基于系统论匹配准则的尺度不变特征变换的图像自动拼接研究
|
摘要
基于特征点的图像拼接不仅不易受光照、旋转等因素影响,而且还有利于提高速度,是目前图像拼接的主流方向。尺度不变特征变换(SIFT)是目前比较成熟的一种角点检测算法,但是其特征点匹配问题仍然没有得到很好的解决。从系统相似的角度出发,提出了基于系统相似论的匹配准则,并将新匹配准则与传统的匹配准则进行了对比,指出了传统匹配准则存在的问题,测试了新准则匹配的精度和速度,分析了新准则能够取得更高精度的原因,并据新准则成功地检测了待拼接图像中的匹配角点,然后用改进的样本一致性算法计算出仿射变换的投影矩阵,并用Levenberg-Marquardt(L-M)算法对其求精,最终实现了图像的自动拼接。最后给出了全景相机图像的拼接结果,并对新的匹配准则给出了进一步的分析讨论。
The image stitching based on feature point is not only invulnerable to the light,rotation and other factors,but also helpful to increase efficiency.It has become one of the most attended methods.Scale invariant feature transform(SIFT) is a better coner extraction algorithm,but there are still some problems in the matching step.A new matching principle based on system similarity theory was proposed,and then it was compared with the traditional matching principle.The problems with tradtional matching principle was pointed out,and also the precision and speed of the new principle was tested,and the reason why the new principle get higher precision was analysed.By the new principle the matching features were detected successfully.And then,the transform matrix was calculated by the progressive sample consistency algorithm.Further more, it was optimized by the Levenberg-Marquardt(L-M) algorithm,and finally automatic image stitching was realized.At last, the stiching result of panorama camera image was given,further discussion about the new matching principle was also given in the end of the paper.
The image stitching based on feature point is not only invulnerable to the light,rotation and other factors,but also helpful to increase efficiency.It has become one of the most attended methods.Scale invariant feature transform(SIFT) is a better coner extraction algorithm,but there are still some problems in the matching step.A new matching principle based on system similarity theory was proposed,and then it was compared with the traditional matching principle.The problems with tradtional matching principle was pointed out,and also the precision and speed of the new principle was tested,and the reason why the new principle get higher precision was analysed.By the new principle the matching features were detected successfully.And then,the transform matrix was calculated by the progressive sample consistency algorithm.Further more, it was optimized by the Levenberg-Marquardt(L-M) algorithm,and finally automatic image stitching was realized.At last, the stiching result of panorama camera image was given,further discussion about the new matching principle was also given in the end of the paper.
引文
1 He Renfang,Wang Cheng,Yang Wenbing.Image matching based on chaos-genetic algorithms[J].Infrared and Laser Engineering,2003,32(1):13-16何仁芳,王承,杨文兵.基于混沌遗传算法的图像匹配[J].红外与激光工程,2003,32(1):13-16
2 Zhang Ruijuan,Zhang Jianqi,Yang Cui et al..Study on color image registration technique based on CSIFT[J].Acta Optica Sinica,2008,28(11):2097-2103张锐娟,张建奇,杨翠等.基于CSIFT的彩色图像配准技术研究[J].光学学报,2008,28(11):2097-2103
