Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MoonMetaSync: Lunar Image Registration Analysis

Ashutosh Kumar, Sarthak Kaushal, Shiv Vignesh Murthy

TL;DR

SyncVision, a Python package that compares lunar images using various registration methods, including SIFT, ORB, and IntFeat, is introduced, introducing a versatile tool for lunar image registration and evaluation, with implications for multi-resolution image analysis in space exploration applications.

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.

MoonMetaSync: Lunar Image Registration Analysis

TL;DR

SyncVision, a Python package that compares lunar images using various registration methods, including SIFT, ORB, and IntFeat, is introduced, introducing a versatile tool for lunar image registration and evaluation, with implications for multi-resolution image analysis in space exploration applications.

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.

Paper Structure

This paper contains 19 sections, 5 equations, 6 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Dataset
  5. Matching OHRC and TMC-2 Images
  6. Image Preprocessing
  7. Image Registration
  8. Feature Detection
  9. Feature Matching
  10. Transformation Model
  11. SyncVision
  12. Results
  13. Performance of Feature Detectors
  14. Analysis of Lunar Images
  15. Discussions
  16. ...and 4 more sections

Figures (6)

  • Figure 1: Overall methodology of image registration in the SyncVision framework, showcasing the sequential process of aligning TMC-2 and OHRC patches. This includes feature extraction using advanced algorithms, keypoint matching, and interpolation techniques (both bi-linear and bi-cubic) to achieve optimal alignment. The flow demonstrates how these components work together to enhance image quality and accuracy in lunar terrain analysis, ensuring precise registration of diverse image data.
  • Figure 2: TMC-2 patch (Size: 128x128)
  • Figure 3: OHRC patch (Size: 1024x1024)
  • Figure 4: Bi-linear interpolation, calculates the value of a new pixel based on a weighted average of the four nearest pixels in the original image.
  • Figure 5: Bi-cubic interpolation, calculates the value of a new pixel based on a weighted average of the 16 nearest pixels in the original image
  • ...and 1 more figures