Sciweavers

269 search results - page 41 / 54
» Towards Urban 3D Reconstruction from Video
Sort
View
ICCV
2007
IEEE
14 years 9 months ago
Perspectively Invariant Normal Features
We extend the successful 2D robust feature concept into the third dimension in that we produce a descriptor for a reconstructed 3D surface region. The descriptor is perspectively ...
Kevin Köser, Reinhard Koch
ICMCS
2009
IEEE
133views Multimedia» more  ICMCS 2009»
13 years 5 months ago
View indepedent human movement recognition from multi-view video exploiting a circular invariant posture representation
In this paper a novel method for view independent human movement representation and recognition, exploiting the rich information contained in multi-view videos, is proposed. The bi...
Nikolaos Gkalelis, Nikos Nikolaidis, Ioannis Pitas
ICIP
2005
IEEE
14 years 9 months ago
Spacetime-continuous geometry meshes from multi-view video sequences
We reconstruct geometry for a time-varying scene given by a number of video sequences. The dynamic geometry is represented by a 3D hypersurface embedded in space-time. The interse...
Bastian Goldlücke, Marcus A. Magnor
ECCV
2004
Springer
14 years 9 months ago
Novel Skeletal Representation for Articulated Creatures
Abstract. Volumetric structures are frequently used as shape descriptors for 3D data. The capture of such data is being facilitated by developments in multi-view video and range sc...
Gabriel J. Brostow, Irfan A. Essa, Drew Steedly, V...
ICRA
2010
IEEE
135views Robotics» more  ICRA 2010»
13 years 6 months ago
Using multiple hypothesis in model-based tracking
— Classic registration methods for model-based tracking try to align the projected edges of a 3D model with the edges of the image. However, wrong matches at low level can make t...
Céline Teuliere, Éric Marchand, Laur...