基于图像尖锐度的角点匹配算法
|
摘要
从多角度拍摄同一物体所得不同视角图像中的关键点的匹配对图像三维重建至关重要。为了得到精准的角点匹配对,提出了基于图像尖锐度角点匹配的新算法。该算法分为3个步骤:第1,为最大限度避免噪声的干扰,使用Canny算子先检测图像,进而使用8邻域轮廓追踪算法追踪边缘点得到边缘轮廓线。第2,计算轮廓线的尖锐度获取图像中的关键角点。第3,先粗匹配利用零均值归一化互相关法建立不同图像角点间一对多的关系,再进行精匹配采用优化后减少迭代次数的松弛迭代法得到一对一匹配点对。实验表明,该算法能够在提高运行效率的同时提高角点匹配的精准度,最终得到角点精匹配对。
It is crucial to 3 Dimage reconstruction that matching the key points of the same object from multi-angle shots of images.We propose a new corner matching algorithm based on image sharpness to get precise corner matching pairs.The algorithm is divided into three steps.Firstly,the coarse edge information of image is gained by Canny operator.To minimize noise interference to the greatest extent,we then use the 8 neighborhood contour tracking algorithm to track the edge points to obtain the edge contour.Secondly,the sharpness of the contour lines is calculated to get the key corner points in the image.Thirdly,one-to-many matching relationships between corner points in different images are established through the zero-mean normalized cross-correlation method,thus coarse-matching of point pairs is achieved;and we adopt an optimized relaxation iteration method to reduce the number of iterations and obtain one-to-one precise-matching of point pairs.Experimental results show that the proposed algorithm is able to improve the running efficiency and accuracy of corner matching,thus realizing precise-matching of point pairs.
It is crucial to 3 Dimage reconstruction that matching the key points of the same object from multi-angle shots of images.We propose a new corner matching algorithm based on image sharpness to get precise corner matching pairs.The algorithm is divided into three steps.Firstly,the coarse edge information of image is gained by Canny operator.To minimize noise interference to the greatest extent,we then use the 8 neighborhood contour tracking algorithm to track the edge points to obtain the edge contour.Secondly,the sharpness of the contour lines is calculated to get the key corner points in the image.Thirdly,one-to-many matching relationships between corner points in different images are established through the zero-mean normalized cross-correlation method,thus coarse-matching of point pairs is achieved;and we adopt an optimized relaxation iteration method to reduce the number of iterations and obtain one-to-one precise-matching of point pairs.Experimental results show that the proposed algorithm is able to improve the running efficiency and accuracy of corner matching,thus realizing precise-matching of point pairs.
引文
[1]Jain A K,Zhong Y,Lakshmanan S.Object matching using deformable templates[J].IEEE Transactions on Pattern A-nalysis and Machine Intelligence,1996,18(3):267-278.
[2]Yu Li,Wang Run-sheng.Object detection and recognition based on multiscale deformable template[J].Journal of Computer Research and Development,2002,39(10):1325-1330.(in Chinese)
[3]Kuglin C D.The phase correlation image alignment method[C]∥Proc of International Conference on Cybernetics Society,1975:163-165.
[4]Dubuisson M P,Jain A K.A modified Hausdorff distance for object matching[C]∥Proc of the 12th IAPR International Conference on Pattern Recognition,1994:566-568.
[5]Anuta P E.Spatial registration of multispectral and multitemporal digital imagery using fast Fourier transform techniques[J].IEEE Transactions on Geoscience Electronics,1970,8(4):353-368.
[6]Leese J A,Novak C S,Clark B B.An automated technique for obtaining cloud motion from geosynchronous satellite data using cross correlation[J].Journal of Applied Meteorology,1971,10(1):118-132.
[7]Barnea D I,Silverman H F.A class of algorithms for fast digital image registration[J].IEEE Transactions on Computers,1972,21(2):179-186.
[8]Lewis J P.Fast normalized cross-correlation[J].Circuits Systems&Signal Processing,1995,82(2):144-156.
[9]Wells W M,Viola P A,Atsumi H,et al.Multi-modal volume registration by maximization of mutual information[J].Medical Image Analysis,1996,1(1):35-51.
[10]Maes F,Collignon A M F,Vandermeulen D,et al.Multimodality image registration by maximization of mutual information[J].IEEE Transactions on Medical Imaging,1997,16(2):187-198.
[11]Studholme C,Hill D L G,Hawkes D J.An overlap invariant entropy measure of 3D medical image alignment[J].Pattern Recognition,1999,32(1):71-86.