3 Yuan Weiqi,Xu Lu,Lin Zhonghua.Iris identification method based on gray surface matching[J].Acta Optica Sinica,2006, 26(10):1537-1542苑玮琦,徐露,林忠华.基于灰度曲面匹配的虹膜识别方法[J].光学学报,2006,26(10):1537-1542
4 Yang Zhanlong,Guo Baolong.Image mosaic technique based on pseudo-Zernike moments of interest points[J].Chinese J. Lasers,2007,34(11):1548-1552杨占龙,郭宝龙.基于兴趣点伪泽尼克矩的图像拼接[J].中国激光,2007,34(11):1548-1552
5 Li Haibin,Zhang Qiang.A new stereo matching Algorithm based on sub-line segment[J].Acta Optica Sinica,2007,27(5): 907-912李海滨,张强.一种新的基于子线段的立体匹配算法[J].光学学报,2007,27(5):907-912
6 D.G.Lowe.Object recognition from local scale-invariant features[C].International Conference on Computer Vision, 1999,2:1150-1157
7 D.G.Lowe.Distinctive image features from scale invariant keypoints[J].J.Computer Vision,2004,60(2):91-110
8 Xie Fan,Qin Shiyin.Wide baseline stereo vision matching approach for monocular mobile robot based on SIFT[J].Chinese J.Scientific Instrument,2008,29(11):2247-2252谢凡,秦世引.基于SIFT的单目移动机器人宽基线立体匹配[J].仪器仪表学报,2008,29(11):2247-2252
9 Wu Huilan.Liu Guodong,Liu Bingguo et al..Study on the circle center fast accurate locating technique based on the SIFT[J].J. Optoelectronics Laser,2008,19(11):1512-1515吴慧兰,刘国栋,刘炳国.基于SIFT算法的圆心快速精确定位技术研究[J].光电子·激光,2008,19(11):1512-1515
10 Liu Xiaojun,Yang Jie,Sun Jianwei et al..Image registration approach based on SIFT[J].Infrared and Laser Engineering, 2008,37(1):156-160刘小军,杨杰,孙建伟等.基于S1FT的图像配准方法[J].红外与激光工程,2008,37(1):156-160
11 Jonathan Klippenstein,Hong Zhang.Quantitative evaluation of feature extractors for visual SLAM[C].Proceedings of the Fourth Canadian Confermce on Computer and Robot Vision, 2007,157-164
12 Li Lingling,Li Cuihua,Zeng Xiaoming et al..An automatic image registration method based on SIFT and Harris-Aff ine features matching[J].Huazhong Univ.of Sci.& Technol. (Natural Science Edition),2008,36(8):13-16李玲玲,李翠华,曾晓明.基于Harris-Affine和SIFT特征匹配的图像自动配准[J].华中科技大学学报(自然科学版),2008, 36(8):13-16
13 Ji Hua,Wu Yuanhao,Sun Honghai.SIFT feature matching algorithm with global information[J].Optics and Precision Engineering,2009,17(2):439-444季华,吴元浩,孙宏海.结合全局信息的SIFT特征匹配算法[J].光学精密工程,2009,17(2):439-444
14 Zhou Suoyu.System Science Guide[M].BeiJing:Earthquake Press,1988周所宇.系统科学导引[M].北京:地震出版社,1988
15 Zhou Meili.Similar System[M].Beijing:Science and Technology Literature Press,1994.19-22周美丽.相似系统论[M].北京:科学与技术文化出版社,1994. 19-22
16 Guan Yi,Wang Xiaolong,Wang Qiang.Measurement of system similarity[C].Proc.of the 8th National Conference on Computntionnl Linguistics,2005,1 - 7关毅,王晓龙,王强.论系统相似度的度量[C].全国第八届计算语言学联合学术会议,2005,1-7
17 O.Chum,J.Matas.Matching with PROSAC progressive sample consensus[C].Proc.CVPR,2005,1:20-25
18 Gao Chao,Zhang Xin,Wang Yunli et al..Automatic stitching approach of aerial image sequence based on SIFT features[J]. Computer Applications,2007,27(11):2789-2792高超,张鑫,王云丽等.一种基于SIFT特征的航拍图像序列自动拼接方法[J].计算机应用,2007,27(11):2789-2792
2 Zhang Ruijuan,Zhang Jianqi,Yang Cui et al..Study on color image registration technique based on CSIFT[J].Acta Optica Sinica,2008,28(11):2097-2103张锐娟,张建奇,杨翠等.基于CSIFT的彩色图像配准技术研究[J].光学学报,2008,28(11):2097-2103
