Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Frank Perbet"'
Publikováno v:
Pattern Recognition Letters. 34:1808-1818
This paper is about detecting bipedal motion in video sequences by using point trajectories in a framework of classification. Given a number of point trajectories, we find a subset of points which are arising from feet in bipedal motion by analysing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89128df08f063b2e036cfae4b6fff1bc
https://doi.org/10.1016/j.patrec.2012.12.019
https://doi.org/10.1016/j.patrec.2012.12.019
Publikováno v:
BMVC
In applying the Hough transform to the problem of 3D shape recognition and registration, we develop two new and powerful improvements to this popular inference method. The first, intrinsic Hough, solves the problem of exponential memory requirements
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f953e2eb2fe9cefa9c92a9c00b3c0ab9
https://doi.org/10.1007/s11263-013-0623-2
https://doi.org/10.1007/s11263-013-0623-2
Publikováno v:
IEICE Transactions on Information and Systems. :1740-1748
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::875360fe7a27bc1b5850b20f086f36b0
https://doi.org/10.1587/transinf.e95.d.1740
https://doi.org/10.1587/transinf.e95.d.1740
Publikováno v:
Proceedings of the 5th International Conference on 3D Body Scanning Technologies, Lugano, Switzerland, 21-22 October 2014.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c668f417bd75e0d508a239b1c1f9c854
https://doi.org/10.15221/14.406
https://doi.org/10.15221/14.406
Publikováno v:
CVPR
This paper proposes a method for estimating the 3D body shape of a person with robustness to clothing. We formulate the problem as optimization over the manifold of valid depth maps of body shapes learned from synthetic training data. The manifold it
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ab0ee3175823212ef5f0506c0094e15
https://doi.org/10.1109/cvpr.2014.91
https://doi.org/10.1109/cvpr.2014.91
Autor:
Oliver Woodford, Riccardo Gherardi, Atsuto Maki, Roberto Cipolla, Bjorn Stenger, Minh-Tri Pham, Frank Perbet
The non-Euclidean nature of direct isometries in a Euclidean space, i.e. transformations consisting of a rotation and a translation, creates difficulties when computing distances, means and distributions over them, which have been well studied in the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::977beef33c6fa0c879f8249a81f42891
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-158118
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-158118
Autor:
Atsuto Maki, Roberto Cipolla, Oliver Woodford, Riccardo Gherardi, Minh-Tri Pham, Frank Perbet, Bjorn Stenger
Publikováno v:
Machine Learning for Computer Vision ISBN: 9783642286605
This chapter presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transformations for the first time. We introduce a new distance between poses in th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf18406be24732ca3b1d0775aa7efda4
https://doi.org/10.1007/978-3-642-28661-2_6
https://doi.org/10.1007/978-3-642-28661-2_6
Publikováno v:
Computer Vision – ECCV 2012 ISBN: 9783642337857
ECCV (7)
ECCV (7)
This paper presents a new class of moves, called α-expansion-contraction, which generalizes α-expansion graph cuts for multi-label energy minimization problems. The new moves are particularly useful for optimizing the assignments in model fitting f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f98cfe541324b6b437dbc6e33a1dd59f
https://doi.org/10.1007/978-3-642-33786-4_14
https://doi.org/10.1007/978-3-642-33786-4_14
Autor:
George Vogiatzis, Roberto Cipolla, Frank Perbet, Oliver Woodford, Carlos Hernández, Minh-Tri Pham, Atsuto Maki, Bjorn Stenger
Publikováno v:
ICCV Workshops
We present a video-based system which interactively captures the geometry of a 3D object in the form of a point cloud, then recognizes and registers known objects in this point cloud in a matter of seconds (fig. 1). In order to achieve interactive sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::210cf84aa63575efa087399dd465e0f1
https://doi.org/10.1109/iccvw.2011.6130324
https://doi.org/10.1109/iccvw.2011.6130324
Publikováno v:
ICCV
This paper presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transforms for the first time. We introduce a new distance between poses in this spac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b40b650b4a46bd2afaefdb4b4593cd3
https://doi.org/10.1109/iccv.2011.6126236
https://doi.org/10.1109/iccv.2011.6126236