Mathematical Analysis of Image Matching Techniques

TL;DR

This paper evaluates classical local feature-based image matching algorithms, specifically SIFT and ORB, on satellite imagery to understand their effectiveness and impact of keypoint quantity on matching quality.

Contribution

It provides an analytical and experimental comparison of SIFT and ORB for satellite image matching, highlighting how keypoint count affects inlier ratio and matching accuracy.

Findings

SIFT generally achieves higher inlier ratios than ORB on satellite images.

Increasing the number of keypoints improves matching quality up to a point.

The study offers insights into the trade-offs between computational cost and matching accuracy.

Abstract

Image matching is a fundamental problem in Computer Vision with direct applications in robotics, remote sensing, and geospatial data analysis. We present an analytical and experimental evaluation of classical local feature-based image matching algorithms on satellite imagery, focusing on the Scale-Invariant Feature Transform (SIFT) and the Oriented FAST and Rotated BRIEF (ORB). Each method is evaluated through a common pipeline: keypoint detection, descriptor extraction, descriptor matching, and geometric verification via RANSAC with homography estimation. Matching quality is assessed using the Inlier Ratio - the fraction of correspondences consistent with the estimated homography. The study uses a manually constructed dataset of GPS-annotated satellite image tiles with intentional overlaps. We examine the impact of the number of extracted keypoints on the resulting Inlier Ratio.