3 Yuan Weiqi,Xu Lu,Lin Zhonghua.Iris identification method based on gray surface matching[J].Acta Optica Sinica,2006, 26(10):1537-1542苑玮琦,徐露,林忠华.基于灰度曲面匹配的虹膜识别方法[J].光学学报,2006,26(10):1537-1542
4 Yang Zhanlong,Guo Baolong.Image mosaic technique based on pseudo-Zernike moments of interest points[J].Chinese J. Lasers,2007,34(11):1548-1552杨占龙,郭宝龙.基于兴趣点伪泽尼克矩的图像拼接[J].中国激光,2007,34(11):1548-1552
5 Li Haibin,Zhang Qiang.A new stereo matching Algorithm based on sub-line segment[J].Acta Optica Sinica,2007,27(5): 907-912李海滨,张强.一种新的基于子线段的立体匹配算法[J].光学学报,2007,27(5):907-912
6 D.G.Lowe.Object recognition from local scale-invariant features[C].International Conference on Computer Vision, 1999,2:1150-1157
7 D.G.Lowe.Distinctive image features from scale invariant keypoints[J].J.Computer Vision,2004,60(2):91-110
8 Xie Fan,Qin Shiyin.Wide baseline stereo vision matching approach for monocular mobile robot based on SIFT[J].Chinese J.Scientific Instrument,2008,29(11):2247-2252谢凡,秦世引.基于SIFT的单目移动机器人宽基线立体匹配[J].仪器仪表学报,2008,29(11):2247-2252
9 Wu Huilan.Liu Guodong,Liu Bingguo et al..Study on the circle center fast accurate locating technique based on the SIFT[J].J. Optoelectronics Laser,2008,19(11):1512-1515吴慧兰,刘国栋,刘炳国.基于SIFT算法的圆心快速精确定位技术研究[J].光电子·激光,2008,19(11):1512-1515
10 Liu Xiaojun,Yang Jie,Sun Jianwei et al..Image registration approach based on SIFT[J].Infrared and Laser Engineering, 2008,37(1):156-160刘小军,杨杰,孙建伟等.基于S1FT的图像配准方法[J].红外与激光工程,2008,37(1):156-160
11 Jonathan Klippenstein,Hong Zhang.Quantitative evaluation of feature extractors for visual SLAM[C].Proceedings of the Fourth Canadian Confermce on Computer and Robot Vision, 2007,157-164
12 Li Lingling,Li Cuihua,Zeng Xiaoming et al..An automatic image registration method based on SIFT and Harris-Aff ine features matching[J].Huazhong Univ.of Sci.& Technol. (Natural Science Edition),2008,36(8):13-16李玲玲,李翠华,曾晓明.基于Harris-Affine和SIFT特征匹配的图像自动配准[J].华中科技大学学报(自然科学版),2008, 36(8):13-16
13 Ji Hua,Wu Yuanhao,Sun Honghai.SIFT feature matching algorithm with global information[J].Optics and Precision Engineering,2009,17(2):439-444季华,吴元浩,孙宏海.结合全局信息的SIFT特征匹配算法[J].光学精密工程,2009,17(2):439-444
14 Zhou Suoyu.System Science Guide[M].BeiJing:Earthquake Press,1988周所宇.系统科学导引[M].北京:地震出版社,1988
15 Zhou Meili.Similar System[M].Beijing:Science and Technology Literature Press,1994.19-22周美丽.相似系统论[M].北京:科学与技术文化出版社,1994. 19-22
16 Guan Yi,Wang Xiaolong,Wang Qiang.Measurement of system similarity[C].Proc.of the 8th National Conference on Computntionnl Linguistics,2005,1 - 7关毅,王晓龙,王强.论系统相似度的度量[C].全国第八届计算语言学联合学术会议,2005,1-7
17 O.Chum,J.Matas.Matching with PROSAC progressive sample consensus[C].Proc.CVPR,2005,1:20-25
18 Gao Chao,Zhang Xin,Wang Yunli et al..Automatic stitching approach of aerial image sequence based on SIFT features[J]. Computer Applications,2007,27(11):2789-2792高超,张鑫,王云丽等.一种基于SIFT特征的航拍图像序列自动拼接方法[J].计算机应用,2007,27(11):2789-2792
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心