eprintid: 3213
rev_number: 7
eprint_status: archive
userid: 305
dir: disk0/00/00/32/13
datestamp: 2018-12-12 03:11:32
lastmod: 2018-12-12 03:11:32
status_changed: 2018-12-12 03:11:32
type: article
metadata_visibility: show
creators_name: Nguyen, Xuan Thanh
creators_name: Ngo, Thi Duyen
creators_name: Le, Thanh Ha
creators_id: duyennt@vnu.edu.vn
creators_id: ltha@vnu.edu.vn
title: A Spatial-temporal 3D Human Pose   Reconstruction Framework
ispublished: submitted
subjects: IT
divisions: fac_fit
abstract: 3D human pose reconstruction from single-view camera is a difficult and challenging topic. Many approaches have been proposed, but almost focus on frame-by-frame independently while inter-frames are highly correlated in a pose sequence. In contrast, we introduce a novel spatial-temporal 3D reconstruction framework that leverages both intra and inter frame relationships in consecutive 2D pose sequences. Orthogonal Matching Pursuit (OMP) algorithm, pre-trained Pose-angle Limits and Temporal Models have been implemented. We quantitatively compare our framework with recent works on CMU motion capture dataset and Vietnamese traditional dance sequences. Our method outperforms others with 10 percent lower of Euclidean reconstruction error and robustness against Gaussian noise. Additionally, it is also important to mention that our reconstructed 3D pose sequences are smoother and more natural than others
date: 2018
date_type: submitted
publisher: KIPS
full_text_status: none
publication: Journal of Information Processing Systems
refereed: TRUE
issn: 1976-913X
citation:   Nguyen, Xuan Thanh and Ngo, Thi Duyen and Le, Thanh Ha  (2018) A Spatial-temporal 3D Human Pose Reconstruction Framework.  Journal of Information Processing Systems .    ISSN 1976-913X    (Submitted)