Laser & Optoelectronics Progress, Volume. 56, Issue 1, 011006(2019)
Image Registration Method Based on Accelerated Segmentation Feature Optimization
Figures & Tables(12)
Fig. 2. Skewed edge pseudo corner. (a) Edge; (b) decision circle of p; (c) detection result of p
Table 1. Reprojection error of homography pixel
View tableTable 1. Reprojection error of homography pixel
Reprojection error Registration method SIFT algorithm BRIEF algorithm FREAK algorithm Proposed algorithm Number of original image keypoints 10578 5316 5048 2696 Number of registered image keypoints 11985 4672 4749 2392 Matching pairs 2189 572 667 144 Inner points 1507 437 649 117 Total projection error 1592 989.805 1488.871 116.729 Mean projection error 1.0564 2.2650 2.2941 0.9976
Table 2. Running time of each phase of registrationms
View tableTable 2. Running time of each phase of registrationms
Registration algorithm Keypoint extraction Feature description Feature matching Image registration Whole process SIFT algorithm 0.350614 1.087653 2.0458 0.508946 3.993013 BRIEF algorithm 0.032061 0.870168 1.0538 0.469765 2.49071 FREAK algorithm 0.031493 0.353148 1.0049 0.422904 2.07261 Proposed algorithm 0.468860 0.207120 0.4878 0.287049 1.90601
Tools
Get Citation
Copy Citation Text
Jia Li, Ping Duan, Yongxiang Yao, Feng Cheng. Image Registration Method Based on Accelerated Segmentation Feature Optimization[J]. Laser & Optoelectronics Progress, 2019, 56(1): 011006
Paper Information
Category: Image Processing
Received: May. 18, 2018
Accepted: Jul. 24, 2018
Published Online: Aug. 1, 2019
The Author Email: Ping Duan (dpgiser@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20