[1]赵小强,岳宗达.一种面向图像拼接的快速匹配算法[J].南京理工大学学报(自然科学版),2016,40(02):165.[doi:10.14177/j.cnki.32-1397n.2016.40.02.006]
 Zhao Xiaoqiang,Yue Zongda.Fast matching algorithm for image mosaic[J].Journal of Nanjing University of Science and Technology,2016,40(02):165.[doi:10.14177/j.cnki.32-1397n.2016.40.02.006]
点击复制

一种面向图像拼接的快速匹配算法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
40卷
期数:
2016年02期
页码:
165
栏目:
出版日期:
2016-04-30

文章信息/Info

Title:
Fast matching algorithm for image mosaic
文章编号:
1005-9830(2016)02-0165-07
作者:
赵小强12岳宗达1
1.兰州理工大学 电气工程与信息工程学院,甘肃 兰州 730050; 2.甘肃省工业过程先进控制实验室,甘肃 兰州 730050
Author(s):
Zhao Xiaoqiang12Yue Zongda1
1.College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou 730050,China; 2.Key Laboratory of Gansu Advanced Control for Industrial Processes,Lanzhou 730050,China
关键词:
图像匹配 尺度不变特征变换 自适应非极大值抑制 Radon变换 随机抽样一致性
Keywords:
image matching scale invariant feature transform adaptive non-maxima suppression Radon transform random sample consistency
分类号:
TP751.1
DOI:
10.14177/j.cnki.32-1397n.2016.40.02.006
摘要:
针对图像拼接中尺度不变特征变换(Scale invariant feature transform,SIFT)算法的计算复杂度高、实时性差和误匹配等问题,提出了一种基于自适应非极大值抑制(Adaptive non-maxima suppression,ANMS)的Radon-SIFT方法。首先采用SIFT特征检测提取初始特征点,并用ANMS对初始特征点进行优选,得到分布均匀的特征点集; 在特征区域内做一系列直线,以这些直线上的Radon变换值作为特征描述符,以欧氏距离为度量准则进行特征匹配,然后采用随机抽样一致性(Random sample consistency,RANSAC)算法剔除误匹配点,从而提高了算法的正确匹配率和运算速率。仿真结果表明,该文算法具有较高的精度和较强的鲁棒性,且运算量少,实时性强。
Abstract:
Aiming at the problems of the large computation,the poor real-time and the mismatching of the scale invariant feature transform(SIFT)algorithm for image mosaic,a Radon-SIFT method based on the adaptive non-maxima suppression(ANMS)is proposed here.Firstly,this method uses feature detector of SIFT to extract initial feature points,and then the initial feature points are preferred by ANMS,so the feature point set of uniform distribution is obtained.Secondly,series of lines are made in the feature area.Image Radon transform integral values on the lines are adopted as feature vector descriptors and the features are matched by the measure criterion of the Euclidean distance.The Random sample consistency(RANSAC)algorithm is used to eliminate mismatching points and the computation speed and the correct matching rate are improved.Simulation results show that the proposed algorithm has the higher accuracy and robustness,and the amount of its arithmetic operation is reduced.

参考文献/References:

