ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Real-Time Tracking IDs and Joints of Users
Cited 0 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
백성민, 김명규
발행일
201812
출처
International Conference on Network, Communication and Computing (ICNCC) 2018, pp.221-226
DOI
https://dx.doi.org/10.1145/3301326.3301365
협약과제
18KS1200, 청소년용 실감 체험형 스포츠 통합플랫폼 기술 개발, 김명규
초록
This paper proposes a method of using multiple depth sensors vulnerable to joint occlusion and rotation to capture the dynamic motions of two users. The proposed method captures a series of multi-user motions by tracking user IDs, sorting out ID specific joints, and incorporating the joint movement data based on weighting. The ellipses accelerate the process of sorting out the depth data per user. Then, the sorted depth data add to the accuracy of joint positions for the adjustment of lower-limb joints. The proposed method enables an accurate restoration of 3D poses even in dynamic motions, and is applicable to experiential and training programs.
KSP 제안 키워드
Depth Data, Depth sensor, Dynamic motion, Lower limb, Movement data, Real-time Tracking, Training programs, joint movement, multi-user