Remote sensing image matching by integrating affine invariant feature extraction and RANSAC

Authors:
Liang Cheng;Manchun Li;Yongxue Liu;Wenting Cai;Yanming Chen;Kang Yang
Affiliations:
Department of Geographical Information Science, Nanjing University, Nanjing 210093, China;Department of Geographical Information Science, Nanjing University, Nanjing 210093, China;Department of Geographical Information Science, Nanjing University, Nanjing 210093, China;Department of Geographical Information Science, Nanjing University, Nanjing 210093, China;Department of Geographical Information Science, Nanjing University, Nanjing 210093, China;Department of Geographical Information Science, Nanjing University, Nanjing 210093, China
Venue:
Computers and Electrical Engineering
Year:
2012

Citing 7
Cited 1

Multiple view geometry in computer visiond

Multiple view geometry in computer visiond
Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?"

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Matching Widely Separated Views Based on Affine Invariant Regions

International Journal of Computer Vision
Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Comparison of Affine Region Detectors

International Journal of Computer Vision

A MapReduce-based indoor visual localization system using affine invariant features

Computers and Electrical Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new technical framework for remote sensing image matching by integrating affine invariant feature extraction and RANSAC is presented. The novelty of this framework is an automatic optimization strategy for affine invariant feature matching based on RANSAC. An automatic way to determine the distance threshold of RANSAC is proposed, which is a key problem to implement this RANSAC-based automatic optimization. Since affine invariant feature matching technology has been successfully applied to remote sensing image matching, we design an experiment to compare the proposed framework (with optimization) with the standard affine invariant feature matching (without optimization). By using three pairs with different types of imagery, the experimental results indicate that the proposed framework can always get higher correctness of image matching in automatic way, compared to the standard affine invariant feature matching technology.