메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(이화여자대학교) (이화여자대학교) (이화여자대학교) (이화여자대학교)
저널정보
대한전자공학회 대한전자공학회 학술대회 2022년도 대한전자공학회 추계학술대회 논문집
오류 신고하기

피인용 0

검색

    초록·키워드

    The electric scooter-sharing service has experienced rapid growth with the limelight of personal mobility devices. However, there is a growing concern in society about increasing cases of e-scooter accidents. To address this problem, we propose a deep learning-based electric scooter safe driving system that considers both user images and road images. In our framework, we use CNN-based models to detect whether the user is using a helmet or keeping eyes forward using a user image. At the same time, we check whether the driver is riding on the road and then estimate the distance between the user and the closest pedestrian within a road image. Finally, we determine the final velocity of the e-scooter using the result value of each model. Through a fast and accurate deep learning model, we improve efficiency for real-time inference and achieve high confidence in the system by considering multiple dangers simultaneously.

    최근 본 자료 전체보기