MoonMetaSync: Lunar Image Registration Analysis

TL;DR

This paper evaluates feature detection methods for lunar image registration, introduces a new detector called IntFeat, and provides a Python tool for comparing registration techniques across different image resolutions in extraterrestrial environments.

Contribution

It introduces IntFeat, a novel feature detector combining SIFT and ORB features, and presents SyncVision, a Python package for lunar image registration analysis across scales.

Findings

IntFeat outperforms traditional methods in lunar image registration.

Upscaling low-resolution lunar images improves registration accuracy.

SyncVision enables comprehensive comparison of registration methods.

Abstract

This paper compares scale-invariant (SIFT) and scale-variant (ORB) feature detection methods, alongside our novel feature detector, IntFeat, specifically applied to lunar imagery. We evaluate these methods using low (128x128) and high-resolution (1024x1024) lunar image patches, providing insights into their performance across scales in challenging extraterrestrial environments. IntFeat combines high-level features from SIFT and low-level features from ORB into a single vector space for robust lunar image registration. We introduce SyncVision, a Python package that compares lunar images using various registration methods, including SIFT, ORB, and IntFeat. Our analysis includes upscaling low-resolution lunar images using bi-linear and bi-cubic interpolation, offering a unique perspective on registration effectiveness across scales and feature detectors in lunar landscapes. This research contributes to computer vision and planetary science by comparing feature detection methods for lunar imagery and introducing a versatile tool for lunar image registration and evaluation, with implications for multi-resolution image analysis in space exploration applications.