计算机与现代化 ›› 2023, Vol. 0 ›› Issue (04): 56-61.

• 图像处理 • 上一篇    下一篇

利用词袋模型估计尺度差异的异源影像匹配方法

  

  1. (河海大学地球科学与工程学院,江苏 南京 211100)
  • 出版日期:2023-05-09 发布日期:2023-05-09
  • 作者简介:喻鹏飞(1998—),男,湖北荆门人,硕士研究生,研究方向:数字图像处理,计算机视觉,摄影测量与遥感,E-mail: 853436799@qq.com; 通信作者:李浩(1964—),男,江苏江阴人,教授,博士,研究方向:摄影测量,计算机视觉及影像地理信息系统,E-mail: lihao@hhu.edu.cn; 何秀凤(1962—),女,江苏泰州人,教授,博士,研究方向:GNSS卫星导航定位,InSAR技术和变形监测,E-mail: xfhe@hhu.edu.cn; 洪振华(1998—),男,江西上饶人,硕士研究生,研究方向:数字图像处理,摄影测量,E-mail: 14779862194@qq.com; 刘宇宸(1999—),女,山东菏泽人,硕士研究生,研究方向:深度学习,遥感技术与应用,E-mail: 2604089738@qq.com。
  • 基金资助:
    国家自然科学基金重点项目(41830110)

YU Peng-fei, LI Hao, HE Xiu-feng, HONG Zhen-hua, LIU Yu-chen

  1. (School of Earth Science and Engineering, Hohai University, Nanjing 211100, China)
  • Online:2023-05-09 Published:2023-05-09

摘要: 针对影像匹配中因影像间尺度差异过大导致同名特征点数目不足甚至误匹配的问题,提出一种利用词袋模型估计尺度差异的异源影像SIFT匹配方法(BS-SIFT)。该方法通过提前感知待匹配影像间存在的尺度差异,将异源影像匹配转化为在同一尺度上开始,提高匹配的内点率,进而增加大尺度差异影像的匹配点数量。首先,通过将连续变化的不同尺度影像特征点在特征空间聚类,并将各尺度影像特征重分配到特征中心,得到各尺度下的特征分布关系;然后,结合影像特征中心的空间信息熵定权,得到待匹配影像间尺度描述符;最后,分析尺度描述符距离分布可得到最佳影像尺度差。实验结果表明,本文提出的BS-SIFT算法在超过10倍尺度差的影像匹配上仍能取得较好结果,相较于经典的SIFT算法,本文算法在取得较高效率的同时可得到更多的同名特征点,匹配正确率至少提升9个百分点,最大可达37个百分点。

关键词: 影像匹配, 尺度不变换特征, 词袋模型; 大尺度差异; 特征描述; 航空航天影像

Abstract: Aiming at the problem that the number of homonymous feature points is insufficient or even mismatched due to the large-scale difference between images in image matching, this paper proposes a heterologous image SIFT matching method (BS-SIFT) using word bag model to estimate the scale difference. By sensing the scale difference between the images to be matched in advance, this method transforms the heterogenous image matching into starting at the same scale, improves the interior point rate of matching, and then increases the number of matching points of large-scale difference images. Firstly, by aggregating continuously changing image feature points of different scales in the feature space and reallocating image features of each scale to feature center, the feature distribution relationship of each scale is obtained. Secondly, the scale descriptor between images to be matched is obtained by combining the spatial information entropic weighting of image feature center. Finally, the best image scale difference can be obtained by analyzing the distance distribution of scale descriptors. The experimental results show that the BS-SIFT algorithm proposed in this paper can still achieve good results in image matching with a scale difference of more than 10 times. Compared with the classical SIFT algorithm, the algorithm proposed in this paper can significantly obtain more homonymous feature points while achieving higher efficiency, and the matching accuracy is improved by at least 9 percentage points and up to 37 percentage points.

Key words: image matching, SIFT, word bag model, large scale difference, feature description, aerospace image