Sciweavers

223 search results - page 3 / 45
» Dealing with Multiple Motions in Optical Flow Estimation
Sort
View
CVPR
1997
IEEE
14 years 7 months ago
Learning Parameterized Models of Image Motion
A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that ar...
Michael J. Black, Yaser Yacoob, Allan D. Jepson, D...
JUCS
2007
104views more  JUCS 2007»
13 years 5 months ago
Real-time Architecture for Robust Motion Estimation under Varying Illumination Conditions
: Motion estimation from image sequences is a complex problem which requires high computing resources and is highly affected by changes in the illumination conditions in most of th...
Javier Díaz, Eduardo Ros, Rafael Rodr&iacut...
MVA
2007
139views Computer Vision» more  MVA 2007»
13 years 7 months ago
A Method for Estimating Rigid Object Motion Using Regularized Scene Flow
In this paper, we propose a method for estimating object motion by three-dimensional scene flow using multiple cameras. The scene flow is regularized by applying subspace constr...
Hiroki Mizuno, Hironobu Fujiyoshi
CVPR
1996
IEEE
14 years 7 months ago
Skin and Bones: Multi-layer, Locally Affine, Optical Flow and Regularization with Transparency
This paper describes a new method for estimating optical flow that strikes a balance between the flexibility of local dense computations and the robustness and accuracy of global ...
Shanon X. Ju, Michael J. Black, Allan D. Jepson
FGR
1996
IEEE
186views Biometrics» more  FGR 1996»
13 years 9 months ago
Cardboard People: A Parameterized Model of Articulated Image Motion
We extend the work of Black and Yacoob on the tracking and recognition of human facial expressions using parameterized models of optical flow to deal with the articulatedmotion of...
Shanon X. Ju, Michael J. Black, Yaser Yacoob