基于特征点的图像配准技术及应用
|
摘要
图像配准是图像处理的基本任务之一,用于将不同时间、不同传感器、不同视角及不同拍摄条件下获取的两幅或多幅图像(主要是几何形式上)进行匹配。图像配准是多种图像处理及应用,如图像融合、图像拼接、变化检测等的基础,配准效果将直接影响到后续图像处理工作。在对图像配准方法进行分析的基础上,本文对基于形状内容描述子的图像配准方法和基于灰度差分不变量的图像配准方法进行了研究。
本文提出了一种新的特征描述子―形状内容描述子(SCD)。其基本原理是根据曲线上的点到特征点的角度划分区域,得到一个N维的特征描述向量。构建的形状内容描述算子不依赖于特征点的全局特征,对图像的光照、位移、视角、噪声等有较强的适应能力。在将上述的特征描述算法应用于图像配准时,为克服这种图像配准技术只适用于图像间存在小角度旋转(约为0～5°)的不足,采用局部梯度方向直方图来确定旋转角度。
灰度差分不变量(GDI)具有平移和旋转不变性,并且对噪声具有较强的鲁棒性。基于灰度差分不变量的图像配准算法首先利用灰度差分不变量构造特征描述子,然后通过计算各象素描述子之间的欧氏距离来决定是否匹配。实验结果表明,这种方法对噪声和配准误差都有一定的鲁棒性。
本文最后介绍了图像配准在图像拼接和图像融合中的应用。将本文提出的两种图像配准算法应用在图像拼接上,实验证明该算法能够有效地拼接普通相机拍摄的照片,并具有较好的稳定性和较高精度。在图像融合中,采用透明融合技术对可见光和红外热图像进行融合。
Image Registration is a fundamental task in image Processing used to (mainly in geometrical) match two or more images obtained at different time, from different sensors or from different viewpoints. Image Registration is the foundation of many image processing and applications such as image fusion, image stitching, change detection. And the effect of registration works on the following processing steps directly. In this paper, two image registration methods are presented: the registration based on the Shape Context Descriptor (SCD) and the registration based on the Gray-value Differential Invariants (GDI).
A novel shape context descriptor is presented. For each feature, the shape context descriptor divides 360°central angle (the centre is the feature point) equally into N parts, then according the angle values between the feature point and the edge points, get a 1×N vector. This new technique doesn’t depend on global information. It is robust to noise, scale and so on. To overcome the drawback that the registration algorithm is only suitable to small rotation angle, the orientation difference between two images is calculated using a local gradient orientation histogram.
Another registration algorithms based on the Gray-value Differential Invariants is introduced. The differential invariants are robust to noise, translation and rotation. Firstly the differential invariants are used to form local invariant feature, then the matching degree is gained via Euclidean distance. The experiment results show this method is robust to noise and registration error.
Finally, we apply the two proposed algorithms in image stitching and image fusion. In image stitching, the results from experiments show the validity, good stability, and high precision of the two algorithms. In image fusion, transparency fusion technique is applied in the fusion of the visible and infrared light images.
本文提出了一种新的特征描述子―形状内容描述子(SCD)。其基本原理是根据曲线上的点到特征点的角度划分区域,得到一个N维的特征描述向量。构建的形状内容描述算子不依赖于特征点的全局特征,对图像的光照、位移、视角、噪声等有较强的适应能力。在将上述的特征描述算法应用于图像配准时,为克服这种图像配准技术只适用于图像间存在小角度旋转(约为0～5°)的不足,采用局部梯度方向直方图来确定旋转角度。
灰度差分不变量(GDI)具有平移和旋转不变性,并且对噪声具有较强的鲁棒性。基于灰度差分不变量的图像配准算法首先利用灰度差分不变量构造特征描述子,然后通过计算各象素描述子之间的欧氏距离来决定是否匹配。实验结果表明,这种方法对噪声和配准误差都有一定的鲁棒性。
本文最后介绍了图像配准在图像拼接和图像融合中的应用。将本文提出的两种图像配准算法应用在图像拼接上,实验证明该算法能够有效地拼接普通相机拍摄的照片,并具有较好的稳定性和较高精度。在图像融合中,采用透明融合技术对可见光和红外热图像进行融合。
Image Registration is a fundamental task in image Processing used to (mainly in geometrical) match two or more images obtained at different time, from different sensors or from different viewpoints. Image Registration is the foundation of many image processing and applications such as image fusion, image stitching, change detection. And the effect of registration works on the following processing steps directly. In this paper, two image registration methods are presented: the registration based on the Shape Context Descriptor (SCD) and the registration based on the Gray-value Differential Invariants (GDI).
