DVF-NET: Bi-Temporal Remote Sensing Image Registration Network Based on Displacement Vector Field Fusion
Sensors · 24.02.2025 · 25 (5) · 1380
DOI: 10.3390/s25051380 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 24.02.2025. Verfasst von Mingliang Xue und 5 weiteren Autor:innen. Beteiligte Einrichtung: SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering, Dalian Minzu University, Dalian 116600, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Liaoning Provincial Science and Technology Plan Joint Program (Technology R\&D Program Project), Liaoning Province Doctoral Research Start-up Fund, Research Foundation of Liaoning Educational Department.
Abstract (Originalsprache)
Accurate image registration is essential for various remote sensing applications, particularly in multi-temporal image analysis. This paper introduces DVF-NET, a novel deep learning-based framework for dual-temporal remote sensing image registration. DVF-NET integrates two displacement vector fields to address nonlinear distortions caused by significant variations between images, enabling more precise image alignment. A key innovation of this method is the incorporation of a Structural Attention Module (SAT), which enhances the model’s ability to focus on structural features, improving the feature extraction process. Additionally, we propose a novel loss function design that combines multiple similarity metrics, ensuring more comprehensive supervision during training. Experimental results on various remote sensing datasets indicate that the proposed DVF-NET outperforms the existing methods in both accuracy and robustness, particularly when handling images with substantial geometric distortions such as tilted buildings. The results validate the effectiveness of our approach and highlight its potential for various remote sensing tasks, including change detection, land cover classification, and environmental monitoring. DVF-NET provides a promising direction for the advancement of remote sensing image registration techniques, offering both high precision and robustness in complex real-world scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering, Dalian Minzu University, Dalian 116600, China.
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.
- School of Intelligent Engineering, Sun Yat-Sen University, Shenzhen Campus, Shenzhen 518107, China.
ORCID-Profile: Mingliang Xue, Yiming Zhang, Wanquan Liu
Förderung
- Liaoning Provincial Science and Technology Plan Joint Program (Technology R\&D Program Project)
- Liaoning Province Doctoral Research Start-up Fund
- Research Foundation of Liaoning Educational Department
Zitieren
APA
Xue, M., Zhang, Y., Jia, S., Cao, C., Feng, L., & Liu, W. (2025). DVF-NET: Bi-Temporal Remote Sensing Image Registration Network Based on Displacement Vector Field Fusion. Sensors, 25(5), 1380. https://doi.org/10.3390/s25051380
Vancouver
Xue M, Zhang Y, Jia S, Cao C, Feng L, Liu W. DVF-NET: Bi-Temporal Remote Sensing Image Registration Network Based on Displacement Vector Field Fusion. Sensors. 2025;25(5):1380. doi:10.3390/s25051380
BibTeX
@article{Xue2025,
author = {Xue, Mingliang and Zhang, Yiming and Jia, Shucai and Cao, Chong and Feng, Lin and Liu, Wanquan},
title = {DVF-NET: Bi-Temporal Remote Sensing Image Registration Network Based on Displacement Vector Field Fusion},
journal = {Sensors},
year = {2025},
volume = {25},
number = {5},
pages = {1380},
doi = {10.3390/s25051380}
}
EUVIMED