ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Dynamic Pose EstimationUsingMultiple RGB-DCameras
Cited 18 time in scopus Download 106 time Share share facebook twitter linkedin kakaostory
저자
홍성진, 김예진
발행일
201811
출처
Sensors, v.18 no.11, pp.1-17
ISSN
1424-8220
출판사
MDPI AG
DOI
https://dx.doi.org/10.3390/s18113865
협약과제
18KS1200, 청소년용 실감 체험형 스포츠 통합플랫폼 기술 개발, 김명규
초록
Human poses are difficult to estimate due to the complicated body structure and the self-occlusion problem. In this paper, we introduce a marker-less system for human pose estimation by detecting and tracking key body parts, namely the head, hands, and feet. Given color and depth images captured by multiple red, green, blue, and depth (RGB-D) cameras, our system constructs a graph model with segmented regions from each camera and detects the key body parts as a set of extreme points based on accumulative geodesic distances in the graph. During the search process, local detection using a supervised learning model is utilized to match local body features. A final set of extreme points is selected with a voting scheme and tracked with physical constraints from the unified data received from the multiple cameras. During the tracking process, a Kalman filter-based method is introduced to reduce positional noises and to recover from a failure of tracking extremes. Our system shows an average of 87% accuracy against the commercial system, which outperforms the previous multi-Kinects system, and can be applied to recognize a human action or to synthesize a motion sequence from a few key poses using a small set of extremes as input data.
KSP 제안 키워드
Body Structure, Body features, Body parts, Depth image, Extreme points, Filter-based method, Geodesic distance, Graph model, Human Action, Human pose estimation, Learning model
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)