A novel shape context descriptor is presented. For each feature, the shape context descriptor divides 360°central angle (the centre is the feature point) equally into N parts, then according the angle values between the feature point and the edge points, get a 1×N vector. This new technique doesn’t depend on global information. It is robust to noise, scale and so on. To overcome the drawback that the registration algorithm is only suitable to small rotation angle, the orientation difference between two images is calculated using a local gradient orientation histogram.
Another registration algorithms based on the Gray-value Differential Invariants is introduced. The differential invariants are robust to noise, translation and rotation. Firstly the differential invariants are used to form local invariant feature, then the matching degree is gained via Euclidean distance. The experiment results show this method is robust to noise and registration error.
Finally, we apply the two proposed algorithms in image stitching and image fusion. In image stitching, the results from experiments show the validity, good stability, and high precision of the two algorithms. In image fusion, transparency fusion technique is applied in the fusion of the visible and infrared light images.
引文
[1] L.G. Brown. A survey of image registration techniques, ACM Computer Surveys, 1992, 24(4): 325-376
[2] W.K. Pratt. Correlation techniques of image registration. IEEE Transactions on Aerospace and Electronic Systems, 1974, AES-10(3): 353~358
[3]王小睿,吴信才,遥感多图像的自动配准方法,中国图形图像学报,1997,2(10): 735~739
[4] P.E. Anuta. Spatial Registration of Multispectral and Multitemporal Digital Imagery Using Fast Fourier Transform Techniques. IEEE Transactions on Geoscience Electronics, Oct. 1970, 8(4): 353~368.
[5] A. Arcese, P. Mengert, E. Trombini. Image detection through bipolar correlation. IEEE Transactions on Information Theory, Sep 1970, 16(5): 534~ 541
[6] D.I. Barnea, H.F. Silverman. A class of Algorithms for Fast Digital Image Registration. IEEE Transactions on Computers, Feb. 1972, C(21): 179~186.
[7]李中科,吴乐南,基于霍夫变换和相位相关的图像配准方法,信号处理,2004年,20(2): 166~169
[8] H.G. Barrow et al. Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching. Proc 5th Joint Conf. On Artificial Intelligence. Cambridge. Mess., 1977:659~663
[9] Mikio Takagi, Takamichi Hiyama, Mitsuo Sone and Morio Onoe. Automatic Correcting Method of Geometric Distortion in Meteorological Satellite NOAA Image.电子情报通信学会论文志, 1988, J71-D(S): 883~893
[10] J. Flusser. An Adaptive Method for Image Registration. Pattern Recognition, 1992, 25(1): 45~54.
[11] B. Zitová, J. Flusser, Image registration methods: a survey, Image and vision Computing 21(2003): 997~1000
[12] H. Rusinck, A. Levy, M.E. Noz. Performance of two methods for registering PET and MR brain scans. Conf Record 1991 IEEE, Nuclear Science Symp Med Image Conf 1991, 3: 2195~2162.
[13] P.J. Besl, N.D. Macky. A method for registration of 3-D shapes. IEEE Trans part Anal Mach Intell. 1992, 14(4): 239~256.
[14]王卫东,俎栋林,包尚联等,基于边缘提取得医学图像配准方法,.中国体视学与图像分析,1998年,3(12): 204~207.
