[1]周露露,路 纲,田艳玲.拓扑约束优化特征匹配的图像配准与拼接[J].计算机技术与发展,2019,29(06):37-41.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 008]
　ZHOU Lu-lu,LU Gang,TIAN Yan-ling.Image Registration and Stitching of Feature Matching of Topology Constraints Optimization[J].,2019,29(06):37-41.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 008]
点击复制

拓扑约束优化特征匹配的图像配准与拼接()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年06期
页码:
37-41
栏目:
智能、算法、系统工程
出版日期:
2019-06-10

文章信息/Info

Title:
Image Registration and Stitching of Feature Matching of Topology Constraints Optimization
文章编号:
1673-629X(2019)06-0037-05
作者:
周露露; 路 纲; 田艳玲
陕西师范大学 计算机科学学院,陕西 西安 710000
Author(s):
ZHOU Lu-lu; LU Gang; TIAN Yan-ling
School of Computer Science,Shaanxi Normal University,Xi’an 710000,China
关键词:
特征匹配; 图像拼接; 尺度不变特征变换; 拓扑约束; 重复率; 辨识率
Keywords:
feature matching; image stitching; scale invariant feature transform; topological constraint; repetition rate; recognition rate
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 06. 008
摘要:
对于尺度不变特征变换方法(SIFT)应用的图像拼接过程中存在错误匹配的问题,结合拓扑学理论,提出一种去除错误匹配的 SIFT 改进算法。 定义特征点间的拓扑关系,对于两幅图像的特征点间拓扑关系做异或运算得到判断矩阵,获得拓扑关系完全相同的特征点集,有效提高特征点的匹配精度。 另外,提出利用特征点重复率、特征点辨识率以及图像拼接运行时间三个指标对改进后的算法进行评价,并与尺度不变特征变换算法等进行对比。 数据分析与拼接结果表明,使用拓扑约束去除错误匹配后特征点的重复率为 98.6%,与待拼接图像中具有最多重复的特征点,从而达到了提高匹配的准确性和鲁棒性以及图像拼接精度的效果,拓扑约束后特征点辨识率达到0.83 的平均水平,算法去除错误匹配对,提高了特征点的匹配正确性。 该算法继承了 SIFT 算法强壮的稳健性,进一步提高了图像拼接的准确性和真实性。
Abstract:
In view of the fact that there are a lot of mismatches in the application of scale invariant feature transform (SIFT) in image stitching,we propose an improved SIFT algorithm to eliminate mismatch based on topology theory. Defining topological structure between feature points,the difference or operation of topological relation between feature points of two images is used to obtain the judgment matrix,and the set of feature points with the same topological relation is obtained,which effectively improves the matchingaccuracy of feature points. In addition,we evaluate the improved algorithm from three indexes:the repetition rate of feature points,the recognition rate of feature points and the running time of image stitching,and make a comparison with the scale-invariant feature transformation algorithm. The results of data analysis and stitching show that the repetition rate of the feature points removed by topology constraints is 98. 6%,which is the most repetitive feature points in the image to be stitched,so that the accuracy and robustness of the matching can be improved. In order to improve the accuracy of image stitching,the recognition rate of feature points reaches an average level of 0.83 after topological constraints. The algorithm removes the error matching pairs,improves the correctness of feature points matching and inherits the robust robustness of SIFT algorithm. The accuracy and authenticity of image stitching are further improved.

相似文献/References:

[1]冉柯柯 王继成.基于比值法图像拼接的等比例改进算法[J].计算机技术与发展,2010,(02):5.
　RAN Ke-ke,WANG Ji-cheng.An Improved Mosaic Algorithm Based on Ratio Matching Using Geometric Proportion[J].,2010,(06):5.
[2]杨丹 孙向南 张小洪.一种分层渐进匹配的鲁棒估计算法[J].计算机技术与发展,2009,(06):36.
　YANG Dan,SUN Xiang-nan,ZHANG Xiao-hong.A Robust Estimating Algorithm Based on Layered Progressive Matching[J].,2009,(06):36.
[3]季诚 欧阳宁 张彤.基于视频片断的全景图拼接[J].计算机技术与发展,2009,(09):239.
　JI Cheng,OUYANG Ning,ZHANG Tong.Panorama Stitching in Video Sequences[J].,2009,(06):239.
[4]叶永凯 禹继国 顾耀林 曹小龙.基于特征匹配的渐变纹理图像合成算法[J].计算机技术与发展,2009,(11):42.
　YE Yong-kai,YU Ji-guo,GU Yao-lin,et al.Texture Synthesis with Local Variation Based on Feature Matching[J].,2009,(06):42.
[5]李云霞 曾毅 钟瑞艳 郭涛.基于SIFT特征匹配的图像拼接算法[J].计算机技术与发展,2009,(01):43.
　LI Yun-xia,ZENG Yi,ZHONG Rui-yan,et al.Algorithm of Image Stitching Based on SIFT Feature Matching[J].,2009,(06):43.
[6]蔡丽欢 廖英豪 郭东辉.图像拼接方法及其关键技术研究[J].计算机技术与发展,2008,(03):1.
　CAI Li-huan,LIAO Ying-hao,GUO Dong-hui.Study on Image Stitching Methods and Its Key Technologies[J].,2008,(06):1.
[7]侯顺风 张佑生 江涛.块拼接纹理合成算法在图像拼接中的应用[J].计算机技术与发展,2007,(07):247.
　HOU Shun-feng,ZHANG You-sheng,JIANG Tao.Application of Patch- Based Texture Synthesis in Image Creating[J].,2007,(06):247.
[8]江良洲 龙凤.磨粒图像自动拼接与预处理技术研究[J].计算机技术与发展,2010,(10):250.
　JIANG Liang-zhou,LONG Feng.Wear Particle Image Mosaicing and Preprocessing Technique Research for Ferrography[J].,2010,(06):250.
[9]欧书琴 李新华 孔颉 陈军.基于非下采样Contourlet变换的彩色图像拼接算法[J].计算机技术与发展,2010,(11):37.
　OU Shu-qin,LI Xin-hua,KONG Jie,et al.Color Image Mosaicing Algorithm Based on Nonsubsampled Contourlet Transform[J].,2010,(06):37.
[10]杨阳 王民 王稚慧.道路交通现场中改进的图像拼接方法[J].计算机技术与发展,2011,(07):105.
　YANG Yang,WANG Min,WANG Zhi-hui.Improved Image Mosaic Method in Road Traffic Scene[J].,2011,(06):105.

更新日期/Last Update: 2019-06-10