What question did this study set out to answer?

This study aims to evaluate the effectiveness of different image registration methods using multi-spectral bands for high-resolution satellite and aerial imagery.

July 4, 2026Open Access

Multi-Spectral Band Analysis for Satellite-to-Aerial Image Registration: A Comparative Study of Deep Learning and Traditional Feature-Matching Methods

Key Points

This study aims to evaluate the effectiveness of different image registration methods using multi-spectral bands for high-resolution satellite and aerial imagery.
Compared five feature-matching approaches including LightGlue, SIFT, and edge-based FFT methods.
Integrated detector-free deep matchers (LoFTR and RoMa) for comparative analysis.
Assessed registration accuracy against network GNSS check points.
LightGlue achieved high inlier counts with over 1100 matched points.
SIFT with CLAHE preprocessing showed the lowest matching RMSE at 1.55 pixels.
Registration accuracy was approximately 2.8 m, statistically similar across all methods.

Abstract

Precise geometric registration between high-resolution satellite imagery and aerial orthophotos is essential for generating high-definition (HD) maps that support autonomous vehicle navigation. This study presents a comprehensive evaluation of multi-spectral band performance for image registration between KOMPSAT-3A satellite imagery (0.55 m resolution) and VWorld aerial orthophotos (0.25 m resolution) across seven patch size configurations. Five feature-matching approaches were systematically compared: LightGlue with CLAHE preprocessing, edge-based FFT methods (with and without CLAHE), and SIFT-based methods (with and without CLAHE). Two additional detector-free deep matchers, LoFTR and RoMa, were further integrated into the same pipeline for comparison. The experimental results reveal significant variations in registration accuracy across spectral bands, with the panchromatic-derived products (SPECPAN and EMPPAN) and luminance composite BT601 image demonstrating superior stability compared to individual visible and NIR bands. LightGlue achieved consistently high inlier counts (averaging 1100+ matched points) across all spectral bands and patch configurations, while SIFT with CLAHE preprocessing yielded the lowest matching RMSE (averaging 1.55 pixels). Among all matchers, the detector-free methods produced the densest and most stable correspondences, with LoFTR giving the best transformation stability, whereas edge-based methods were markedly less stable. However, an independent assessment against network GNSS check points showed a registration accuracy of approximately 2.8 m that was statistically similar across all matchers, indicating that matcher selection mainly affects correspondence density and transformation stability rather than independent geodetic accuracy. The achieved meter-level accuracy is suitable for HD map preprocessing and candidate GCP generation rather than final lane-level mapping, and the reported guidance is specific to the tested KOMPSAT-3A/VWorld setting.

Read Full Paperexternally

AI에게 질문

Bookmark

View Full Paper