[15]周海芳,刘光明,郑明玲,杨学军。遥感图像自动配准得串行与并行策略研究。国防科技大学学报。2004年,26(2): 56~61
[16] F. Mokhtarian and R. Suomela. Robust image corner detection through curvature scale space. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(12): 1376~1381
[17]龚声蓉,刘纯平,王强等,数字图像处理与分析,北京,清华大学出版社,2006: 169~176。
[18] X.C.He and N.H.C.Yung, Curvature scale space corner detector with adaptive threshold and dynamic region of support, Proceedings of the 17th International Conference on Pattern Recognition, August 2004, 2: 791~794.
[19] C. Harris, M. Stephens. A combined corner and edge detector. Proceeding of Alvey Vision Conference, Manchester, UK, 1988: 189~192.
[20]刘宇斌,一种分阶段的高精度亚象素图像特征点提取方法,南华大学学报(自然科学版),2006,20(2): 54~57。
[21]李弼程,彭天强,彭波等,智能图像处理技术,电子工业出版社,2004: 239~239。
[22]曹闻,李弼程,邓子健,一种基于小波变换的图像配准方法,测绘通报,2004,2: 16~19
[23] K. Yang, R. Sukthankar. PCA-SIFT: A more distinctive representation for local image descriptors. Proc. Conf. CVPR, 2004: 511~517
[24] K. Mikolajczyk, C. Schmid. A performance evaluation of local descriptors. IEEE Trans. On PAMI, 2005, 27(10): 1615~1630
[25] A. Johnson, M. Hebert. Object recognition by matching oriented points. Proc. Conf. CVPR, 1997: 684~689
[26] R.Zabih, J. Woodfil. Non-parametric local transforms for computing visual correspondence. Proc. Third European Conf. Computer Vision, 1994: 151~158
[27] W. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 2004, 2(60): 91~110
[28] S. Belongie, J. Malik, J. Puzicha. Shape Matching and Object Recognition Using Shape Contexts. IEEE Trans. attern Analysis and Machine Intelligence, Apr.2002, 2(4): 509~522
[29] J. Koenderink, A.D. Doorn. Representation of local geometry in the visual system.Biological Cybernetics, 1987, 55: 367~375
[30] L. Florack, etc. General intensity transformations and second order invariants. Proc. Seventh Scandinavian Conf. Image Analysis, 1991: 338~345
[31] W. Freeman, E. Adelson. The design and use of steerable filters. IEEE Trans. PAMI, 1991, 13 (9): 891~906
[32] A. Baumberg. Reliable feature matching across widely separated views, Proc. CVPR, 2000: 774~781
[33] F. Schaffalitzky, A. Zisserman. Multi-view matching for unordered image sets. Proc. Seventh European Conf. Computer Vision, 2002: 414~431
[34] L.V. Gool, T. Moons, D. Ungureanu. Affine/Photometric invariants for planar intensity patterns. Proc. Fourth European Conf. Computer Vision, 1996: 642~651
[35]李博,图像的不变特征检测与描述研究,[硕士学位论文],重庆,重庆大学,2007年
[36] J. Koenderink and A. van Doorn, Representation of Local Geometry in the Visual System, Biological Cybernetics, vol. 55, pp. 1987,367~375.
[37] C. Schmid, R. Mohr. Local grayvalue invariants for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(5):530~535.
