A Spatial-temporal 3D Human Pose Reconstruction Framework

Xuan Thanh Nguyen, Thi Duyen Ngo and Thanh Ha Le
Volume: 15, No: 2, Page: 399 ~ 409, Year: 2019
10.3745/JIPS.02.0110
Keywords: 3D Human Pose, Reconstruction, Spatial-Temporal Model
Full Text:

Abstract
Three-dimensional (3D) human pose reconstruction from single-view image is a difficult and challenging topic. Existing approaches mostly process frame-by-frame independently while inter-frames are highly correlated in a sequence. In contrast, we introduce a novel spatial-temporal 3D human pose 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. Several quantitative comparisons between our proposed framework and recent works have been studied on CMU motion capture dataset and Vietnamese traditional dance sequences. Our framework outperforms others by 10% lower of Euclidean reconstruction error and more robust against Gaussian noise. Additionally, it is also important to mention that our reconstructed 3D pose sequences are more natural and smoother than others.

Article Statistics
Multiple requests among the same broswer session are counted as one view (or download).
If you mouse over a chart, a box will show the data point's value.


Cite this article
IEEE Style
X. T. Nguyen, T. D. Ngo and T. H. Le, "A Spatial-temporal 3D Human Pose Reconstruction Framework," Journal of Information Processing Systems, vol. 15, no. 2, pp. 399~409, 2019. DOI: 10.3745/JIPS.02.0110.

ACM Style
Xuan Thanh Nguyen, Thi Duyen Ngo, and Thanh Ha Le. 2019. A Spatial-temporal 3D Human Pose Reconstruction Framework, Journal of Information Processing Systems, 15, 2, (2019), 399~409. DOI: 10.3745/JIPS.02.0110.