[12]Thévenaz P,Unser M.Optimization of mutual information for multiresolution image registration[J].IEEE Transactions on Image Processing,2000,9(12):2083-2099.
[13]Lowe D G.Object recognition from local scale-invariant features[C]∥Proc of the 7th IEEE International Conference on Computer Vision,1999:1150-1157.
[14]Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[15]Verma A,Banerji S,Liu C J.A new color SIFT descriptor and methods for image category classification[C]∥Proc of International Congress on Computer Applications and Computational Science,2010:4-6.
[16]Wengert C,Douze M,Jégou H.Bag-of-colors for improved image search[C]∥Proc of the 19th ACM International Conference on Multimedia,2011:1437-1440.
[17]Rassem T H,Khoo B E.Object class recognition using combination of color SIFT descriptors[C]∥Prco of 2011IEEE International Conference on Imaging Systems and Techniques(IST),2011:290-295.
[18]Tian X L,Jiao L C,Liu X L,et al.Feature integration of EODH and Color-SIFT:Application to image retrieval based on codebook[J].Signal Processing:Image Communication,2014,29(4):530-545.
[19]Bay H,Tuytelaars T,Van Gool L.Surf:Speeded up robust features[C]∥Proc of the 9th European Conference on Computer Vision,2006:404-417.
[20]Rublee E,Rabaud V,Konolige K,et al.ORB:An efficient alternative to SIFT or SURF[C]∥Proc of 2011IEEE International Conference on Computer Vision(ICCV),2011:2564-2571.
[21]Pang Y W,Li W,Yuan Y,et al.Fully affine invariant SURF for image matching[J].Neurocomputing,2012,85:6-10.
[22]Yang Tong-yu,Peng Guo-hua.Fast algorithm for image matching based on NCC[J].Modern Electronics Technique,2010,33(22):107-109.(in Chinese)
[23]Liu Zhao-ying,Zhou Fu-geng,Bai Xiang-zhi,et al.Multimode image registration based on mutual information of region of interests[J].Aero Weaponry,2011(4):7-12.(in Chinese)
[24]Han Bing,Wang Yong-ming.Research of image matching based on a fast normalized cross correlation algorithm[J].Acta Armamentarii,2010,31(2):160-165.(in Chinese)
[25]Cheng De-zhi,Li Yan-jun,Yu Rui-xing.Image matching method based on improved SIFT algorithm[J].Computer Simulation,2011,28(7):285-289.(in Chinese)
[26]Zhang Kai-yu,Liang Feng-mei.Research on the key algorithm of image registration based on improved SURF[J].Science Technology and Engineering,2013,13(10):2875-2879.(in Chinese)
[27]He Dong-jian,Geng Nan,Zhang Yi-kuan.Digital image processing[M].2nd Edition.Xi’an:Xidian University Press,2008.(in Chinese)
[28]Wen Yang-tian,Li Zheng,Wu Zhong-guang.Image registration based on SUSAN algorithm[J].Journal of Computer Applications,2006,26(10):2380-2382.(in Chinese)
[29]Ji Li-e,Shi Ji-sheng.Image registration based on SUSANfeature points[J].Sensor World,2013,19(4):7-9.(in Chinese)
[30]Zhang Qian,Liu Zheng-kai,Pang Yan-wei,et al.Automatic registration of aerophotos based on SUSAN operator[J].Acta Geodaetica et Cartographica Sinica,2003,32(3):245-250.(in Chinese)
[31]Qian Wen-guang,Lin Xiao-zhu.Curvature calculation and corners extraction of image contour[J].Chinese Journal of Scientific Instrument,2007,28(4):63-68.(in Chinese)
[32]Qian Wen-guang,Lin Xiao-zhu.Detection algorithm of image corner based on contour sharp degree[J].Computer Engineering,2008,34(6):202-204.(in Chinese)
[33]An Ting,He Yi-min,Zhang Zhi-yi.An improved bidirectional SIFT feature matching algorithm[J].Computer Engineering&Science,2016,38(1):138-143.(in Chinese)
[34]Park S Y,Park S K,Hebert M.Fast and scalable approximate spectral matching for higher order graph matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(3):479-492.
[2]余莉,王润生.基于多尺度变形模板的目标检测与识别[J].计算机研究与发展,2002,39(10):1325-1330.
[22]杨通钰,彭国华.基于NCC的图像匹配快速算法[J].现代电子技术,2010,33(22):107-109.
[23]刘兆英,周付根,白相志,等.基于感兴趣区域互信息的多模图像配准方法[J].航空兵器,2011(4):7-12.
