仿射不变特征提取及其在景象匹配中的应用
|
摘要
随着我国对精确打击武器的迫切需求,开展关于景象匹配技术的研究具有重要的国防意义。但是用于图像匹配的实时图和模板图通常是在不同时间、不同视角、不同天气、不同传感器条件下获得的,图像间存在较大畸变,传统的基于灰度模板的匹配方法往往不能对目标进行准确定位。因此,在发生畸变的图像中提取不变特征,成为近年来研究人员最青睐的方向。另外,仿射不变特征提取也是计算机视觉领域的重要研究方向,在图像配准、目标跟踪、三维重构、目标识别等领域都有非常广泛的应用。
本论文对仿射不变特征的提取方法进行了详细的研究,主要研究成果分为以下三个方面:
(1)针对纹理不丰富、灰度分布均匀、具有一定的面积、与背景差异较大的目标,提出了一种基于目标区域协方差矩阵的目标识别方法。首先,利用自动多门限区域分割方法将目标从背景中分割出来;然后,求取目标区域的协方差矩阵,并用协方差矩阵定义一个椭圆区域,通过对协方差矩阵的分解,将椭圆区域归一化为圆域,求出仿射不变特征向量;最后,求出两幅图像中目标区域的仿射变换矩阵,将模板变换后进行进一步的识别。该方法具有完全的仿射不变性,且对光照变化不敏感。另外,基于本算法的理论,论文中还给出了仿射变换参数求解及目标姿态测量的新方法,且具有较高的精度。
(2)针对背景复杂、不易进行目标分割的图像,研究了基于MSA变换的全局不变特征提取方法。针对MSA变换对光照变化敏感的问题,提出了两种抗光照变化的算法——结合方向编码的MSA和MSA直方图不变量,并探讨了两种减少计算量的策略——分块和去掉傅里叶变换的高频分量。实验证明,改进的方法能有效克服光照变化的影响,且计算量大约是原来的1/8。
(3)针对目标被大面积遮挡时,无法用全局不变量进行识别的情况,研究了基于SIFT的局部不变特征提取方法。针对SIFT特征描述子对相似区域区分性差的问题,提出了一种结合全局形状信息的特征向量生成方法,该方法增强了SIFT特征描述子的可区分性,减少了误匹配点对的数量。另外,本论文依据仿射变换的性质,给出了一种剔除误匹配点对的方法,在不影响正确匹配点对的情况下取得了较好的效果。
With the urgent demand of precision strike weapons in our country, research work on scence matching has important significance for national defense. However the template and real-time image are gotton in different time and weather conditions, from different viewpoints, by different sensors, so there is a large distortion between them, and the traditional matcing methods based on gray-scale template can not position object accurately. Therefore extracting invariant features from the original and distorted images attracts more and more attention of researchers. In addition, affine-invariant features extraction is an important component of many computer vision tasks such as image registration, object tracking, 3D reconstruction, and object recognition.
This paper studies methods of affine invariant features extraction in details, and the primary research productions are as follows:
(1) A method of object recognition based on covariant matrix is presented, which is applicable for object with less texture, homogeneous gray level, and strong contrast with background. Firstly, segment the object from background with auto multi-threshold method. Then calculate the covariant matrix of object area and define an ellipse with it, by decomposing the covariant matrix, normalize the ellipse to a cirle and compute the invariant feature vector. Finally, compute the affine matrix between objects, and translate the template for further recognition. The descriptor computed by the presented method is full affine invariant, and insentitive to change in illumination. In addition, according to the basic theory proposed, methods of computing affine parameters and measuring object 2D attitude are given, which have high accuracy.
(2) The method for extracting global invariant features based on MSA transform is studied, which is applicable for object in complicated background. Two improved methods against illumination change are proposed, which are MSA combined with direction code and MSA histogram invariant. Then two strategies for reducing computation load are discussed, which are blocking the image and discarding high frequency Fourier coefficients. Experimental results show that the improved methods are robust to illumination change, and the computation load is about 1/8 of that of the original algorithm.
(3) The method for extracting local invariants based on SIFT is studied, which is applicable for scene in which object is partly occluded. An image may have many areas that are locally similar to each other, and these multiple locally similar regions produce ambiguities when matching local descriptors, which may result in mismatches. A method integrating global scope is presented to resolve ambiguities while allow for non-rigid shape transformations, which can enhance the discrimination of descriptors and reduce the numbers of mismatches. In addition, according to properties of affine transformation, a method for rejecting mismatches is given, which is effective without effecting correct matches.
