Relative Motion Recovery Reconstruction Algorithm for Fixed Cameras
Aiming at the problem that the structure from motion algorithm needs to change the position of the camera in the process of camera shooting, we utilize the relationship between the relative motion of the object and the camera to obtain the image sequence containing the multi-angle view of the object. A relative structure from motion is designed and realized by locating the region where the object is located in the image sequence and constraining the applicable range of feature point extraction. The experimental results show that the SFRM algorithm is applicable to the fixed position of the camera, and can increase the proportion of matched pairs located in the object region from 32% to 84% of the total number of matched pairs, and improve the time efficiency by 38.29% compared with the traditional SFM algorithm, thus successfully expanding the applicability of the SFM algorithm.
Authors
- Bing Li (ORCID: https://orcid.org/0000-0002-5055-8921)
- Yirui Wang (ORCID: https://orcid.org/0000-0002-9804-8736)
- Yibo Zhen
Institutions
- Harbin Engineering University (CN)
Publication Details
- Published
- 2024-08-04
- DOI
- https://doi.org/10.1109/icma61710.2024.10632905
- Primary Topic
- Advanced Vision and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00