[24]韩冰,王永明.基于一种快速归一化积相关算法的图像匹配研究[J].兵工学报,2010,31(2):160-165.
[25]程德志,李言俊,余瑞星.基于改进SIFT算法的图像匹配方法[J].计算机仿真,2011,28(7):285-289.
[26]张开玉,梁凤梅.基于改进SURF的图像配准关键算法研究[J].科学技术与工程,2013,13(10):2875-2879.
[27]何东健,耿楠,张义宽.数字图像处理[M].第2版.西安:西安电子科技大学出版社,2008.
[28]文杨天,李征,吴仲光.基于SUSAN算法的图像配准[J].计算机应用,2006,26(10):2380-2382.
[29]纪利娥,石继升.基于SUSAN特征点的图像配准算法[J].传感器世界,2013,19(4):7-9.
[30]张迁,刘政凯,庞彦伟,等.基于SUSAN算法的航空影像的自动配准[J].测绘学报,2003,32(3):245-250.
[31]钱文光,林小竹.图像轮廓曲率计算与角点提取[J].仪器仪表学报,2007,28(4):63-68.
[32]钱文光,林小竹.基于轮廓尖锐度的图像角点检测算法[J].计算机工程,2008,34(6):202-204.
[33]安婷,贺一民,张志毅.改进的双向SIFT特征匹配算法[J].计算机工程与科学,2016,38(1):138-143.
[2]Yu Li,Wang Run-sheng.Object detection and recognition based on multiscale deformable template[J].Journal of Computer Research and Development,2002,39(10):1325-1330.(in Chinese)
[3]Kuglin C D.The phase correlation image alignment method[C]∥Proc of International Conference on Cybernetics Society,1975:163-165.
[4]Dubuisson M P,Jain A K.A modified Hausdorff distance for object matching[C]∥Proc of the 12th IAPR International Conference on Pattern Recognition,1994:566-568.
[5]Anuta P E.Spatial registration of multispectral and multitemporal digital imagery using fast Fourier transform techniques[J].IEEE Transactions on Geoscience Electronics,1970,8(4):353-368.
[6]Leese J A,Novak C S,Clark B B.An automated technique for obtaining cloud motion from geosynchronous satellite data using cross correlation[J].Journal of Applied Meteorology,1971,10(1):118-132.
[7]Barnea D I,Silverman H F.A class of algorithms for fast digital image registration[J].IEEE Transactions on Computers,1972,21(2):179-186.
[8]Lewis J P.Fast normalized cross-correlation[J].Circuits Systems&Signal Processing,1995,82(2):144-156.
[9]Wells W M,Viola P A,Atsumi H,et al.Multi-modal volume registration by maximization of mutual information[J].Medical Image Analysis,1996,1(1):35-51.
[10]Maes F,Collignon A M F,Vandermeulen D,et al.Multimodality image registration by maximization of mutual information[J].IEEE Transactions on Medical Imaging,1997,16(2):187-198.
[11]Studholme C,Hill D L G,Hawkes D J.An overlap invariant entropy measure of 3D medical image alignment[J].Pattern Recognition,1999,32(1):71-86.
[12]Thévenaz P,Unser M.Optimization of mutual information for multiresolution image registration[J].IEEE Transactions on Image Processing,2000,9(12):2083-2099.
[13]Lowe D G.Object recognition from local scale-invariant features[C]∥Proc of the 7th IEEE International Conference on Computer Vision,1999:1150-1157.
[14]Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[15]Verma A,Banerji S,Liu C J.A new color SIFT descriptor and methods for image category classification[C]∥Proc of International Congress on Computer Applications and Computational Science,2010:4-6.
[16]Wengert C,Douze M,Jégou H.Bag-of-colors for improved image search[C]∥Proc of the 19th ACM International Conference on Multimedia,2011:1437-1440.
[17]Rassem T H,Khoo B E.Object class recognition using combination of color SIFT descriptors[C]∥Prco of 2011IEEE International Conference on Imaging Systems and Techniques(IST),2011:290-295.
[18]Tian X L,Jiao L C,Liu X L,et al.Feature integration of EODH and Color-SIFT:Application to image retrieval based on codebook[J].Signal Processing:Image Communication,2014,29(4):530-545.
[19]Bay H,Tuytelaars T,Van Gool L.Surf:Speeded up robust features[C]∥Proc of the 9th European Conference on Computer Vision,2006:404-417.
[20]Rublee E,Rabaud V,Konolige K,et al.ORB:An efficient alternative to SIFT or SURF[C]∥Proc of 2011IEEE International Conference on Computer Vision(ICCV),2011:2564-2571.
