road...

Full description

Saved in:
Bibliographic Details
Main Authors KIM, Jin Sul, LEE, Dong Su, OH, Seung Min, AKM, Ashiquzzaman, KIM, Yeong Gwang
Format Patent
LanguageEnglish
French
Korean
Published 23.06.2022
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:An accident prediction device according to the present invention comprises a communication unit which receives public data and personal data, and a processor which: uses a machine-learning model to analyze a road image included in at least one of the public data or the personal data; ascertains road conditions on the basis of the analyzed road image; predicts the probability of an accident occurring on the basis of the ascertained road conditions; generates information related to the probability of an accident occurring on the basis of the predicted probability of an accident occurring; transmits at least one of a new dangerous area list or the information related to the probability of an accident occurring to a manager device through the communication unit; and transmits the information related to the probability of an accident occurring to a user device through the communication unit. Un dispositif de prédiction d'accident selon la présente invention comprend une unité de communication qui reçoit des données publiques et des données personnelles, et un processeur qui : utilise un modèle d'apprentissage automatique pour analyser une image de route incluse dans les données publiques et/ou les données personnelles ; identifie des conditions routières sur la base de l'image de route analysée ; prédit la probabilité de survenue d'un accident sur la base des conditions routières déterminées ; génère des informations relatives à la probabilité de survenue d'un accident sur la base de la probabilité prédite de survenue d'un accident ; transmet une nouvelle liste de zones dangereuses et/ou les informations relatives à la probabilité de survenue d'un accident à un dispositif gestionnaire par l'intermédiaire de l'unité de communication ; et transmet les informations relatives à la probabilité de survenue d'un accident à un dispositif utilisateur par l'intermédiaire de l'unité de communication. 본 발명은 사고발생 예측 장치에 있어서, 공공 데이터 및 개인 데이터를 수신하는 통신부; 및 기계학습 모델을 이용하여, 상기 공공 데이터 및 상기 개인 데이터 중 적어도 하나에 포함된 도로 영상을 분석하고, 상기 분석된 도로 영상에 기초하여 도로 상태를 파악하고, 상기 파악된 도로 상태에 기초하여 사고발생 가능성을 예측하고, 상기 예측된 사고발생 가능성에 기초하여 상기 사고발생 가능성 관련 정보를 생성하고, 관리자 장치로 신규 위험지역 리스트 및 상기 사고발생 가능성 관련 정보 중 적어도 하나를 상기 통신부를 통해 송신하고, 사용자 장치로 상기 사고발생 가능성 관련 정보를 상기 통신부를 통해 송신하는 프로세서를 포함한다.
Bibliography:Application Number: WO2021KR00962