本论文对仿射不变特征的提取方法进行了详细的研究,主要研究成果分为以下三个方面:
(1)针对纹理不丰富、灰度分布均匀、具有一定的面积、与背景差异较大的目标,提出了一种基于目标区域协方差矩阵的目标识别方法。首先,利用自动多门限区域分割方法将目标从背景中分割出来;然后,求取目标区域的协方差矩阵,并用协方差矩阵定义一个椭圆区域,通过对协方差矩阵的分解,将椭圆区域归一化为圆域,求出仿射不变特征向量;最后,求出两幅图像中目标区域的仿射变换矩阵,将模板变换后进行进一步的识别。该方法具有完全的仿射不变性,且对光照变化不敏感。另外,基于本算法的理论,论文中还给出了仿射变换参数求解及目标姿态测量的新方法,且具有较高的精度。
(2)针对背景复杂、不易进行目标分割的图像,研究了基于MSA变换的全局不变特征提取方法。针对MSA变换对光照变化敏感的问题,提出了两种抗光照变化的算法——结合方向编码的MSA和MSA直方图不变量,并探讨了两种减少计算量的策略——分块和去掉傅里叶变换的高频分量。实验证明,改进的方法能有效克服光照变化的影响,且计算量大约是原来的1/8。
(3)针对目标被大面积遮挡时,无法用全局不变量进行识别的情况,研究了基于SIFT的局部不变特征提取方法。针对SIFT特征描述子对相似区域区分性差的问题,提出了一种结合全局形状信息的特征向量生成方法,该方法增强了SIFT特征描述子的可区分性,减少了误匹配点对的数量。另外,本论文依据仿射变换的性质,给出了一种剔除误匹配点对的方法,在不影响正确匹配点对的情况下取得了较好的效果。
With the urgent demand of precision strike weapons in our country, research work on scence matching has important significance for national defense. However the template and real-time image are gotton in different time and weather conditions, from different viewpoints, by different sensors, so there is a large distortion between them, and the traditional matcing methods based on gray-scale template can not position object accurately. Therefore extracting invariant features from the original and distorted images attracts more and more attention of researchers. In addition, affine-invariant features extraction is an important component of many computer vision tasks such as image registration, object tracking, 3D reconstruction, and object recognition.
This paper studies methods of affine invariant features extraction in details, and the primary research productions are as follows:
(1) A method of object recognition based on covariant matrix is presented, which is applicable for object with less texture, homogeneous gray level, and strong contrast with background. Firstly, segment the object from background with auto multi-threshold method. Then calculate the covariant matrix of object area and define an ellipse with it, by decomposing the covariant matrix, normalize the ellipse to a cirle and compute the invariant feature vector. Finally, compute the affine matrix between objects, and translate the template for further recognition. The descriptor computed by the presented method is full affine invariant, and insentitive to change in illumination. In addition, according to the basic theory proposed, methods of computing affine parameters and measuring object 2D attitude are given, which have high accuracy.
(2) The method for extracting global invariant features based on MSA transform is studied, which is applicable for object in complicated background. Two improved methods against illumination change are proposed, which are MSA combined with direction code and MSA histogram invariant. Then two strategies for reducing computation load are discussed, which are blocking the image and discarding high frequency Fourier coefficients. Experimental results show that the improved methods are robust to illumination change, and the computation load is about 1/8 of that of the original algorithm.
(3) The method for extracting local invariants based on SIFT is studied, which is applicable for scene in which object is partly occluded. An image may have many areas that are locally similar to each other, and these multiple locally similar regions produce ambiguities when matching local descriptors, which may result in mismatches. A method integrating global scope is presented to resolve ambiguities while allow for non-rigid shape transformations, which can enhance the discrimination of descriptors and reduce the numbers of mismatches. In addition, according to properties of affine transformation, a method for rejecting mismatches is given, which is effective without effecting correct matches.
引文
[1]章毓晋.图象处理和分析基础[M].北京:高等教育出版社,2002.1-20.
[2]鲁小锁.图像特征提取与匹配技术研究及其在对象识别中的应用[D]:[硕士学位论文].长春:吉林大学计算机科学与技术学院,2007.
[3]冷雪飞.基于图像特征的景象匹配辅助导航系统中关键技术研究[D]:[博士学位论文].南京:南京航空航天大学自动化学院,2007.
[4]孙即祥.模式识别中的特征提取与计算机视觉不变量[M].长沙:国防工业出版社,2001.228-230.
[5]唐涛.图像仿射不变特征及其在遥感图像目标识别中的应用[D]:[硕士学位论文].长沙:国防科学技术大学,2006.
[6] Hu M K. Visual pattern recognition by moment invariants [J].IRE Trans.Inform Theory, 1962, IT-8(2):179-187.
