Sciweavers

173 search results - page 1 / 35
» Modeling and Estimating Persistent Motion with Geometric Flo...
Sort
View
CVPR
2010
IEEE
13 years 11 months ago
Modeling and Estimating Persistent Motion with Geometric Flows
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local...
Dahua Lin, Eric Grimson, John Fisher
CVPR
2004
IEEE
14 years 6 months ago
Motion-Based Background Subtraction Using Adaptive Kernel Density Estimation
Background modeling is an important component of many vision systems. Existing work in the area has mostly addressed scenes that consist of static or quasi-static structures. When...
Anurag Mittal, Nikos Paragios
CVPR
1997
IEEE
14 years 6 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...
ICRA
2006
IEEE
139views Robotics» more  ICRA 2006»
13 years 10 months ago
Adaptive Geometric Templates for Feature Matching
Robust motion recovery in tracking multiple targets using image features is affected by difficulties in obtaining good correspondences over long sequences. Difficulties are intr...
Harini Veeraraghavan, Paul R. Schrater, Nikolaos P...
ICCV
1999
IEEE
13 years 9 months ago
Multi-Frame Optical Flow Estimation using Subspace Constraints
We show that the set of all ow- elds in a sequence of frames imaging a rigid scene resides in a lowdimensional linear subspace. Based on this observation, we develop a method for ...
Michal Irani