ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper 3차원 합성곱 신경망을 통한 축구 객체 모션 인식 기법
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
이지원, 김윤형, 남도원, 유원영
Issue Date
2018-06
Citation
대한전자공학회 학술 대회 (하계) 2018, pp.528-531
Publisher
대한전자공학회
Language
Korean
Type
Conference Paper
Abstract
Recently, sports and ICT technology have been combined, enabling quantitative and objective analysis of sports and players. As a result, in the case of soccer game, quantitative analysis of competition and athletes is underway in various companies, but due to technical limitations, many data are still being generated based on the manual work of experts. In this paper, we propose an object motion recognition technique based on 3D CNN which is a basis for further automation of soccer analysis. As can be seen from the experimental results, it can be confirmed that the proposed technique not only has high speed performance but also satisfactory accuracy as compared with the existing technologies.
KSP Keywords
3D CNN, High Speed, Manual work, Motion Recognition, Object motion, Objective analysis, Quantitative analysis, Soccer Analysis, recognition technique, speed performance