期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 14, 期 -, 页码 1895-1908出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2021.3050459
关键词
Feature matching; image registration; mismatch removal; remote sensing; visualization descriptor
类别
资金
- National Natural Science Foundation of China [41971392]
- Yunnan Ten-thousand Talents Program
This article proposes a method based on local structure visualization descriptors and convolutional neural networks for image registration, aiming to improve the reliability and precision of feature matching. The method is not restricted by specific transformation models, has good adaptability to various remote sensing images, and extensive experiments demonstrate its superior performance.
Image registration is a fundamental and important task in remote sensing. In this article, we focus on feature-based image registration. Existing attempts often require estimating a transformation model or imposing relaxed geometric constraints to establish reliable feature correspondences. However, a parametric model cannot handle image pairs undergoing complex transformations, and relaxed methods discard a lot of structure information and the results are often coarse. To solve the above issues, we propose a local structure visualization descriptor to preserve the original structure information, and cast the feature matching task into an evaluation of the consensus of visual structure under a convolutional neural network. This strategy can effectively measure the similarity of neighborhood structure for mismatch removal. In summary, our method does not depend on a specific transformation model and can process arbitrary remote sensing images (e.g., different deformations, severe outliers, various rotations, and scaling changes). To demonstrate the robustness of our strategy for image registration, extensive experiments on various real remote sensing images for feature matching are conducted and compared against nine state-of-the-art methods, where our method gives the best performances in most scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据