Sciweavers

118 search results - page 16 / 24
» Recursive estimation of generative models of video
Sort
View
CVPR
2003
IEEE
14 years 9 months ago
Variational Inference for Visual Tracking
The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or nonGaussian functions, leading to analytically intractable inference. ...
Jaco Vermaak, Neil D. Lawrence, Patrick Pér...
ECCV
2006
Springer
14 years 9 months ago
Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection
Using the variational approaches to estimate optical flow between two frames, the flow discontinuities between different motion fields are usually not distinguished even when an an...
Jiangjian Xiao, Hui Cheng, Harpreet S. Sawhney, Ce...
ICASSP
2009
IEEE
14 years 2 months ago
Motion-based object segmentation using local background sprites
It is well known that video material with a static background allows easier segmentation than that with a moving background. One approach to segmentation of sequences with a movin...
Andreas Krutz, Alexander Glantz, Thilo Borgmann, M...
CVPR
2007
IEEE
14 years 9 months ago
Kernel-based Tracking from a Probabilistic Viewpoint
In this paper, we present a probabilistic formulation of kernel-based tracking methods based upon maximum likelihood estimation. To this end, we view the coordinates for the pixel...
Quang Anh Nguyen, Antonio Robles-Kelly, Chunhua Sh...
ICPR
2002
IEEE
14 years 8 months ago
3-D Modeling of an Outdoor Scene by Multi-Baseline Stereo Using a Long Sequence of Images
Three-dimensional (3-D) models of outdoor scenes are widely used for object recognition, navigation, mixed reality, and so on. Because such models are often made manually with hig...
Tomokazu Sato, Masayuki Kanbara, Naokazu Yokoya, H...