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

Authors:
D. Demirdjian;T. Darrell
Affiliations:
Massachusetts Institute of Technology, AI Laboratory, Cambridge, MA 02139, USA. demirdji@ai.mit.edu;Massachusetts Institute of Technology, AI Laboratory, Cambridge, MA 02139, USA. trevor@ai.mit.edu
Venue:
International Journal of Computer Vision
Year:
2002

Citing 9
Cited 0

Computing occluding and transparent motions

International Journal of Computer Vision
A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry

Artificial Intelligence - Special volume on computer vision
Motion-egomotion discrimination and motion segmentation from image-pair streams

Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Hierarchical Model-Based Motion Estimation

ECCV '92 Proceedings of the Second European Conference on Computer Vision
Learning and Recognizing Human Dynamics in Video Sequences

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
From projective to Euclidean reconstruction

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Direct Estimation of Motion and Extended Scene Structure from a Moving Stereo Rig

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Robust Dense Matching Using Local and Global Geometric Constraints

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.