Template based Human Pose and Shape Estimation from a Single RGB-D Image

Zhongguo Li, Anders Heyden, Magnus Oskarsson

2019

Abstract

Estimating the 3D model of the human body is needed for many applications. However, this is a challenging problem since the human body inherently has a high complexity due to self-occlusions and articulation. We present a method to reconstruct the 3D human body model from a single RGB-D image. 2D joint points are firstly predicted by a CNN-based model called convolutional pose machine, and the 3D joint points are calculated using the depth image. Then, we propose to utilize both 2D and 3D joint points, which provide more information, to fit a parametric body model (SMPL). This is implemented through minimizing an objective function, which measures the difference of the joint points between the observed model and the parametric model. The pose and shape parameters of the body are obtained through optimization and the final 3D model is estimated. The experiments on synthetic data and real data demonstrate that our method can estimate the 3D human body model correctly.

Paper Citation

in Harvard Style

Li Z., Heyden A. and Oskarsson M. (2019). Template based Human Pose and Shape Estimation from a Single RGB-D Image.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 574-581. DOI: 10.5220/0007383605740581

in Bibtex Style

@conference{icpram19,
author={Zhongguo Li and Anders Heyden and Magnus Oskarsson},
title={Template based Human Pose and Shape Estimation from a Single RGB-D Image},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={574-581},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007383605740581},
isbn={978-989-758-351-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Template based Human Pose and Shape Estimation from a Single RGB-D Image
SN - 978-989-758-351-3
AU - Li Z.
AU - Heyden A.
AU - Oskarsson M.
PY - 2019
SP - 574
EP - 581
DO - 10.5220/0007383605740581