Details
| Original language | English |
|---|---|
| Article number | 7451280 |
| Pages (from-to) | 1505-1516 |
| Number of pages | 12 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | 38 |
| Issue number | 8 |
| Publication status | Published - 1 Aug 2016 |
Abstract
This article tackles the problem of estimating non-rigid human 3D shape and motion from image sequences taken by uncalibrated cameras. Similar to other state-of-the-art solutions we factorize 2D observations in camera parameters, base poses and mixing coefficients. Existing methods require sufficient camera motion during the sequence to achieve a correct 3D reconstruction. To obtain convincing 3D reconstructions from arbitrary camera motion, our method is based on a-priorly trained base poses. We show that strong periodic assumptions on the coefficients can be used to define an efficient and accurate algorithm for estimating periodic motion such as walking patterns. For the extension to non-periodic motion we propose a novel regularization term based on temporal bone length constancy. In contrast to other works, the proposed method does not use a predefined skeleton or anthropometric constraints and can handle arbitrary camera motion. We achieve convincing 3D reconstructions, even under the influence of noise and occlusions. Multiple experiments based on a 3D error metric demonstrate the stability of the proposed method. Compared to other state-of-the-art methods our algorithm shows a significant improvement.
Keywords
- 3D reconstruction, factorization, Human motion, structure and motion
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Artificial Intelligence
- Mathematics(all)
- Applied Mathematics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 38, No. 8, 7451280, 01.08.2016, p. 1505-1516.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - 3D Reconstruction of human motion from monocular image sequences
AU - Wandt, Bastian
AU - Ackermann, Hanno
AU - Rosenhahn, Bodo
N1 - Funding information: The work has been partially supported by the ERC-Starting Grant (Dynamic MinVIP) and the DFG-project RO 2497/11-1. The authors gratefully acknowledge the support.
PY - 2016/8/1
Y1 - 2016/8/1
N2 - This article tackles the problem of estimating non-rigid human 3D shape and motion from image sequences taken by uncalibrated cameras. Similar to other state-of-the-art solutions we factorize 2D observations in camera parameters, base poses and mixing coefficients. Existing methods require sufficient camera motion during the sequence to achieve a correct 3D reconstruction. To obtain convincing 3D reconstructions from arbitrary camera motion, our method is based on a-priorly trained base poses. We show that strong periodic assumptions on the coefficients can be used to define an efficient and accurate algorithm for estimating periodic motion such as walking patterns. For the extension to non-periodic motion we propose a novel regularization term based on temporal bone length constancy. In contrast to other works, the proposed method does not use a predefined skeleton or anthropometric constraints and can handle arbitrary camera motion. We achieve convincing 3D reconstructions, even under the influence of noise and occlusions. Multiple experiments based on a 3D error metric demonstrate the stability of the proposed method. Compared to other state-of-the-art methods our algorithm shows a significant improvement.
AB - This article tackles the problem of estimating non-rigid human 3D shape and motion from image sequences taken by uncalibrated cameras. Similar to other state-of-the-art solutions we factorize 2D observations in camera parameters, base poses and mixing coefficients. Existing methods require sufficient camera motion during the sequence to achieve a correct 3D reconstruction. To obtain convincing 3D reconstructions from arbitrary camera motion, our method is based on a-priorly trained base poses. We show that strong periodic assumptions on the coefficients can be used to define an efficient and accurate algorithm for estimating periodic motion such as walking patterns. For the extension to non-periodic motion we propose a novel regularization term based on temporal bone length constancy. In contrast to other works, the proposed method does not use a predefined skeleton or anthropometric constraints and can handle arbitrary camera motion. We achieve convincing 3D reconstructions, even under the influence of noise and occlusions. Multiple experiments based on a 3D error metric demonstrate the stability of the proposed method. Compared to other state-of-the-art methods our algorithm shows a significant improvement.
KW - 3D reconstruction
KW - factorization
KW - Human motion
KW - structure and motion
UR - http://www.scopus.com/inward/record.url?scp=84978744027&partnerID=8YFLogxK
U2 - 10.1109/tpami.2016.2553028
DO - 10.1109/tpami.2016.2553028
M3 - Article
C2 - 27093439
AN - SCOPUS:84978744027
VL - 38
SP - 1505
EP - 1516
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 8
M1 - 7451280
ER -