Sciweavers

598 search results - page 52 / 120
» Point-Based Modeling from a Single Image
Sort
View
ICIP
1994
IEEE
14 years 11 months ago
A Connectionist Model for Local Speed Estimation
Classical models for motion detection with artificial neural networks are inspired in physiological data of simple visual systems. Local speed estimationis a problem that involves...
Francisco J. Vico, F. J. Garrido, Francisco Sandov...
EMMCVPR
1999
Springer
14 years 2 months ago
Markov Random Field Modelling of fMRI Data Using a Mean Field EM-algorithm
This paper considers the use of the EM-algorithm, combined with mean field theory, for parameter estimation in Markov random field models from unlabelled data. Special attention ...
Markus Svensén, Frithjof Kruggel, D. Yves v...
ECCV
2006
Springer
14 years 1 months ago
Spatial Segmentation of Temporal Texture Using Mixture Linear Models
In this paper we propose a novel approach for the spatial segmentation of video sequences containing multiple temporal textures. This work is based on the notion that a single tem...
Lee Cooper, Jun Liu, Kun Huang
CVIU
2010
267views more  CVIU 2010»
13 years 7 months ago
Accelerated hardware video object segmentation: From foreground detection to connected components labelling
This paper demonstrates the use of a single-chip FPGA for the segmentation of moving objects in a video sequence. The system maintains highly accurate background models, and integ...
Kofi Appiah, Andrew Hunter, Patrick Dickinson, Hon...
CVPR
2008
IEEE
14 years 12 months ago
Increasing the density of Active Appearance Models
Active Appearance Models (AAMs) typically only use 50-100 mesh vertices because they are usually constructed from a set of training images with the vertices hand-labeled on them. ...
Krishnan Ramnath, Simon Baker, Iain Matthews, Deva...