Details
| Original language | English |
|---|---|
| Pages (from-to) | 402-415 |
| Number of pages | 14 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | 32 |
| Issue number | 3 |
| Publication status | Published - Mar 2010 |
Abstract
In this paper, we propose the combined use of complementary concepts for 3D tracking: region fitting on one side and dense optical flow as well as tracked SIFT features on the other. Both concepts are chosen such that they can compensate for the shortcomings of each other. While tracking by the object region can prevent the accumulation of errors, optical flow and SIFT can handle larger transformations. Whereas segmentation works best in case of homogeneous objects, optical flow computation and SIFT tracking rely on sufficiently structured objects. We show that a sensible combination yields a general tracking system that can be applied in a large variety of scenarios without the need to manually adjust weighting parameters.
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. 32, No. 3, 03.2010, p. 402-415.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Combined region and motion-based 3D tracking of rigid and articulated objects.
AU - Brox, Thomas
AU - Rosenhahn, Bodo
AU - Gall, Juergen
AU - Cremers, Daniel
PY - 2010/3
Y1 - 2010/3
N2 - In this paper, we propose the combined use of complementary concepts for 3D tracking: region fitting on one side and dense optical flow as well as tracked SIFT features on the other. Both concepts are chosen such that they can compensate for the shortcomings of each other. While tracking by the object region can prevent the accumulation of errors, optical flow and SIFT can handle larger transformations. Whereas segmentation works best in case of homogeneous objects, optical flow computation and SIFT tracking rely on sufficiently structured objects. We show that a sensible combination yields a general tracking system that can be applied in a large variety of scenarios without the need to manually adjust weighting parameters.
AB - In this paper, we propose the combined use of complementary concepts for 3D tracking: region fitting on one side and dense optical flow as well as tracked SIFT features on the other. Both concepts are chosen such that they can compensate for the shortcomings of each other. While tracking by the object region can prevent the accumulation of errors, optical flow and SIFT can handle larger transformations. Whereas segmentation works best in case of homogeneous objects, optical flow computation and SIFT tracking rely on sufficiently structured objects. We show that a sensible combination yields a general tracking system that can be applied in a large variety of scenarios without the need to manually adjust weighting parameters.
UR - http://www.scopus.com/inward/record.url?scp=85028106911&partnerID=8YFLogxK
U2 - 10.1109/tpami.2009.32
DO - 10.1109/tpami.2009.32
M3 - Article
C2 - 20075468
AN - SCOPUS:85028106911
VL - 32
SP - 402
EP - 415
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 3
ER -