※ 기관로그인 시 무료 이용이 가능합니다.
※ 학술발표대회집, 워크숍 자료집 중 4페이지 이내 논문은 '요약'만 제공되는 경우가 있으니, 구매 전에 간행물명, 페이지 수 확인 부탁 드립니다.
3,000원
원문정보
초록
영어
We propose a method for recognizing gestures from a specific user in multi-user environments. Previous studies require expensive equipment or demand users to become familiar with specialized devices, which poses practical limitations. We utilize OpenCv to detect a specific marker and employs MediaPipe’s real-time hand tracking to recognize only the hand with the detected marker. This method reduces malfunction rates. In multi-user experiments, the system reduced misrecognition of unintended user’s gestures by more than 90%, enabling highly reliable and user-specific gesture recognition. In simultaneous tests with hands both with without the marker, only the hand bearing the marker was accurately recognized, confirming the effectiveness of the proposed system.
목차
Abstract 1. 서론 2. 시스템 모델 2.1 방법론 2.2 시스템 아키텍처 3. 결과 4. 결론 Acknowledgement References