Sciweavers

24 search results - page 1 / 5
» Monocular and Stereo Methods for AAM Learning from Video
Sort
View
CVPR
2007
IEEE
14 years 6 months ago
Monocular and Stereo Methods for AAM Learning from Video
The active appearance model (AAM) is a powerful method for modeling deformable visual objects. One of the major drawbacks of the AAM is that it requires a training set of pseudo-d...
Jason Saragih, Roland Göcke
FGR
2008
IEEE
188views Biometrics» more  FGR 2008»
13 years 11 months ago
Person-independent face tracking based on dynamic AAM selection
Abstract This paper proposes a real-time high-precision method to track an unknown face in front of an information system by selecting appropriate model to a video image. Active Ap...
Akihiro Kobayashi, Junji Satake, Takatsugu Hirayam...
ICRA
2009
IEEE
167views Robotics» more  ICRA 2009»
13 years 11 months ago
Articulated object tracking by rendering consistent appearance parts
— We describe a general methodology for tracking 3-dimensional objects in monocular and stereo video that makes use of GPU-accelerated filtering and rendering in combination wit...
Zachary A. Pezzementi, Sandrine Voros, Gregory D. ...
CVPR
2005
IEEE
14 years 6 months ago
Localization in Urban Environments: Monocular Vision Compared to a Differential GPS Sensor
In this paper we present a method for computing the localization of a mobile robot with reference to a learning video sequence. The robot is first guided on a path by a human, whi...
Eric Royer, Maxime Lhuillier, Michel Dhome, Thierr...
NIPS
2000
13 years 6 months ago
Learning and Tracking Cyclic Human Motion
We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segm...
Dirk Ormoneit, Hedvig Sidenbladh, Michael J. Black...