Epiflow-A paradigm for tracking stereo correspondences

Authors:
Hongsheng Zhang;Shahriar Negahdaripour
Affiliations:
Underwater Vision and Imaging Laboratory, Electrical and Computer Engineering Department, University of Miami, 1251 Memorial Dr. Rm-406, Coral Gables, FL 33124-0640, USA;Underwater Vision and Imaging Laboratory, Electrical and Computer Engineering Department, University of Miami, 1251 Memorial Dr. Rm-406, Coral Gables, FL 33124-0640, USA
Venue:
Computer Vision and Image Understanding
Year:
2008

Citing 18
Cited 1

Algorithms for subpixel registration

Computer Vision, Graphics, and Image Processing
Least-Squares Fitting of Two 3-D Point Sets

IEEE Transactions on Pattern Analysis and Machine Intelligence
Least-Squares Estimation of Transformation Parameters Between Two Point Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
On unified optical flow field

Pattern Recognition
A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry

Artificial Intelligence - Special volume on computer vision
The Development and Comparison of Robust Methodsfor Estimating the Fundamental Matrix

International Journal of Computer Vision
Stereo-Motion with Stereo and Motion in Complement

IEEE Transactions on Pattern Analysis and Machine Intelligence
Cooperative stereo-motion: matching and reconstruction

Computer Vision and Image Understanding
Multiple view geometry in computer vision

Multiple view geometry in computer vision
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Match Propogation for Image-Based Modeling and Rendering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Unbiased Estimation and Statistical Analysis of 3-D Rigid Motion from Two Views

IEEE Transactions on Pattern Analysis and Machine Intelligence
Analysis of 3-D Rotation Fitting

IEEE Transactions on Pattern Analysis and Machine Intelligence
3D Model Acquisition from Extended Image Sequences

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
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
An Efficient Solution to the Five-Point Relative Pose Problem

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Improved Temporal Correspondences in Stereo-Vision by RANSAC

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04

Quasi-Parallax for Nearly Parallel Frontal Eyes

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose the epiflow as a novel framework to integrate the motion and stereo epipolar geometries for the tracking of stereo matches. For a given stereo pair, spatio-temporal correspondences in the next stereo pair are established from the solution of an optimization problem that incorporates the epiflow geometrical constraint with the brightness constancy assumption as the photometric similarity measure. Two different implementations are proposed, each utilizing the stereo RANSAC algorithm as a mechanism to gain robustness and efficiency in handling large temporal disparity ranges, identify outliers and estimate the motion of the stereo rig as complementary information. The performance of the proposed methods is demonstrated in experiments with various complex underwater images, and comparison with results from the SIFT method allows the assessment of our novel contributions.