[1] Brown L G,A survey of image registration techniques[J].ACM Computing Surveys,1992,24(4):325-376.
[2]常琳,金光,杨秀彬.航天TDI CCD相机成像拼接快速配准算法设计与分析[J].光学学报,2014,34(5):0511001-1-0511001-9.
Chang Lin,Jin Guang,Yang Xiubin.Fast registration algorithm design and analysis of TDI CCD camera assembly imaging[J].Acta Optica Sinica,2014,34(5):0511001-1-0511001-9.
[3]王玉亮,廖文和,沈建新.基于快速鲁棒特征的眼底图像自动配准与拼接[J].南京理工大学学报,2012,36(1):79-85.
Wang Yuliang,Liao Wenhe,Shen Jianxin.Automatic fundus image registration and mosaic based on speed up robust features[J].Journal of Nanjing University of Science and Technology,2012,36(1):79-85.
[4]刘纪红,张倩,郭晴.基于SIFT的软骨切片电镜图像拼接算法[J].东北大学学报,2014,35(6):785-789.
Liu Jihong,Zhang Qian,Guo Qing.Electron microscope cartilage slicing image stitching algorithm based on SIFT[J].Journal of Northeastern University,2014,35(6):785-789.
[5]Mikolajczyk K,Schmid C.A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[6]Lowe D G.Object recognition from local scale-invariant features[C]//Proceedings of International Conference on Computer Vision.Corfu,Greece:IEEE,1999:1150-1157.
[7]Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[8]刘士荣,吴楚,张波涛,等.基于极线约束SIFT特征和粒子滤波的目标跟踪算法[J].上海交通大学学报,2014,48(7):1026-1038.
Liu Shirong,Wu Chu,Zhang Botao,et al.A tracking algorithm based on SIFT feature and particle filter with epipolar constraint[J].Journal of Shanghai Jiao Tong University,2014,48(7):1026-1038.
[9]Ke Y,Sukthankar R.PCA-SIFT:A more distinctive representation for local image descriptors[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D C,US:IEEE,2004(2):506-513
[10]颜雪军,赵春霞,袁夏.2DPCA-SIFT:一种有效的局部特征描述方法[J].自动化学报,2014,40(4):675-682.
Yan Xuejun,Zhao Chunxia,Yuan Xia.2DPCA-SIFT:An efficient local feature descriptor[J].ACTA Automatica Sinica,2014,40(4):675-682.
[11]曾峦,王元钦,谭久彬.改进的SIFT特征提取和匹配算法[J].光学精密工程,2011,19(6):1391-1397.
Zeng Luan,Wang Yuanqin,Tan Jiubin.Improved algorithm for SIFT feature extraction and matching[J].Optics and Precision Engineering,2011,19(6):1391-1397.
[12]刘立,彭复员,赵坤,等.采用简化SIFT算法实现快速图像匹配[J].红外与激光工程,2008,37(1):181-184.
Liu Li,Peng Fuyuan,Zhao Kun,et al.Simplified SIFT algorithm for fast image matching[J].Infrared and Laser Engineering,2008,37(1):181-184.
[13]于丽莉,戴青.一种改进的SIFT特征匹配算法[J].计算机工程,2011,37(2):210-212.
Yu Lili,Dai Qing.Improved SIFT feature matching algorithm[J].Computer Engineering,2011,37(2):210-212.
[14]Song R,Szymanski J.Well-distributed SIFT features[J].Electronics Letters,2009,45(6):308-310.
[15]许晓帆,王毅,王永泉.基于非极大值抑制的SIFT改进算法[J].电子设计工程,2014,22(18):180-182.
Xu Xiaofan,Wang Yi,Wang Yongquan.Improved SIFT algorithm based on adaptive non-maximun suppression[J].Electronic Design Engineering,2014,22(18):180-182.
[16]Petrou K A.The trace transform and its application[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(8):811-828.
[17]Fischler M A,Bolles R C.Random sample consensus:A paradigm for model fitting with applications to image analysis and automated cartography[J].Communi-cations of the ACM,1981,24(6):381-395.

相似文献/References:

[1]茅正冲,黄舒伟.基于结构化判别稀疏表示的目标跟踪[J].南京理工大学学报(自然科学版),2018,42(03):271.[doi:10.14177/j.cnki.32-1397n.2018.42.03.003]
 Mao Zhengchong,Huang Shuwei.Structured discriminant sparse representation based object tracking[J].Journal of Nanjing University of Science and Technology,2018,42(02):271.[doi:10.14177/j.cnki.32-1397n.2018.42.03.003]

备注/Memo

备注/Memo:
收稿日期:2015-09-07 修回日期:2015-12-07
基金项目:国家自然科学基金(51265032; 61263003); 甘肃省基础研究创新群体(1506RJIA031)
作者简介:赵小强(1969-),男,博士,教授,主要研究方向:生产调度建模与优化算法、故障诊断、图像处理,E-mail:xqzhao@lut.cn。
引文格式:赵小强,岳宗达.一种面向图像拼接的快速匹配算法[J].南京理工大学学报,2016,40(2):165-171.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2016-04-30