Didi Zhao, Jiahui Li, Fenli Tan, Chenxin Zeng, Yiqun Ji. Image Registration Algorithm Based on Smoothness Constraint and Cluster Analysis[J]. Laser & Optoelectronics Progress, 2021, 58(12): 1210010
- Laser & Optoelectronics Progress
- Vol. 58, Issue 12, 1210010 (2021)
Fig. 1. Image registration process of our algorithm
Fig. 2. Schematic of the SC
Fig. 3. Screening of initial matches based on SC. (a) Selection of reliable matches; (b) checking the consistency of the global zoom scale; (c) local geometric constraints
Fig. 4. RANSAC algorithm based on cluster analysis
Fig. 5. Selection process of optimal inliers. (a) Tentative inliers; (b) cluster analysis results of tentative inliers; (c) distribution quality of the luster center
Fig. 6. Testing images. (a) Blur change; (b) viewpoint change; (c) rotation and scale changes; (d) illumination change; (e) rotation change; (f) scale change
Fig. 7. Effect of different parameters on the purification performance of initial matches. (a) Number of inliers with different α; (b) ratio of inliers with different α; (c) number of inliers with different β; (d) ratio of inliers with different β
Fig. 8. Images pairs for homography estimation
|
Table 1. Performances of different algorithms
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20