An Image Registration Method Based on Shape Features of Regional Groups
2023 IEEE International Conference on Unmanned Systems (ICUS)(2023)
Abstract
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.
MoreTranslated text
Key words
battle damage image,image registration,regional feature
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined