ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Basketball Event Recognition Technique using Deterministic Finite Automata (DFA)
Cited 12 time in scopus Download 1 time Share share facebook twitter linkedin kakaostory
저자
이정수, 이지원, 문성원, 남도원, 유원영
발행일
201802
출처
International Conference on Advanced Communications Technology (ICACT) 2018, pp.675-678
DOI
https://dx.doi.org/10.23919/ICACT.2018.8323880
협약과제
17CS1200, 스포츠 영상 콘텐츠의 내용 이해 기반 분석/요약/검색 기술 개발, 남도원
초록
Recently, many researchers and sport managers are trying to analyse the movement of sports players by combining sports and ICT technology, and to change the contents of the game using these analysis results. In the case of basketball, leading companies such as STATS Sports are focusing on tracking the players and analysing the players' movements. However, the recording of sports events such as shoot, foul, and rebound resulting from the players' movements is made entirely by the manual work of the recorders. In this paper, we propose a technique to automatically extract events generated by players or judges in basketball games. Experiments have shown that it is possible to automatically extract events by tracking players and referees and analysing the predefined motion of players and referees.
KSP 제안 키워드
Deterministic finite automata, Event recognition, Manual work, Sports events, recognition technique