Neural Network-based Feature Point Descriptors for Registration of Optical and SAR Images

机译：基于神经网络的特征点描述符用于光学和SAR图像配准

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Registration of images of different nature is an important technique used in image fusion, change detection, efficient information representation and other problems of computer vision. Solving this task using feature-based approaches is usually more complex than registration of several optical images because traditional feature descriptors (SIFT, SURF, etc.) perform poorly when images have different nature. In this paper we consider the problem of registration of SAR and optical images. We train neural network to build feature point descriptors and use RANSAC algorithm to align found matches. Experimental results are presented that confirm the method's effectiveness.

机译：不同性质的图像配准是用于图像融合，变化检测，有效的信息表示和计算机视觉的其他问题的重要技术。使用基于特征的方法来解决此任务通常比配准多个光学图像要复杂得多，因为当图像具有不同的性质时，传统的特征描述符（SIFT，SURF等）的性能较差。在本文中，我们考虑了SAR和光学图像的配准问题。我们训练神经网络来构建特征点描述符，并使用RANSAC算法来对齐找到的匹配项。实验结果证实了该方法的有效性。

著录项

来源
《International conference on machine vision》|2017年|106960L.1-106960L.8|共8页
会议地点
作者
Dmitry Abulkhanov; Ivan Konovalenko; Dmitry Nikolaev; Alexey Savchik; Evgeny Shvets; Dmitry Sidorchuk;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
optical and SAR image registration; feature points descriptors; remote sensing; spatial consistent matching (SCM); computer vision;

机译：光学和SAR图像配准;特征点描述符;遥感;空间一致性匹配（SCM）;计算机视觉;

相似文献

外文文献
中文文献
专利

1. Universal SAR and optical image registration via a novel SIFT framework based on nonlinear diffusion and a polar spatial-frequency descriptor [J] . Yu Qiuze, Ni Dawen, Jiang Yuxuan, ISPRS Journal of Photogrammetry and Remote Sensing . 2021,第Jana期

机译：通用SAR和光学图像通过基于非线性扩散和极性空间频率描述符的新型SIFT框架
2. Automatic optical-to-SAR image registration using a structural descriptor [J] . Image Processing, IET . 2020,第1期

机译：使用结构描述符自动进行SAR光学图像配准
3. Robust Feature Matching Method for SAR and Optical Images by Using Gaussian-Gamma-Shaped Bi-Windows-Based Descriptor and Geometric Constraint [J] . Min Chen, Ayman Habib, Haiqing He, Remote Sensing . 2017,第9期

机译：高斯-伽马形双窗口描述符和几何约束的SAR和光学图像鲁棒特征匹配方法
4. Neural Network-based Feature Point Descriptors for Registration of Optical and SAR Images [C] . Dmitry Abulkhanov, Ivan Konovalenko, Dmitry Nikolaev, International Conference on Machine Vision . 2018

机译：基于神经网络的特征点描述符，用于登记光学和SAR图像
5. Evaluation of Feature Detector-Descriptors for Automatic Registration of Multimodal Lunar Images [D] . Cwir, Weronika. 2020

机译：用于自动登记多模式月球图像的特征检测器描述符的评估
6. Fully automated convolutional neural network-based affine algorithm improves liver registration and lesion co-localization on hepatobiliary phase T1-weighted MR images [O] . Kyle A. Hasenstab, Guilherme Moura Cunha, Atsushi Higaki, 2019

机译：基于全自动卷积神经网络的仿射算法改进了肝胆T1期加权MR图像上的肝脏配准和病变共定位
7. Robust Feature Matching Method for SAR and Optical Images by Using Gaussian-Gamma-Shaped Bi-Windows-Based Descriptor and Geometric Constraint [O] . Min Chen, Ayman Habib, Haiqing He, 2017

机译：基于高斯 - 伽马形的基于Bi-Windows的描述符和几何约束，SAR和光学图像的强大特征匹配方法

Neural Network-based Feature Point Descriptors for Registration of Optical and SAR Images

摘要

著录项

相似文献

相关主题

期刊订阅