An Image Registration Method Based on Shape Features of Regional Groups

Zepeng Wang, Fang Wu, Yixun Liu, Chao Tang, Derong Chen, Jiulu Gong*

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Aiming at the problem that local features such as midpoints, lines and so on in images before and after damage are severely changed, an image registration method based on shape features of regional building groups is proposed. Firstly, the building area is extracted by segmentation. Then a grouping strategy is designed to group building areas. The feature descriptor of regional group is constructed by using invariant moments, so that the feature descriptor is invariant with translation, rotation and scaling. Finally, the registration is completed by matching the invariant moments. In this paper, the images from the Russia-Ukraine war are used for registration experiments. The experimental results show that compared with the existing methods, the proposed method has a higher feature matching rate and can complete the registration of pre-damage images and post-damage images.

源语言英语
主期刊名Proceedings of 2023 IEEE International Conference on Unmanned Systems, ICUS 2023
编辑Rong Song
出版商Institute of Electrical and Electronics Engineers Inc.
1464-1469
页数6
ISBN(电子版)9798350316308
DOI
出版状态已出版 - 2023
活动2023 IEEE International Conference on Unmanned Systems, ICUS 2023 - Hefei, 中国
期限: 13 10月 202315 10月 2023

出版系列

姓名Proceedings of 2023 IEEE International Conference on Unmanned Systems, ICUS 2023

会议

会议2023 IEEE International Conference on Unmanned Systems, ICUS 2023
国家/地区中国
Hefei
时期13/10/2315/10/23

指纹

探究 'An Image Registration Method Based on Shape Features of Regional Groups' 的科研主题。它们共同构成独一无二的指纹。

引用此