Sciweavers

3025 search results - page 495 / 605
» Deriving Intrinsic Images from Image Sequences
Sort
View
ICCV
1995
IEEE
14 years 23 days ago
Recovering 3D Motion of Multiple Objects Using Adaptive Hough Transform
—We present a method to determine 3D motion and structure of multiple objects from two perspective views, using adaptive Hough transform. In our method, segmentation is determine...
Tina Yu Tian, Mubarak Shah
PAMI
2006
111views more  PAMI 2006»
13 years 9 months ago
Stereo Matching with Linear Superposition of Layers
In this paper, we address stereo matching in the presence of a class of non-Lambertian effects, where image formation can be modeled as the additive superposition of layers at diff...
Yanghai Tsin, Sing Bing Kang, Richard Szeliski
TCSV
2008
291views more  TCSV 2008»
13 years 9 months ago
A Statistical Video Content Recognition Method Using Invariant Features on Object Trajectories
Abstract--This work is dedicated to a statistical trajectorybased approach addressing two issues related to dynamic video content understanding: recognition of events and detection...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
IVC
2007
188views more  IVC 2007»
13 years 9 months ago
Integration of deformable contours and a multiple hypotheses Fisher color model for robust tracking in varying illuminant enviro
In this paper, we propose a new technique to perform figure-ground segmentation in image sequences of moving objects under varying illumination conditions. Unlike most of the alg...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
JAIR
2007
124views more  JAIR 2007»
13 years 9 months ago
Closed-Loop Learning of Visual Control Policies
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...
Sébastien Jodogne, Justus H. Piater