Details
| Original language | English |
|---|---|
| Title of host publication | 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 |
| Publisher | IEEE Computer Society |
| Pages | 1-8 |
| Number of pages | 8 |
| ISBN (electronic) | 9781467367592 |
| Publication status | Published - 19 Oct 2015 |
| Event | IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015 |
Publication series
| Name | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
|---|---|
| Volume | 2015-October |
| ISSN (Print) | 2160-7508 |
| ISSN (electronic) | 2160-7516 |
Abstract
This paper 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 our 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. 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
- Bones, Cameras, Databases, Image sequences, Legged locomotion, Shape, Three-dimensional displays
ASJC Scopus subject areas
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015. IEEE Computer Society, 2015. p. 1-8 7301286 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2015-October).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - 3D human motion capture from monocular image sequences
AU - Wandt, Bastian
AU - Ackermann, Hanno
AU - Rosenhahn, Bodo
PY - 2015/10/19
Y1 - 2015/10/19
N2 - This paper 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 our 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. 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 paper 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 our 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. 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 - Bones
KW - Cameras
KW - Databases
KW - Image sequences
KW - Legged locomotion
KW - Shape
KW - Three-dimensional displays
UR - http://www.scopus.com/inward/record.url?scp=84952049979&partnerID=8YFLogxK
U2 - 10.1109/cvprw.2015.7301286
DO - 10.1109/cvprw.2015.7301286
M3 - Conference contribution
AN - SCOPUS:84952049979
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 1
EP - 8
BT - 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
PB - IEEE Computer Society
T2 - IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
Y2 - 7 June 2015 through 12 June 2015
ER -