The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kinect를 이용한 자세 인식의 복잡성을 목표로 거리 특성을 이용한 자세 인식 방법을 제안한다. 먼저, Kinect를 통해 깊이 영상 데이터를 수집하고, 20개 골격 관절의 60차원 좌표 정보를 획득하였다. 둘째, 관절의 자세 표현 기여도에 따라 24차원 Kinect 골격 관절 데이터를 인체 구조에 따라 정규화한 95.9차원 거리 특성 벡터로 변환하였다. 셋째, DTW(Dynamic Time Warping)를 이용한 최단 거리의 정적 자세 인식 방법과 최소 누적 거리의 동적 자세 인식 방법을 제안하였다. 실험 결과, 정적 자세, 비교차적 동적 자세, 교차적 동적 자세의 인식률은 각각 93.6%, 89.8%, XNUMX%인 것으로 나타났다. 마지막으로 자세 선택, Kinect 배치, 문헌과의 비교 등을 논의하여 Kinect 기반 자세 인식 기술 및 인터랙션 디자인에 대한 참고자료를 제공하였다.
Yan LI
Shenyang Sport University
Zhijie CHU
Shenyang University of Technology
Yizhong XIN
Shenyang University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Yan LI, Zhijie CHU, Yizhong XIN, "Posture Recognition Technology Based on Kinect" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 3, pp. 621-630, March 2020, doi: 10.1587/transinf.2019EDP7221.
Abstract: Aiming at the complexity of posture recognition with Kinect, a method of posture recognition using distance characteristics is proposed. Firstly, depth image data was collected by Kinect, and three-dimensional coordinate information of 20 skeleton joints was obtained. Secondly, according to the contribution of joints to posture expression, 60 dimensional Kinect skeleton joint data was transformed into a vector of 24-dimensional distance characteristics which were normalized according to the human body structure. Thirdly, a static posture recognition method of the shortest distance and a dynamic posture recognition method of the minimum accumulative distance with dynamic time warping (DTW) were proposed. The experimental results showed that the recognition rates of static postures, non-cross-subject dynamic postures and cross-subject dynamic postures were 95.9%, 93.6% and 89.8% respectively. Finally, posture selection, Kinect placement, and comparisons with literatures were discussed, which provides a reference for Kinect based posture recognition technology and interaction design.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7221/_p
부
@ARTICLE{e103-d_3_621,
author={Yan LI, Zhijie CHU, Yizhong XIN, },
journal={IEICE TRANSACTIONS on Information},
title={Posture Recognition Technology Based on Kinect},
year={2020},
volume={E103-D},
number={3},
pages={621-630},
abstract={Aiming at the complexity of posture recognition with Kinect, a method of posture recognition using distance characteristics is proposed. Firstly, depth image data was collected by Kinect, and three-dimensional coordinate information of 20 skeleton joints was obtained. Secondly, according to the contribution of joints to posture expression, 60 dimensional Kinect skeleton joint data was transformed into a vector of 24-dimensional distance characteristics which were normalized according to the human body structure. Thirdly, a static posture recognition method of the shortest distance and a dynamic posture recognition method of the minimum accumulative distance with dynamic time warping (DTW) were proposed. The experimental results showed that the recognition rates of static postures, non-cross-subject dynamic postures and cross-subject dynamic postures were 95.9%, 93.6% and 89.8% respectively. Finally, posture selection, Kinect placement, and comparisons with literatures were discussed, which provides a reference for Kinect based posture recognition technology and interaction design.},
keywords={},
doi={10.1587/transinf.2019EDP7221},
ISSN={1745-1361},
month={March},}
부
TY - JOUR
TI - Posture Recognition Technology Based on Kinect
T2 - IEICE TRANSACTIONS on Information
SP - 621
EP - 630
AU - Yan LI
AU - Zhijie CHU
AU - Yizhong XIN
PY - 2020
DO - 10.1587/transinf.2019EDP7221
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2020
AB - Aiming at the complexity of posture recognition with Kinect, a method of posture recognition using distance characteristics is proposed. Firstly, depth image data was collected by Kinect, and three-dimensional coordinate information of 20 skeleton joints was obtained. Secondly, according to the contribution of joints to posture expression, 60 dimensional Kinect skeleton joint data was transformed into a vector of 24-dimensional distance characteristics which were normalized according to the human body structure. Thirdly, a static posture recognition method of the shortest distance and a dynamic posture recognition method of the minimum accumulative distance with dynamic time warping (DTW) were proposed. The experimental results showed that the recognition rates of static postures, non-cross-subject dynamic postures and cross-subject dynamic postures were 95.9%, 93.6% and 89.8% respectively. Finally, posture selection, Kinect placement, and comparisons with literatures were discussed, which provides a reference for Kinect based posture recognition technology and interaction design.
ER -