EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Stereo Radargrammetry Using Deep Learning-Based Image Matching with Fine-Tuned Model on Synthetic Aperture Radar Images

Koichi Ito, Tatsuya Sasayama, Shintaro Ito, Haruki Iwasa, Takafumi Aoki, Jyunpei Uemoto

Remote Sensing · 21.05.2026 · 18 (10) · 1662

DOI: 10.3390/rs18101662 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 21.05.2026. Verfasst von Koichi Ito und 5 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Stereo radargrammetry using Synthetic Aperture Radar (SAR) images is a powerful technique for all-weather 3D topographic measurements. However, conventional methods based on local template matching often struggle to establish accurate correspondences in mountainous or vegetated areas due to severe SAR-specific geometric modulations. In this paper, we propose a novel high-accuracy stereo radargrammetry framework by introducing RoMa, a robust Transformer-based deep learning model, for dense SAR image matching. Optical pre-trained deep learning models often suffer from a domain gap. To overcome this limitation, we develop an automated pipeline to construct a patch-based SAR image dataset using a reference Digital Surface Model (DSM) and an SAR projection model. By fine-tuning RoMa on this dataset, the model effectively adapts to the complex non-linear deformations of SAR images. Furthermore, unlike conventional methods, our approach establishes correspondences directly on the original slant-range images without requiring ground-range projection, thereby avoiding image quality degradation caused by pixel interpolation. Experimental results using airborne Pi-SAR2 images demonstrate that the fine-tuned RoMa significantly outperforms conventional methods, achieving an 82.86% matching accuracy at a 10-pixel threshold. In the 3D measurement evaluation, the proposed method achieves the lowest elevation mean error (−1.24 m) and the highest inlier ratio (74.1%), proving its effectiveness in generating accurate, dense, and wide-area 3D point clouds even in challenging terrains.

Förderung

  • JSPS KAKENHI

Zitieren

APA

Ito, K., Sasayama, T., Ito, S., Iwasa, H., Aoki, T., & Uemoto, J. (2026). Stereo Radargrammetry Using Deep Learning-Based Image Matching with Fine-Tuned Model on Synthetic Aperture Radar Images. Remote Sensing, 18(10), 1662. https://doi.org/10.3390/rs18101662

Vancouver

Ito K, Sasayama T, Ito S, Iwasa H, Aoki T, Uemoto J. Stereo Radargrammetry Using Deep Learning-Based Image Matching with Fine-Tuned Model on Synthetic Aperture Radar Images. Remote Sensing. 2026;18(10):1662. doi:10.3390/rs18101662

BibTeX
@article{Ito2026,
  author = {Ito, Koichi and Sasayama, Tatsuya and Ito, Shintaro and Iwasa, Haruki and Aoki, Takafumi and Uemoto, Jyunpei},
  title = {Stereo Radargrammetry Using Deep Learning-Based Image Matching with Fine-Tuned Model on Synthetic Aperture Radar Images},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {10},
  pages = {1662},
  doi = {10.3390/rs18101662}
}
Kostenlos starten →