Sciweavers

888 search results - page 52 / 178
» Global pose estimation using non-tree models
Sort
View
ICIP
2004
IEEE
15 years 11 months ago
Robust ego-motion estimation and 3d model refinement using depth based parallax model
We present an iterative algorithm for robustly estimating the egomotion and refining and updating a coarse, noisy and partial depth map using a depth based parallax model and brig...
Amit K. Agrawal, Rama Chellappa
ICIP
2001
IEEE
15 years 11 months ago
Tracking of human activities using shape-encoded particle propagation
We present an approach to tracking human activities in a monocular video. We model the human body by decomposing it into torso and limbs and use simple 3D shapes to approximate th...
Hankyu Moon, Rama Chellappa, Azriel Rosenfeld
AAAI
1993
14 years 11 months ago
Learning Object Models from Appearance
We address the problem of automatically learning object models for recognition and pose estimation. In contrast to the traditional approach, we formulate the recognition problem a...
Hiroshi Murase, Shree K. Nayar
BMVC
1998
14 years 11 months ago
Segmentation of Global Motion using Temporal Probabilistic Classification
The segmentation of pixels belonging to different moving elements within a cinematographic image sequence underpins a range of post-production special effects. In this work, the s...
P. R. Giaccone, Graeme A. Jones
ICCV
2007
IEEE
15 years 11 months ago
Conditional State Space Models for Discriminative Motion Estimation
We consider the problem of predicting a sequence of real-valued multivariate states from a given measurement sequence. Its typical application in computer vision is the task of mo...
Minyoung Kim, Vladimir Pavlovic