Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Andreas Baak"'
Autor:
Christian Theobalt, Meinard Müller, Andreas Baak, Hans-Peter Seidel, Gaurav Bharaj, Thomas Helten
Publikováno v:
3DV
Reconstructing a three-dimensional representation of human motion in real-time constitutes an important research topic with applications in sports sciences, human-computer-interaction, and the movie industry. In this paper, we contribute with a robus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c985971eef6346dee55a32d93aef0f9b
https://doi.org/10.1109/3dv.2013.44
https://doi.org/10.1109/3dv.2013.44
Publikováno v:
Consumer Depth Cameras for Computer Vision ISBN: 9781447146391
ICCV
ICCV
In recent years, depth cameras have become a widely available sensor type that captures depth images at real-time frame rates. Even though recent approaches have shown that 3D pose estimation from monocular 2.5D depth images has become feasible, ther
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d8cad72f58829a26845c3719cd0a6e3e
https://doi.org/10.1007/978-1-4471-4640-7_5
https://doi.org/10.1007/978-1-4471-4640-7_5
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642449635
Time-of-Flight and Depth Imaging
Time-of-Flight and Depth Imaging
Optical capturing of human body motion has many practical applications, ranging from motion analysis in sports and medicine, over ergonomy research, up to computer animation in game and movie production. Unfortunately, many existing approaches requir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b39d24fc757abfbb148c2cdc1b86fe93
https://doi.org/10.1007/978-3-642-44964-2_9
https://doi.org/10.1007/978-3-642-44964-2_9
Autor:
Meinard Müller, Hans-Peter Seidel, Gerard Pons-Moll, Andreas Baak, Bodo Rosenhahn, Thomas Helten
Publikováno v:
Trends and Topics in Computer Vision ISBN: 9783642357480
ECCV Workshops (1)
ECCV Workshops (1)
In this paper, we introduce a novel framework for automatically evaluating the quality of 3D tracking results obtained from markerless motion capturing. In our approach, we use additional inertial sensors to generate suitable reference information. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b83f220f2fd23d66eb2db0225b92446f
https://doi.org/10.1007/978-3-642-35749-7_11
https://doi.org/10.1007/978-3-642-35749-7_11
Autor:
Juergen Gall, Hans-Peter Seidel, Gerard Pons-Moll, Andreas Baak, Laura Leal-Taixé, Bodo Rosenhahn, Meinard Müller
Publikováno v:
ICCV
Human motion capturing (HMC) from multiview image sequences is an extremely difficult problem due to depth and orientation ambiguities and the high dimensionality of the state space. In this paper, we introduce a novel hybrid HMC system that combines
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be20f0d8ad7d87423e11500f2d2cd52d
https://doi.org/10.1109/iccv.2011.6126375
https://doi.org/10.1109/iccv.2011.6126375
Autor:
Meinard Müller, Thomas Helten, Bodo Rosenhahn, Gerard Pons-Moll, Hans-Peter Seidel, Andreas Baak
Publikováno v:
CVPR
In this work, we present an approach to fuse video with orientation data obtained from extended inertial sensors to improve and stabilize full-body human motion capture. Even though video data is a strong cue for motion analysis, tracking artifacts o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aab0284ac551ec08af22f2581053146e
https://doi.org/10.1109/cvpr.2010.5540153
https://doi.org/10.1109/cvpr.2010.5540153
Publikováno v:
ICCV
In this paper, we introduce a novel iterative motion tracking framework that combines 3D tracking techniques with motion retrieval for stabilizing markerless human motion capturing. The basic idea is to start human tracking without prior knowledge ab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c9c9fcd32bbb4029b08ac018409c1f50
https://doi.org/10.1109/iccv.2009.5459291
https://doi.org/10.1109/iccv.2009.5459291
Publikováno v:
Symposium on Computer Animation
In view of increasing collections of available 3D motion capture (mocap) data, the task of automatically annotating large sets of unstructured motion data is gaining in importance. In this paper, we present an efficient approach to label mocap data a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::466a9ad993908879086ac1549653d1c1
https://doi.org/10.1145/1599470.1599473
https://doi.org/10.1145/1599470.1599473
Publikováno v:
Multimedia Information Retrieval
In the last years, various algorithms have been proposed for automatic classification and retrieval of motion capture data. Here, one main difficulty is due to the fact that similar types of motions may exhibit significant spatial as well as temporal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee6e804fadae399f07f1d024b8e11c69
https://doi.org/10.1145/1460096.1460169
https://doi.org/10.1145/1460096.1460169