地球信息科学学报 ›› 2022, Vol. 24 ›› Issue (3): 522-532.doi: 10.12082/dqxxkx.2022.210394

• 遥感科学与应用技术 • 上一篇    下一篇

一种基于面阵摆扫式航空影像的特征匹配方法

张昆1(), 王涛1,*(), 张艳1, 郑迎辉1, 赵祥1, 李芳芳2   

  1. 1.信息工程大学,郑州 450001
    2.中科遥感科技集团有限公司,天津 300384
  • 收稿日期:2021-07-14 修回日期:2021-09-25 出版日期:2022-03-25 发布日期:2022-05-25
  • 通讯作者: *王 涛(1975— ),男,河南郑州人,教授,从事数字摄影测量方向、数字图像处理等研究。E-mail: wangtaoynl@163.com
  • 作者简介:张 昆(1997— ),男,河南兰考人,硕士,主要从事计算机视觉,三维重建等研究。E-mail: 18839103702@163.com
  • 基金资助:
    装备技术基础科研项目(192WJ22007)

A Feature Matching Method based on Area Array Swing-Scan Aerial Image

ZHANG Kun1(), WANG Tao1,*(), ZHANG Yan1, ZHENG Yinghui1, ZHAO Xiang1, LI Fangfang2   

  1. 1. University of Information Engineering, Zhengzhou 450001, China
    2. China Scientific Remote Sensing Technology Group Corporation, Tianjin 300384, China
  • Received:2021-07-14 Revised:2021-09-25 Online:2022-03-25 Published:2022-05-25
  • Supported by:
    Equipment technology basic scientific research project(192WJ22007)

摘要:

特征匹配是面阵摆扫式航空影像处理的关键步骤,针对传统特征匹配方法在面阵摆扫式航空影像匹配时存在匹配点数量少,分布不匀均的问题,本文提出一种基于自适应亮度空间的特征匹配方法。首先根据影像POS(Postion Oriental System)信息求解待匹配影像间变换关系进行影像校正,在校正后的影像上构建自适应亮度空间,使用ORB算子和BEBLID算法在亮度空间上获取特征点和二进制特征描述符,然后基于汉明距离获取初始匹配点,使用RANSAC算法剔除粗差,最后将匹配点变换到原始影像上得到最终匹配结果。本文选取6组具有视角差异及亮度变化的面阵摆扫式航空影像进行实验,将本文算法与SIFT、SURF、ORB、ORB+BEBLID、ASIFT等匹配方法进行比较,结果表明:本文算法通过建立影像间变换关系,构建自适应亮度空间,使得算法提取的特征点数量增加1.5倍,获取匹配点数量是其他算法的3倍以上,且匹配点分布更加均匀,匹配效率高于其他算法,验证了本文算法在具有亮度变化及视角差异的面阵摆扫式航空影像上匹配的有效性。

关键词: 影像匹配, 自适应亮度空间, BEBLID, RANSAC, 单应变换, 面阵摆扫式航空影像, POS

Abstract:

Feature matching is a key step in the area array swing-scan aerial image processing. Traditional feature matching method has some limitations in the area array swing-scan aerial image matching, e.g., the number of matching points is small, and the distribution is uneven. This paper proposes a method based on adaptive feature matching method in brightness space. First, according to the image Position Oriental System (POS) information, we solve the transformation relationship between the images to be matched for image correction, build an adaptive brightness space on the corrected image, and use ORB operator and BEBLID algorithm to obtain feature points and binary feature descriptors in the brightness space. Then, based on the Hamming distance, we obtain the initial matching points, use the RANSAC algorithm to eliminate gross error. Finally, the matching points are transformed to the original image to obtain the final matching result. This paper selects six groups of swept aerial images with different viewing angles and brightness changes for experiments and compares the algorithm proposed in this paper with SIFT, SURF, ORB, ORB+BEBLID, and ASIFT matching methods. The results show that the algorithm in this paper builds an adaptive brightness space by establishing the transformation relationship between images, so that the number of feature points extracted by the algorithm is increased by 1.5 times, and the number of matching points obtained is more than 3 times that of other algorithms. The distribution of matching points is more uniform, and the matching efficiency is higher than other algorithms. The algorithm verifies the effectiveness of the algorithm proposed in this paper to match the area array swing-scan aerial images with brightness changes and viewing angle differences.

Key words: image matching, adaptive brightness space, BEBLID, RANSAC, homography, area array swing scanning aerial image, POS