[38] Gui Yun Tian, Duke Gledhill, David Taylor. Comprehensive interest points based imaging mosaic. Pattern Recognition Letters 24 (2003):1171–1179
[39]蒋煜,基于特征的多模态图像自动配准算法研究,[硕士学术论文],武汉,华中科技大学,2005年
[40] Yehuda Afek, A. Brand. A two phase digital ortho photo mosaicking system. Inter-national Conference on Imaging Science, Systems, and Technology, 1999: 151~154
[41] Yehuda Afek, A. Brand. Mosaicking of orthorectified aerial images. Photogram-metric Engineering & Remote Sensing, 1998, 64(2): 115~125
[42] S.M. Seitz, C.R. Dyer. View morphine. Computer Graphics, 1996, 30(3): 21~30
[43]郑新,基于图像的快速绘制技术的研究,[博士学位论文],北京,中国科学院软件研究所,2001年
[44] Paul Bao, Dan Xu. Multiresolution image morphing in wavelet domain. Proceeding in International Conference on Information Visualisation(IV2000).London, England, 2000: 309~314
[45] Heung-Yeung Shum, Richard Szeliski1.Construction of panoramic image mosaics withglobal and local alignment. International Journal of Computer Vision, 2000, 36(2):101~130
[46]陶波,于志伟,郑筱祥,图像的自动拼接,中国生物医学工程学报,1997,16(4): 316~322
[47] P.J. Burt, E.H. Adelson. A multiresolution spline with application to image mosaics. ACM Transactions on Graphics, 1983, 2 (4): 217~236
[48]向世明,Visual C++数字图像与图形处理,北京,电子工业出版社,2002: 266~267
[2] W.K. Pratt. Correlation techniques of image registration. IEEE Transactions on Aerospace and Electronic Systems, 1974, AES-10(3): 353~358
[3]王小睿,吴信才,遥感多图像的自动配准方法,中国图形图像学报,1997,2(10): 735~739
[4] P.E. Anuta. Spatial Registration of Multispectral and Multitemporal Digital Imagery Using Fast Fourier Transform Techniques. IEEE Transactions on Geoscience Electronics, Oct. 1970, 8(4): 353~368.
[5] A. Arcese, P. Mengert, E. Trombini. Image detection through bipolar correlation. IEEE Transactions on Information Theory, Sep 1970, 16(5): 534~ 541
[6] D.I. Barnea, H.F. Silverman. A class of Algorithms for Fast Digital Image Registration. IEEE Transactions on Computers, Feb. 1972, C(21): 179~186.
[7]李中科,吴乐南,基于霍夫变换和相位相关的图像配准方法,信号处理,2004年,20(2): 166~169
[8] H.G. Barrow et al. Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching. Proc 5th Joint Conf. On Artificial Intelligence. Cambridge. Mess., 1977:659~663
[9] Mikio Takagi, Takamichi Hiyama, Mitsuo Sone and Morio Onoe. Automatic Correcting Method of Geometric Distortion in Meteorological Satellite NOAA Image.电子情报通信学会论文志, 1988, J71-D(S): 883~893
[10] J. Flusser. An Adaptive Method for Image Registration. Pattern Recognition, 1992, 25(1): 45~54.
[11] B. Zitová, J. Flusser, Image registration methods: a survey, Image and vision Computing 21(2003): 997~1000
[12] H. Rusinck, A. Levy, M.E. Noz. Performance of two methods for registering PET and MR brain scans. Conf Record 1991 IEEE, Nuclear Science Symp Med Image Conf 1991, 3: 2195~2162.
[13] P.J. Besl, N.D. Macky. A method for registration of 3-D shapes. IEEE Trans part Anal Mach Intell. 1992, 14(4): 239~256.
[14]王卫东,俎栋林,包尚联等,基于边缘提取得医学图像配准方法,.中国体视学与图像分析,1998年,3(12): 204~207.
[15]周海芳,刘光明,郑明玲,杨学军。遥感图像自动配准得串行与并行策略研究。国防科技大学学报。2004年,26(2): 56~61
[16] F. Mokhtarian and R. Suomela. Robust image corner detection through curvature scale space. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(12): 1376~1381
[17]龚声蓉,刘纯平,王强等,数字图像处理与分析,北京,清华大学出版社,2006: 169~176。
[18] X.C.He and N.H.C.Yung, Curvature scale space corner detector with adaptive threshold and dynamic region of support, Proceedings of the 17th International Conference on Pattern Recognition, August 2004, 2: 791~794.
[19] C. Harris, M. Stephens. A combined corner and edge detector. Proceeding of Alvey Vision Conference, Manchester, UK, 1988: 189~192.
