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
(Woosong University) (Woosong University) (MOPC-FEPASA)
저널정보
한국철도학회 한국철도학회 논문집 한국철도학회 논문집 제28권 제10호(통권 제196호)
오류 신고하기

피인용 0

검색

    초록·키워드

    This paper explores the feasibility of drone flights integrated with computer vision technology for object detection on railway tracks and, thus, aims overall to enhance the workflow required for monitoring tasks. The conceptual model relies on employing existing technology in tracking railway lines for semi-autonomous navigation and artificial intelligence for visual identification. This was demonstrated by a stepwise operation of a drone flight via a navigation algorithm and visual data processing procedure via a machine learning model trained by a manually created supervision library. Experimentation flights showed navigation following railway tracks, executed at 70% for routes of short distances of 100 m or less, and object detection performed at various levels of confidence. The study carried out here highlights the feasibility of such integration and provides a basis for practical implementation.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-26-02-094367409