[7] Dudani S A. Aircraft identification by moment invariants [J]. IEEE Trans., 1977, 26(1):39-45.
[8] Wong R Y.,Hall E L. Scene matching with invariant moments [J]. Comput. Graphics Image Process, 1978, 8:16-24.
[9] Goshtasby A. Template matching in rotated images [J]. IEEE Trans. PAMI, 1985, 7:338-344.
[10] Flusser J, Suk T. A moment-based approach to registration of images with affine geometric distortion [J]. IEEE Transactions on GeoScience and Remote Sensing, 1994, 32(2):382-387.
[11] Flusser J, Suk T. Pattern recognition by affine moment invariant [J]. Pattern recognition, 1993, 26:167-174.
[12] Mukundan R, Malik N K. Attitude estimation using moment invariants [J]. Pattern Recognition Letters, 1993, 14:199-205.
[13] Sluzek A. Identification and inspection of 2-D objects using new moment-based shape descriptors [J]. Pattern recognition Letters, 1995, 16:687-697.
[14] Teb C H, Chin R T. On image analysis by the methods of moments [J]. IEEE Trans., PAMI, 1988, 10(4):496-513.
[15] Chen C C. Improved moment invariant for shape discrimination [J]. Pattern recognition, 1993, 26:683-686.
[16] Khotanzad A. Zernike moment based rotation invariant features for pattern recognition [J].SPIE, 1988, 1002:212-219.
[17]张天序.成像自动目标识别[M].武汉:湖北科学技术出版社,2003.51-56.
[18] Teague M R. Image analysis via the general theory of moments [J]. J.Opt.Soc.Amer. 1980, 70:920-930.
[19] Flusser J. On Independence of rotation moment invariants [J]. Pattern Recognition, 2000, 33:1405-1410.
[20] Khotanzad A, Hong Y H. Invariant image recognition by Zernike moments [J]. IEEE Trans.on PAMI, 1990, 12(5):489-497.
[21] Yang ZH W, Cohen F S. Cross-weighted moments and affine invariants for image registration and matching [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1999, 21(8).
[22]赵军,曲仕茹.基于同底三角形面积比的飞机外形识别方法研究[J].兰州交通大学学报(自然科学版),2005,24(6):94-97.
[23] Rothe I, Susse H, Voss K. The method of normalization to determine invariants [J]. IEEE Transactions on pattern analysis and machine intelligence, 1996, 18(4):366-370.
[24] Shen D G, Horace H.S. Generalized affine invariant image normalization [J]. IEEE Transactions on PAMI, 1997, 19(5):431-440.
[25] Zahn C T, Roskies R Z.Fourier descriptors for plane closed curves [J]. IEEE Transactions on Computers, 1972, 21(3):269-281.
[26] Arbter K, Snyder W E, Burkhardt H, et al.. Application of affine-invariant Fourier descriptors to recognition 3-D objects [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1990, 12(1):640-647.
[27] Gotze N, Drue S, Hartmann G. Invariant object recognition with discriminant features based on local fast-Fourier Mellin transform [J]. In Proceeding of International Conference on Pattern Recognition, 2000:950-951.
[28]张叶.基于人眼视觉机制的景象匹配制导技术研究[D]:[博士学位论文].长春:中国科学院长春光学精密机械与物理研究所,2008.
[29] Kadyrov A,Petrou M. The Trace transform and its application [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,23(8),2005:811-828.
[30] Petrou M,Kadyrov A. Affine invariant features from the Trace transform [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1):30-44.
[31] Rahtu E. Object recognition using multi-scale autoconvolution: M. Sc. thesis.Oulu, Finland:University of Oulu,2004
[32] Janne H. Multi-scale autoconvolution for affine invariant pattern recognition[C].In: Proceedings 16th International Conference on PatternRecognition (ICPR’02), 2002. 119-122.
[33] Rahtu E, Salo M,Heikkila J. Affine invariant pattern recognition using multiscale autoconvolution [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2005, 27(6):908-918.
[34] Khalil M I., Bayoumi M M. Affine invariants for object recognition using the Wavelet transform [J]. ELSEVIER Pattern Recognition Letters, 2002, 23, 57-72.
[35] Harris C, Stephens M. A combined corner and edge detector[C]. Proceedings of the 4th Alvey Vision Conference, 1988: 147-151.
[36] Crowley J. A representation for visual information [D]. Ph.D thesis, Carnegie Mellon University, 1981: 2-20.
[37] Koenderink J. The structure of image [J]. Biological Cybernetics, 1984, 50:363-396.
[38] Lindeberg T. Scale-space for discrete signals [J]. IEEE Transaction PAMI, 1980, 207:187-207.
