一种基于SURF和特征惯性跟随的异源图像配准新方法

IF 1.8 3区工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC

Journal of Infrared, Millimeter, and Terahertz Waves Pub Date : 2023-04-12 DOI:10.1117/12.2661631

S. Shang, Zhan-He Ou, Yang Zhou, Yuhao Yang, Pin Li

{"title":"一种基于SURF和特征惯性跟随的异源图像配准新方法","authors":"S. Shang, Zhan-He Ou, Yang Zhou, Yuhao Yang, Pin Li","doi":"10.1117/12.2661631","DOIUrl":null,"url":null,"abstract":"In this paper, a novel method of heterologous image registration method based on feature inertial following is proposed, which can perform high-precision and rapid registration of SAR image and optical image. The first image pair in the sequence is registered based on improved SURF feature to achieve high-precision registration. Based on this registration result, the other image pairs in the sequence are registered by the method of feature inertia following to achieve rapid registration. The proposed method makes full use of the correlation and gradient properties between image sequence frames. It maintains the registration accuracy of the preceding images, improves the registration speed greatly.","PeriodicalId":16181,"journal":{"name":"Journal of Infrared, Millimeter, and Terahertz Waves","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A novel method of heterologous image registration based on SURF and feature inertial following\",\"authors\":\"S. Shang, Zhan-He Ou, Yang Zhou, Yuhao Yang, Pin Li\",\"doi\":\"10.1117/12.2661631\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, a novel method of heterologous image registration method based on feature inertial following is proposed, which can perform high-precision and rapid registration of SAR image and optical image. The first image pair in the sequence is registered based on improved SURF feature to achieve high-precision registration. Based on this registration result, the other image pairs in the sequence are registered by the method of feature inertia following to achieve rapid registration. The proposed method makes full use of the correlation and gradient properties between image sequence frames. It maintains the registration accuracy of the preceding images, improves the registration speed greatly.\",\"PeriodicalId\":16181,\"journal\":{\"name\":\"Journal of Infrared, Millimeter, and Terahertz Waves\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2023-04-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Infrared, Millimeter, and Terahertz Waves\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1117/12.2661631\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Infrared, Millimeter, and Terahertz Waves","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1117/12.2661631","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

摘要

本文提出了一种基于特征惯性跟随的异源图像配准方法，可以实现SAR图像与光学图像的高精度快速配准。序列中的第一幅图像对基于改进的SURF特征进行配准，实现高精度配准。在此配准结果的基础上，采用特征惯性跟随的方法对序列中的其他图像对进行配准，实现快速配准。该方法充分利用了图像序列帧之间的相关性和梯度特性。它保持了前幅图像的配准精度，大大提高了配准速度。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A novel method of heterologous image registration based on SURF and feature inertial following

In this paper, a novel method of heterologous image registration method based on feature inertial following is proposed, which can perform high-precision and rapid registration of SAR image and optical image. The first image pair in the sequence is registered based on improved SURF feature to achieve high-precision registration. Based on this registration result, the other image pairs in the sequence are registered by the method of feature inertia following to achieve rapid registration. The proposed method makes full use of the correlation and gradient properties between image sequence frames. It maintains the registration accuracy of the preceding images, improves the registration speed greatly.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Journal of Infrared, Millimeter, and Terahertz Waves 工程技术-工程：电子与电气

CiteScore

6.20

自引率

6.90%

发文量

审稿时长

3 months

期刊介绍： The Journal of Infrared, Millimeter, and Terahertz Waves offers a peer-reviewed platform for the rapid dissemination of original, high-quality research in the frequency window from 30 GHz to 30 THz. The topics covered include: sources, detectors, and other devices; systems, spectroscopy, sensing, interaction between electromagnetic waves and matter, applications, metrology, and communications. Purely numerical work, especially with commercial software packages, will be published only in very exceptional cases. The same applies to manuscripts describing only algorithms (e.g. pattern recognition algorithms). Manuscripts submitted to the Journal should discuss a significant advancement to the field of infrared, millimeter, and terahertz waves.