A probabilistic framework for correspondence and egomotion

Authors:
Justin Domke;Yiannis Aloimonos
Affiliations:
Computer Vision Laboratory, Department of Computer Science, University of Maryland, College Park, MD;Computer Vision Laboratory, Department of Computer Science, University of Maryland, College Park, MD
Venue:
WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision
Year:
2006

Citing 5
Cited 4

Computation of component image velocity from local phase information

International Journal of Computer Vision
A critique of structure-from-motion algorithms

Computer Vision and Image Understanding
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Radon-Based Structure from Motion without Correspondences

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information

Vision: A Computational Investigation into the Human Representation and Processing of Visual Information

An Introduction to Inertial and Visual Sensing

International Journal of Robotics Research
Monocular Vision Based Obstacle Detection for Robot Navigation in Unstructured Environment

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Robust tracking in aerial imagery based on an ego-motion Bayesian model

EURASIP Journal on Advances in Signal Processing - Special issue on advanced image processing for defense and security applications
A review and evaluation of methods estimating ego-motion

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper is an argument for two assertions: First, that by representing correspondence probabilistically, drastically more correspondence information can be extracted from images. Second, that by increasing the amount of correspondence information used, more accurate egomotion estimation is possible. We present a novel approach illustrating these principles. We first present a framework for using Gabor filters to generate such correspondence probability distributions. Essentially, different filters 'vote' on the correct correspondence in a way giving their relative likelihoods. Next, we use the epipolar constraint to generate a probability distribution over the possible motions. As the amount of correspondence information is increased, the set of motions yielding significant probabilities is shown to 'shrink' to the correct motion.