Interest point characterisation through textural analysis for rejection of bad correspondences

Authors:
Viorela Ila;Rafael Garcia;Xavier Cufi;Joan Batlle
Affiliations:
Computer Vision and Robotics Group, University of Girona, Campus Montilivi, 17071 Girona, Spain;Computer Vision and Robotics Group, University of Girona, Campus Montilivi, 17071 Girona, Spain;Computer Vision and Robotics Group, University of Girona, Campus Montilivi, 17071 Girona, Spain;Computer Vision and Robotics Group, University of Girona, Campus Montilivi, 17071 Girona, Spain
Venue:
Pattern Recognition Letters
Year:
2005

Citing 7
Cited 0

Finding Trajectories of Feature Points in a Monocular Image Sequence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Identification of partially obscured objects in two and three dimensions by matching noisy characteristic

International Journal of Robotics Research
Robust regression and outlier detection

Robust regression and outlier detection
A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry

Artificial Intelligence - Special volume on computer vision
Determining the Epipolar Geometry and its Uncertainty: A Review

International Journal of Computer Vision
Tracking Line Segments

ECCV '90 Proceedings of the First European Conference on Computer Vision
A RANSAC-based approach to model fitting and its application to finding cylinders in range data

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2

Quantified Score

Hi-index	0.10

Visualization

Abstract

This work proposes a tool based on texture analysis to characterise incorrect point correspondences in underwater image pairs. Interest point correspondences are first detected through region correlation, obtaining pairs of matched points in both images. For every pair of points, their textural characteristics are computed. These textural properties are stored in two corresponding characterisation vectors, which are then compared by means of similarity measures. This measure can be considered as a reliable threshold for outlier rejection. Experiments with real underwater images were carried out.