[1]刘 敏,周 聪,汤靖博.基于SIFT图像配准算法优化研究[J].湖北工业大学学报,2020,(2):32-36.
　LIU Min,ZHOU Cong,TANG Jing Bo.Research on Image Registration Algorithm Optimization Based on SIFT[J].,2020,(2):32-36.
点击复制

基于SIFT图像配准算法优化研究()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2020年第2期
页码:
32-36
栏目:
出版日期:
2020-04-30

文章信息/Info

Title:
Research on Image Registration Algorithm Optimization Based on SIFT
文章编号:
1003-4684(2020)02-0032-05
作者:
刘  敏;  周  聪;  汤靖博
湖北工业大学太阳能高效利用湖北省协同创新中心， 湖北 武汉 430068
Author(s):
LIU Min;  ZHOU Cong;  TANG Jing Bo
Hubei Collaborative Innovation Center for High-efficiency Utilization of Solar Energy, Hubei Univ. of Tech., Wuhan 430068, China
关键词:
图像配准;  SIFT;  改进RANSAC;  相似性评价;  精匹配
Keywords:
image registration;  SIFT;  improved RANSAC;  similarity of evaluation;  fine matching
分类号:
TP391
文献标志码:
A
摘要:
为了满足在图像配准过程中对于准确度和稳定性的要求，提出一种基于SIFT和改进的RANSAC图像配准算法。首先采用SIFT算法进行特征点提取和最近邻匹配方法进行粗匹配，然后对RANSAC算法进行改进，对两幅图像中关键点相似性的评价函数进行改进和优化，实现关键点对的精准匹配，最后进行图像配准。实验表明，算法能够提高图像匹配的准确度同时降低图像匹配时间，具有一定的适用性。
Abstract:
In order to meet the requirements of real-time precision and stability in image registration process, this paper proposes an algorithm based on SIFT and improved RANSAC image registration. Firstly, this work used the SIFT algorithm to extract the feature points and used nearest neighbor matching method for rough matching. Then the paper improved the RANSAC algorithm, so as to improve and optimize the evaluation function of similarity of key points in the two images, and to achieve precise matching of key points. Finally, image registration was performed. Experiments show that the proposed algorithm can improve the accuracy of image matching and reduce image matching time, and has certain applicability.

参考文献/References:

[1]Adel E , Elmogy M , Elbakry H . Image stitching based on feature extraction techniques: a survey[J]. International Journal of Computer Applications, 2014, 99(6):1-8.
[2]Zhang F , Liu F . Parallax-tolerant image stitching[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2014:3262-3269.
[3]Barbara Zitová, Flusser J . Image registration methods: a survey[J]. Image and Vision Computing, 2003, 21(11):977-1000.
[4]Wang Z , Kieu H , Nguyen H , et al. Digital image correlation in experimental mechanics and image registration in computer vision: Similarities, differences and complements[J]. Optics and Lasers in Engineering, 2015, 65:18-27.
[5]Liu X , Tao X , Ge N . Fast remote-sensing image registration using priori information and robust Feature extraction[J]. Tsinghua Science and Technology, 2016, 21(5):552-560.
[6]Oliveira F P M , Tavares J M R S . Medical image registration: a review[J]. Computer Methods in Biomechanics and Biomedical Engineering, 2014, 17(2):73-93.
[7]吴丽萍, 胡郁. 柱面全景图图像拼接中图像平滑的虚拟现实技术[J]. 科学技术与工程, 2017(31):277-282.
[8]Huang L, Li Z. Feature-based image registration using the shape context[J]. International Journal of Remote Sensing, 2010, 31(8):2169-2177.
[9]Lowe D G . Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[10] 甄艳, 刘学军, 王美珍. 一种改进RANSAC的基础矩阵估计方法[J]. 测绘通报, 2014(4):39-43.
[11] Shi G, Xu X, Dai Y. SIFT feature point matching based on improved RANSAC algorithm[C]// International Conference on Intelligent Human-machine Systems & Cybernetics. 2013:474-477.
[12] Jie H, Fei W, Yu G, et al. An improved RANSAC registration algorithm based on region covariance descriptor[C]// Chinese Automation Congress, 2015:746-751.
[13] 王瑜, 禹秋民. 基于曲率特征与改进的RANSAC策略的图像匹配算法[J]. 计算机工程与设计, 2018, 39(12):199-204.

备注/Memo

备注/Memo:
［收稿日期］ 2019-12-19
［基金项目］ 国家自然科学基金面上项目（61471162）；湖北省科技支撑计划项目（2015BAA115）
［第一作者］ 刘    敏(1979-)， 女， 河南周口人，湖北工业大学副教授，研究方向为计算机视觉
［通信作者］ 周    聪(1991-)， 男， 湖北咸宁人，湖北工业大学硕士研究生，研究方向为计算机视觉
更新日期/Last Update: 2020-05-13