[1]介 军,李智杰,姚 鹏.改进的RANSAC匹配点提纯算法[J].西安建筑科技大学学报:自然科学版,2013,45(06):896-901.[doi:10.15986/j.1006-7930.2013.06.025]
　JIE Jun,LI Zhi-jie,YAO Peng.Improved RANSAC algorithm of matched points purifying[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2013,45(06):896-901.[doi:10.15986/j.1006-7930.2013.06.025]
点击复制

改进的RANSAC匹配点提纯算法()
分享到：

西安建筑科技大学学报:自然科学版[ISSN:1006-7930/CN:61-1295/TU]

卷:
45
期数:
2013年06期
页码:
896-901
栏目:
出版日期:
2013-12-31

文章信息/Info

Title:
Improved RANSAC algorithm of matched points purifying
文章编号:
1006-7930(2013)06-0896-06
作者:
介 军1; 李智杰1; 姚 鹏2
(1.西安建筑科技大学信息与控制工程学院,陕西 西安710055; 2.长庆油田分公司机械制造总厂,陕西 西安 710201)
Author(s):
JIE Jun1; LI Zhi-jie1; YAO Peng2
(1.School of Information and Control Engineering, Xian Univ. of Arch.& Tech., Xian 710055, China; 2.Changqing Oilfield Company, Machine Manufacture Plant, Xian 710201, China)
关键词:
角点检测; 图像匹配; 视差梯度; RANSAC
Keywords:
corner detection;  image matching;  disparity constraint;  RANSAC
分类号:
TP 391.413
DOI:
10.15986/j.1006-7930.2013.06.025
文献标志码:
A
摘要:
针对在图像匹配中,随机抽样一致性(RANSAC)算法对匹配点提纯存在计算量大、效率低的问题,采用将基本矩阵作为模型参数估计对象的方法,对RANSAC匹配点提纯算法进行了改进.在改进的算法中,运用Bucket分割技术抽取粗匹配点对,进行两幅图像的检测角点和粗匹配,利用视差梯度对匹配点样本预检验.实验结果表明,此方法在保证较高精度和鲁棒性的情况下,运算量大幅度减少,提高了图像匹配的速度.
Abstract:
Improvement has been made for RANSAC algorithm of matched points purifying in the image matching process by using fundamental matrix as object of model parameter in finding a solution to the problem with the large amount of calculation and the low efficiency that energy. By extracting rough matched points in sub-block generate from Bucketing techniques, algorithm test two images with corner detection and rough matching has also been improved. Moreover, it pretests the sample of matching points using disparity constraint. The experiment shows that this algorithm reduces the amount of computation largely, improves the speed of image matching and keeps high precision and robust

参考文献/References:

[1] ZHU Q, WU B, XU Z.Seed point selection method for triangle con strainedimage matching propagation [J].IEEE Geoscienceand Remote Sensing Letters, 2006, 3(2) : 207-211.
[2] 曲 天伟, 安 波, 陈桂兰. 改进的 RANSAC 算法在图像配准中的应用 [J]. 计 算机应用 ,2010, 30(7) : 1849-1851.
QU Tian-wei, AN Bo, CHEN Gui-lan.Application ofimproved RANSAC algorithm to image registration[J].Journal of Computer Applications,2010, 30(7) : 1849-1851.
[3] HARRIS C, STEPHENS M.Acombinedcornerandedge detection [J].Image Vision Computing, 1998, 15(6) :121-127.
[4] 徐 玮. 一种基于角点匹配的视图合成方法[J]. 系 统仿真学报,2007,19(14) :3263-3265.
XU Wei.Corner Matching-based Approach of View Synthesis[J].Journal of System Simulation, 2007,19 (14) :3263-3265.
[5] FISCHLER M A, BOLLES R C.Randomsampleconsensus: Aparadigmfor modelfitting withapplicationstoim-ageanalysis andautomatedcartography[J].CACM, 1981, 24(6) :381-395.
[6] HARTLEY R, ZISSERMAN A.Multiple View Geometryin Computer Vision [M].2nded.Cambridge Universi-ty , 2003.
[7 ] 陈 付幸 , 王润生. 基于预检验的快速随机抽样一致性算法 [J]. 软件学报,2005,16(8) :1431-1437.
CHEN Fu-xing, WANG Run-sheng.Fast RANSAC with Preview Model Parameters Evaluation[J].Journal ofSoftware,2005,16(8) :1431-1437.
[8] 马 颂德, 张正友. 计算机视觉[M]. 北京: 科学出版社,1998:82-83.
MA Song-de,ZHANG Zheng-you.Computervision[M].Beijing: Science Press,1998:82-83.
[9] CHOUKROUN A, CHARVILLAT V.Bucketingtechniquesinrobustregressionforcomputervision[C]∥In Pro-ceedings of SCIA2003Lecture Notesin Computer Science, Halmsted Sweden, 2003, 2749:609-616.
[10] 黄 以君, 刘伟军. 基于 LQS 的基本矩阵计算方法[J]. 中国图象图形学报,2009,14(10) :2069-2073.
HUANG Yi-jun,LIU Wei-jun.A Methodfor Fundamental Matrix Estimation Using LQS[J].JournalofImageandGraphics, ,2009,14(10) :2069-2073.

相似文献/References:

[1]刘金颂,张庆阳,原思聪(.基于SIFT 和LTP 的图像匹配方法[J].西安建筑科技大学学报:自然科学版,2014,46(05):762.[doi:10.15986/j.1006-7930.2004.]
　LIU Jinsong,ZHANG Qingyang,YUAN Sicong.Image matching using SIFT and rotation invariant uniform LTP[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2014,46(06):762.[doi:10.15986/j.1006-7930.2004.]

备注/Memo

备注/Memo:
收稿日期:2013-01-14 修改稿日期:2013-11-25
基金项目:国家自然科学基金资助项目(50878176)
作者简介:介 军(1971-),男,陕西彬县人,工程师,硕士,主要从事计算机应用和教学研究.
更新日期/Last Update: 2015-10-05