Details
| Original language | English |
|---|---|
| Pages (from-to) | 557-577 |
| Number of pages | 21 |
| Journal | Machine Vision and Applications |
| Volume | 23 |
| Issue number | 3 |
| Publication status | Published - 29 Jan 2011 |
Abstract
Despite great progress achieved in 3-D pose tracking during the past years, occlusions and self-occlusions are still an open issue. This is particularly true in sil-houette-based tracking where even visible parts cannot be tracked as long as they do not affect the object silhouette. Multiple cameras or motion priors can overcome this problem. However, multiple cameras or appropriate training data are not always readily available. We propose a framework in which the pose of 3-D models is found by minimising the 2-D projection error through minimisation of an energy function depending on the pose parameters. This framework makes it possible to handle occlusions and self-occlusions by tracking multiple objects and object parts simultaneously. Therefore, each part is described by its own image region each of which is modeled by one probability density function. This allows to deal with occlusions explicitly, which includes self-occlusions between different parts of the same object as well as occlusions between different objects. The results we present for simulations and real-world scenes demonstrate the improvements achieved in monocular and multi-camera settings. These improvements are substantiated by quantitative evaluations, e.g. based on the HumanEVA benchmark.
Keywords
- Computer vision, Human motion analysis, Kinematic chain, Model-based tracking, Occlusion handling, Pose estimation
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Hardware and Architecture
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Machine Vision and Applications, Vol. 23, No. 3, 29.01.2011, p. 557-577.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Region-based pose tracking with occlusions using 3D models
AU - Schmaltz, Christian
AU - Rosenhahn, Bodo
AU - Brox, Thomas
AU - Weickert, Joachim
N1 - Funding information: We gratefully acknowledge funding by the German Research Foundation (DFG) under the project We 2602/5-2.
PY - 2011/1/29
Y1 - 2011/1/29
N2 - Despite great progress achieved in 3-D pose tracking during the past years, occlusions and self-occlusions are still an open issue. This is particularly true in sil-houette-based tracking where even visible parts cannot be tracked as long as they do not affect the object silhouette. Multiple cameras or motion priors can overcome this problem. However, multiple cameras or appropriate training data are not always readily available. We propose a framework in which the pose of 3-D models is found by minimising the 2-D projection error through minimisation of an energy function depending on the pose parameters. This framework makes it possible to handle occlusions and self-occlusions by tracking multiple objects and object parts simultaneously. Therefore, each part is described by its own image region each of which is modeled by one probability density function. This allows to deal with occlusions explicitly, which includes self-occlusions between different parts of the same object as well as occlusions between different objects. The results we present for simulations and real-world scenes demonstrate the improvements achieved in monocular and multi-camera settings. These improvements are substantiated by quantitative evaluations, e.g. based on the HumanEVA benchmark.
AB - Despite great progress achieved in 3-D pose tracking during the past years, occlusions and self-occlusions are still an open issue. This is particularly true in sil-houette-based tracking where even visible parts cannot be tracked as long as they do not affect the object silhouette. Multiple cameras or motion priors can overcome this problem. However, multiple cameras or appropriate training data are not always readily available. We propose a framework in which the pose of 3-D models is found by minimising the 2-D projection error through minimisation of an energy function depending on the pose parameters. This framework makes it possible to handle occlusions and self-occlusions by tracking multiple objects and object parts simultaneously. Therefore, each part is described by its own image region each of which is modeled by one probability density function. This allows to deal with occlusions explicitly, which includes self-occlusions between different parts of the same object as well as occlusions between different objects. The results we present for simulations and real-world scenes demonstrate the improvements achieved in monocular and multi-camera settings. These improvements are substantiated by quantitative evaluations, e.g. based on the HumanEVA benchmark.
KW - Computer vision
KW - Human motion analysis
KW - Kinematic chain
KW - Model-based tracking
KW - Occlusion handling
KW - Pose estimation
UR - http://www.scopus.com/inward/record.url?scp=84861698093&partnerID=8YFLogxK
U2 - 10.1007/s00138-010-0317-5
DO - 10.1007/s00138-010-0317-5
M3 - Article
AN - SCOPUS:84861698093
VL - 23
SP - 557
EP - 577
JO - Machine Vision and Applications
JF - Machine Vision and Applications
SN - 0932-8092
IS - 3
ER -