A statistical approach to sparse multi-scale phase-based stereo

Authors:
I. Ulusoy;E. R. Hancock
Affiliations:
Computer Vision and Intelligent Systems Research Laboratory, Electrical and Electronics Engineering Department, Middle East Technical University, 06531 Ankara, Turkey;Department of Computer Science, University of York, York Y01 5DD, UK
Venue:
Pattern Recognition
Year:
2007

Citing 11
Cited 1

The Design and Use of Steerable Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recovering local surface structure through local phase difference measurements

CVGIP: Image Understanding
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Maximum-Likelihood Image Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Scale-Space Singularities

ECCV '90 Proceedings of the First European Conference on Computer Vision
The Geometry and Matching of Curves in Multiple Views

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Phase-Based Local Features

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Bayesian Graph Edit Distance

ICIAP '99 Proceedings of the 10th International Conference on Image Analysis and Processing
Regularizing Phase-Based Stereo

ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Multi-scale phase-based local features

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

A compact harmonic code for early vision based on anisotropic frequency channels

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this study, a multi-scale phase based sparse disparity algorithm and a probabilistic model for matching uncertain phase are proposed. The features used are oriented edges extracted using steerable filters. Feature correspondences are estimated using phase-similarity at multiple scale using a magnitude weighting scheme. In order to achieve sub-pixel accuracy in disparity, we use a fine tuning procedure which employs the phase difference between corresponding feature points. We also derive a probabilistic model, where phase uncertainty is trained using data from a single image pair. The model is used to provide stable matches. The disparity algorithm and the probabilistic phase uncertainty model are verified on various stereo image pairs.