Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

14

IJCV
2002

favoriteEmaildiscussreport

172views more IJCV 2002»

Using Multiple-Hypothesis Disparity Maps and Image Velocity for 3-D Motion Estimation

13 years 4 months ago

Using Multiple-Hypothesis Disparity Maps and Image Velocity for 3-D Motion Estimation

Download people.csail.mit.edu

In this paper we explore a multiple hypothesis approach to estimating rigid motion from a moving stereo rig. More precisely, we introduce the use of Gaussian mixtures to model correspondence uncertainties for disparity and image velocity estimation. We show some properties of the disparity space and show how rigid transformations can be represented. An algorithm derived from standard random sampling-based robust estimators, that efficiently estimates rigid transformations from multi-hypothesis disparity maps and velocity fields is given.

David Demirdjian, Trevor Darrell

Real-time Traffic

IJCV 2002 | Image Velocity Estimation | Multiple Hypothesis Approach | Rigid |

claim paper

Related Content

» 3D Rigid Facial Motion Estimation from Disparity Maps

» Joint disparity and optical flow by correspondence growing

» Estimation of 3D Motion from Stereo Images Differential and Discrete Formulations

» Estimating Camera Motion through a 3D Cluttered Scene

» Motion Parallax without Motion Compensation in 3D Cluttered Scenes

» A framework for estimation of orientation and velocity

» Nonlinear disparity mapping for stereoscopic 3D

» Scene Flow Estimation by Growing Correspondence Seeds

» Modeling and 3D local estimation for inplane and outofplane motion guidance by 2D ultrasou...

Post Info
More Details (n/a)

Added	22 Dec 2010
Updated	22 Dec 2010
Type	Journal
Year	2002
Where	IJCV
Authors	David Demirdjian, Trevor Darrell

Comments (0)