Sciweavers

888 search results - page 97 / 178
» Global pose estimation using non-tree models
Sort
View
ECCV
2010
Springer
15 years 8 days ago
Depth-Encoded Hough Voting for joint object detection and shape recovery
Detecting objects, estimating their pose and recovering 3D shape information is a critical problem in many vision and robotics applications. This paper addresses the above needs by...
HUMO
2007
Springer
15 years 4 months ago
Modeling Human Locomotion with Topologically Constrained Latent Variable Models
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Raquel Urtasun, David J. Fleet, Neil D. Lawrence
FGR
2011
IEEE
288views Biometrics» more  FGR 2011»
14 years 1 months ago
Hierarchical CRF with product label spaces for parts-based models
— Non-rigid object detection is a challenging open research problem in computer vision. It is a critical part in many applications such as image search, surveillance, humancomput...
Gemma Roig, Xavier Boix Bosch, Fernando De la Torr...
ICPR
2006
IEEE
15 years 11 months ago
Perspective Symmetry Invariant and Its Applications
Face is a perceptually symmetric object; however, it often appears not so in captured image due to the rotation in depth within the 3D space. In this paper, we explore the invaria...
Shuicheng Yan, Tianqiang Yuan, Xiaoou Tang
BMVC
2010
14 years 8 months ago
Moving Camera Registration for Multiple Camera Setups in Dynamic Scenes
Many practical applications require an accurate knowledge of the extrinsic calibration (i.e., pose) of a moving camera. The existing SLAM and structure-from-motion solutions are n...
Evren Imre, Jean-Yves Guillemaut, Adrian Hilton