Hypergeometric Filters for Optical Flow and Affine Matching

Authors:
Yalin Xiong;Steven A. Shafer
Affiliations:
The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 1521. E-mail: yx@cs.cmu.edu, sas@cs.cmu.edu;The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 1521. E-mail: yx@cs.cmu.edu, sas@cs.cmu.edu
Venue:
International Journal of Computer Vision
Year:
1997

Citing 9
Cited 5

An atlas of functions

An atlas of functions
Phase-based disparity measurement

CVGIP: Image Understanding
Algorithm 707: CONHYP: a numerical evaluator of the confluent hypergeometric function for complex arguments of large magnitudes

ACM Transactions on Mathematical Software (TOMS)
Numerical evaluation of the confluent hypergeometric function for complex arguments of large magnitudes

Journal of Computational and Applied Mathematics
Computational models of binocular vision

Computational models of binocular vision
Image matching using the windowed Fourier phase

International Journal of Computer Vision
Performance of optical flow techniques

International Journal of Computer Vision
Deriving orientation cues from stereo images

ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Handbook of Mathematical Functions, With Formulas, Graphs, and Mathematical Tables,

Handbook of Mathematical Functions, With Formulas, Graphs, and Mathematical Tables,

Volumetric Deformation Analysis Using Mechanics-Based Data Fusion: Applications in Cardiac Motion Recovery

International Journal of Computer Vision
Shift Detection by Restoration

CAIP '99 Proceedings of the 8th International Conference on Computer Analysis of Images and Patterns
A homotopy-based approach for computing defocus blur and affine transform simultaneously

Pattern Recognition
Homotopy-based computation of defocus blur and affine transform

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Complex correlation statistic for dense stereoscopic matching

SCIA'05 Proceedings of the 14th Scandinavian conference on Image Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes new “hypergeometric” filters for the problem ofimage matching under the translational and affine model. This new setof filters has the following advantages: (1) High-precisionregistration of two images under the translational and affine model.Because the window effects are eliminated, we are able to achievesuperb performance in both translational and affine matching. (2) Affine matching without exhaustive search or image warping. Due tothe recursiveness of the filters in the spatial domain, We are ableto analytically express the relation between filter outputs and thesix affine parameters. This analytical relation enables us todirectly compute these affine parameters. (3) Generality. Theapproach we demonstrate here can be applied to a broad class ofmatching problems as long as the transformation between the two imagepatches can be mathematically represented in the frequency domain.