[21]Pang Y W,Li W,Yuan Y,et al.Fully affine invariant SURF for image matching[J].Neurocomputing,2012,85:6-10.
[22]Yang Tong-yu,Peng Guo-hua.Fast algorithm for image matching based on NCC[J].Modern Electronics Technique,2010,33(22):107-109.(in Chinese)
[23]Liu Zhao-ying,Zhou Fu-geng,Bai Xiang-zhi,et al.Multimode image registration based on mutual information of region of interests[J].Aero Weaponry,2011(4):7-12.(in Chinese)
[24]Han Bing,Wang Yong-ming.Research of image matching based on a fast normalized cross correlation algorithm[J].Acta Armamentarii,2010,31(2):160-165.(in Chinese)
[25]Cheng De-zhi,Li Yan-jun,Yu Rui-xing.Image matching method based on improved SIFT algorithm[J].Computer Simulation,2011,28(7):285-289.(in Chinese)
[26]Zhang Kai-yu,Liang Feng-mei.Research on the key algorithm of image registration based on improved SURF[J].Science Technology and Engineering,2013,13(10):2875-2879.(in Chinese)
[27]He Dong-jian,Geng Nan,Zhang Yi-kuan.Digital image processing[M].2nd Edition.Xi’an:Xidian University Press,2008.(in Chinese)
[28]Wen Yang-tian,Li Zheng,Wu Zhong-guang.Image registration based on SUSAN algorithm[J].Journal of Computer Applications,2006,26(10):2380-2382.(in Chinese)
[29]Ji Li-e,Shi Ji-sheng.Image registration based on SUSANfeature points[J].Sensor World,2013,19(4):7-9.(in Chinese)
[30]Zhang Qian,Liu Zheng-kai,Pang Yan-wei,et al.Automatic registration of aerophotos based on SUSAN operator[J].Acta Geodaetica et Cartographica Sinica,2003,32(3):245-250.(in Chinese)
[31]Qian Wen-guang,Lin Xiao-zhu.Curvature calculation and corners extraction of image contour[J].Chinese Journal of Scientific Instrument,2007,28(4):63-68.(in Chinese)
[32]Qian Wen-guang,Lin Xiao-zhu.Detection algorithm of image corner based on contour sharp degree[J].Computer Engineering,2008,34(6):202-204.(in Chinese)
[33]An Ting,He Yi-min,Zhang Zhi-yi.An improved bidirectional SIFT feature matching algorithm[J].Computer Engineering&Science,2016,38(1):138-143.(in Chinese)
[34]Park S Y,Park S K,Hebert M.Fast and scalable approximate spectral matching for higher order graph matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(3):479-492.
[2]余莉,王润生.基于多尺度变形模板的目标检测与识别[J].计算机研究与发展,2002,39(10):1325-1330.
[22]杨通钰,彭国华.基于NCC的图像匹配快速算法[J].现代电子技术,2010,33(22):107-109.
[23]刘兆英,周付根,白相志,等.基于感兴趣区域互信息的多模图像配准方法[J].航空兵器,2011(4):7-12.
[24]韩冰,王永明.基于一种快速归一化积相关算法的图像匹配研究[J].兵工学报,2010,31(2):160-165.
[25]程德志,李言俊,余瑞星.基于改进SIFT算法的图像匹配方法[J].计算机仿真,2011,28(7):285-289.
[26]张开玉,梁凤梅.基于改进SURF的图像配准关键算法研究[J].科学技术与工程,2013,13(10):2875-2879.
[27]何东健,耿楠,张义宽.数字图像处理[M].第2版.西安:西安电子科技大学出版社,2008.
[28]文杨天,李征,吴仲光.基于SUSAN算法的图像配准[J].计算机应用,2006,26(10):2380-2382.
[29]纪利娥,石继升.基于SUSAN特征点的图像配准算法[J].传感器世界,2013,19(4):7-9.
[30]张迁,刘政凯,庞彦伟,等.基于SUSAN算法的航空影像的自动配准[J].测绘学报,2003,32(3):245-250.
[31]钱文光,林小竹.图像轮廓曲率计算与角点提取[J].仪器仪表学报,2007,28(4):63-68.
[32]钱文光,林小竹.基于轮廓尖锐度的图像角点检测算法[J].计算机工程,2008,34(6):202-204.
[33]安婷,贺一民,张志毅.改进的双向SIFT特征匹配算法[J].计算机工程与科学,2016,38(1):138-143.