Multi-Spectral Band Analysis for Satellite-to-Aerial Image Registration: A Comparative Study of Deep Learning and Traditional Feature-Matching Methods
Sensors · 02.07.2026 · 26 (13) · 4165
DOI: 10.3390/s26134165 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 02.07.2026. Verfasst von Dongyeob Han und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil Engineering, Chonnam National University, Gwangju 61186, Republic of Korea. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Aerospace Research Institute, Korean Aerospace Research Institute.
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Civil Engineering, Chonnam National University, Gwangju 61186, Republic of Korea.
- National Satellite Operation & Application Center, Korea Aerospace Research Institute, Daejeon 34133, Republic of Korea.
ORCID-Profile: Dongyeob Han, Sun-Gu Lee
Förderung
- Korea Aerospace Research Institute
- Korean Aerospace Research Institute
Zitieren
APA
Han, D., Song, J. H., & Lee, S. G. (2026). Multi-Spectral Band Analysis for Satellite-to-Aerial Image Registration: A Comparative Study of Deep Learning and Traditional Feature-Matching Methods. Sensors, 26(13), 4165. https://doi.org/10.3390/s26134165
Vancouver
Han D, Song JH, Lee SG. Multi-Spectral Band Analysis for Satellite-to-Aerial Image Registration: A Comparative Study of Deep Learning and Traditional Feature-Matching Methods. Sensors. 2026;26(13):4165. doi:10.3390/s26134165
BibTeX
@article{Han2026,
author = {Han, Dongyeob and Song, Jeong Heon and Lee, Sun-Gu},
title = {Multi-Spectral Band Analysis for Satellite-to-Aerial Image Registration: A Comparative Study of Deep Learning and Traditional Feature-Matching Methods},
journal = {Sensors},
year = {2026},
volume = {26},
number = {13},
pages = {4165},
doi = {10.3390/s26134165}
}
EUVIMED