JOURNAL ARTICLE

SAR-Optical Image Matching Model Based on Contrastive Learning

Abstract

Due to the strong complementary nature of synthetic aperture radar (SAR) and optical imagery in remote sensing, matching SAR images with optical images enables the complementary extraction of ground surface feature information. This approach is beneficial for addressing tasks such as change detection, target recognition, and land cover classification. With the development of deep learning, most current models for SAR-optical image matching utilize siamese neural networks and have achieved good matching performance. However, in practical applications, test data is often unknown, and there may be differences between training and test data. A matching model that performs well on the training dataset may not generalize well to the test data. Domain generalization research for heterogeneous image matching aims to improve the generalization performance of matching models on unknown test domains, and this task has practical significance and application prospects. In this paper, we propose a contrastive learning-based SAR-optical image matching model specifically designed to enhance the generalization performance of matching models trained on multiple datasets. When dealing with cross-domain scenarios, enforcing feature consistency of matching points preserves more information conducive to matching. We propose a contrastive learning method to limit the feature consistency of matching points, thereby improving the generalization performance of cross-source image matching models.

Keywords:
Computer science Matching (statistics) Artificial intelligence Generalization Synthetic aperture radar Pattern recognition (psychology) Feature (linguistics) Consistency (knowledge bases) Feature extraction Test data Contextual image classification Computer vision Image (mathematics) Machine learning Mathematics

Metrics

2
Cited By
0.36
FWCI (Field Weighted Citation Impact)
11
Refs
0.57
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Advanced Image and Video Retrieval Techniques
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
Multimodal Machine Learning Applications
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
Robotics and Sensor-Based Localization
Physical Sciences →  Engineering →  Aerospace Engineering

Related Documents

JOURNAL ARTICLE

Robust Self-supervised Correspondence Learning for SAR-optical Image Matching

Chengjin AnFanzhi CaoPu WangTianxin Shi

Journal:   2022 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) Year: 2022 Pages: 49-53
JOURNAL ARTICLE

Contrastive learning for real SAR image despeckling

Yuwei FangRui LiuYini PengJianjun GuanDuidui LiXin Tian

Journal:   ISPRS Journal of Photogrammetry and Remote Sensing Year: 2024 Vol: 218 Pages: 376-391
© 2026 ScienceGate Book Chapters — All rights reserved.