[20]刘宇斌,一种分阶段的高精度亚象素图像特征点提取方法,南华大学学报(自然科学版),2006,20(2): 54~57。
[21]李弼程,彭天强,彭波等,智能图像处理技术,电子工业出版社,2004: 239~239。
[22]曹闻,李弼程,邓子健,一种基于小波变换的图像配准方法,测绘通报,2004,2: 16~19
[23] K. Yang, R. Sukthankar. PCA-SIFT: A more distinctive representation for local image descriptors. Proc. Conf. CVPR, 2004: 511~517
[24] K. Mikolajczyk, C. Schmid. A performance evaluation of local descriptors. IEEE Trans. On PAMI, 2005, 27(10): 1615~1630
[25] A. Johnson, M. Hebert. Object recognition by matching oriented points. Proc. Conf. CVPR, 1997: 684~689
[26] R.Zabih, J. Woodfil. Non-parametric local transforms for computing visual correspondence. Proc. Third European Conf. Computer Vision, 1994: 151~158
[27] W. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 2004, 2(60): 91~110
[28] S. Belongie, J. Malik, J. Puzicha. Shape Matching and Object Recognition Using Shape Contexts. IEEE Trans. attern Analysis and Machine Intelligence, Apr.2002, 2(4): 509~522
[29] J. Koenderink, A.D. Doorn. Representation of local geometry in the visual system.Biological Cybernetics, 1987, 55: 367~375
[30] L. Florack, etc. General intensity transformations and second order invariants. Proc. Seventh Scandinavian Conf. Image Analysis, 1991: 338~345
[31] W. Freeman, E. Adelson. The design and use of steerable filters. IEEE Trans. PAMI, 1991, 13 (9): 891~906
[32] A. Baumberg. Reliable feature matching across widely separated views, Proc. CVPR, 2000: 774~781
[33] F. Schaffalitzky, A. Zisserman. Multi-view matching for unordered image sets. Proc. Seventh European Conf. Computer Vision, 2002: 414~431
[34] L.V. Gool, T. Moons, D. Ungureanu. Affine/Photometric invariants for planar intensity patterns. Proc. Fourth European Conf. Computer Vision, 1996: 642~651
[35]李博,图像的不变特征检测与描述研究,[硕士学位论文],重庆,重庆大学,2007年
[36] J. Koenderink and A. van Doorn, Representation of Local Geometry in the Visual System, Biological Cybernetics, vol. 55, pp. 1987,367~375.
[37] C. Schmid, R. Mohr. Local grayvalue invariants for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(5):530~535.
[38] Gui Yun Tian, Duke Gledhill, David Taylor. Comprehensive interest points based imaging mosaic. Pattern Recognition Letters 24 (2003):1171–1179
[39]蒋煜,基于特征的多模态图像自动配准算法研究,[硕士学术论文],武汉,华中科技大学,2005年
[40] Yehuda Afek, A. Brand. A two phase digital ortho photo mosaicking system. Inter-national Conference on Imaging Science, Systems, and Technology, 1999: 151~154
[41] Yehuda Afek, A. Brand. Mosaicking of orthorectified aerial images. Photogram-metric Engineering & Remote Sensing, 1998, 64(2): 115~125
[42] S.M. Seitz, C.R. Dyer. View morphine. Computer Graphics, 1996, 30(3): 21~30
[43]郑新,基于图像的快速绘制技术的研究,[博士学位论文],北京,中国科学院软件研究所,2001年
[44] Paul Bao, Dan Xu. Multiresolution image morphing in wavelet domain. Proceeding in International Conference on Information Visualisation(IV2000).London, England, 2000: 309~314
[45] Heung-Yeung Shum, Richard Szeliski1.Construction of panoramic image mosaics withglobal and local alignment. International Journal of Computer Vision, 2000, 36(2):101~130
[46]陶波,于志伟,郑筱祥,图像的自动拼接,中国生物医学工程学报,1997,16(4): 316~322
[47] P.J. Burt, E.H. Adelson. A multiresolution spline with application to image mosaics. ACM Transactions on Graphics, 1983, 2 (4): 217~236
[48]向世明,Visual C++数字图像与图形处理,北京,电子工业出版社,2002: 266~267