[39] Lindeberg T. Feature detection with automatic scale selection [J]. International Journal of Computer Vision, 1998, 30(2): 79-116.
[40] Tuytelaars T, Gool V. Wide baseline stereo matching based on local, affinely invariant regions[C]. In: British Machine Vision Conference, BMVC 2000.
[41] Matas J, Chum O, Urban M, et al...Robust wide baseline stereo from maximally stable extremal regions[C]. In: British Machine Vision Conference, BMVC 2002.
[42] Mikolajczyk K, Schmid C. Scale&affine invariant interest point detectors [J]. International Journal of Computer Vision, 2004, 60(1):63-86.
[43] Mikolajczyk K, Schmid C. Indexing based on scale invariant interest points[C]. In: Proceeding of the 8th International Conference on Computer Vision, 2001:525-531.
[44] Lowe D G. Object recognition from local scale-invariant features[C]. Proceeding of the International Conference on Computer Vision (ICCV’1999), 1999:20-27.
[45] Lowe D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2):99-110.
[46] Mikolajczyk K, Tuytelaars T, Schmid C, et al.. A comparison of affine region detectors [J]. J. Computer Vision.
[47] Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2002, 2(4): 509-522.
[48] Canny J. A computational approach to edge detection [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
[49] Ke Y, Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors[C]. Proc. Conf. Computer Vision and Pattern Recognition, 2004: 511-517.
[50] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1615-1630.
[51] Gool V, Moons T, Ungureanu D. Affine/photometric invariants for planar intensity patterns[C]. Proc. Fourth European Conf. Computer Vision, 1996:642-651.
[52] Mindru F, Moons T, Gool L V. Recognition color patterns irrespective of viewpoint and illumination[C]. IEEE Conference on Computer Vision and Pattern Recognition, 1999, 1:368-373.
[53] Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets[C]. Proc. Seventh European Conf. Computer Vision, 2002: 414-431.
[54] Lazebnik S, Schmid C, Ponce J. Sparse texture representation using affine-invariant neighborhoods[C]. Proc. Conf. Computer Vision and Pattern Recognition, 2003: 319-324.
[55] Freeman W, Adelson E. The design and use of steerable filters [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1991, 13(9): 891-906.
[56] Koenderink J, Doorn A. Representation of local geometry in the visual system [J]. Biological Cybernetics, 1987, 55: 367-375.
[57]加拿大British Columbia大学智能计算实验室[EB/OL]. http://www.cs.ubc.ca/spider/lower/research.html.
[58] Brown M,Lowe D G. Recognising panoramas[C]. In: Proceedings 9th IEEE International Conference on Computer Vision (ICCV’2003), 2003, 2:1218-1225.
[59] Iryna G, Lowe D G. Scene modelling, recognition and tracking with invariant image features[C].In: Third IEEE and ACM International Symposium on Mixed and Augmented Reality, 2004.110-119.
[60] Stephen S, Lowe D G, Jim L. Local and global localization for mobile robots using visual landmarks[C]. Proceedings of the IEEE/RJS International Conference on Intelligent Robots and Systems, 2001. 414-420.
[61] Azad S, Farrokh J S. Using scale-invariant feature points in visual servoing[C]. In: Proceedings of the SPIE, 5603, 2004. 63-70.
[62]芬兰oulu大学机器视觉小组[EB/OL].http://www.ee.oulu.fi/mvg/mvg.php.
[63] Rahtu E, Salo M, Heikkila J. Convexity recognition using multi-scale autoconvolution[C]. In: Proceeding of the IEEE 17th International Conference on Pattern Recognition (ICPR’04), 2004. 692-695.
[64] Rahtu E, Heikkila J. Object classification with multi-scale autoconvolution[C]. In: Proceeding of the IEEE 17th International Conference onPattern Recognition (ICPR’04), 2004. 37-40.
[65] Kannala J, Rahtu E, Heikkila J. Affine registration with multi-scale autoconvolution[C]. In: IEEE International Conference on Image Processing (ICIP 2005), 2005. 1064-1067.
[66]英国Oxford大学机器人研究小组[EB/OL]. http://www.robots.ox.ac.Uk/%7Evgg/ research/affine/detectors.html.
[67]张建国.不变性纹理分析[D]:学位论文.北京:中国科学院自动化所,2002.
[68]周凤岐,孙剑,周军.一类基于模型的仿射代数不变量[J].火力与指挥控制,2007,32(7):126-131.
[69]黄智轶,张丽清.基于深度信息与尺度空间的仿射不变特征检测[J].计算机应用研究,2009,11:4338-4341.
[70]刘小军,杨杰,刘惠,等.基于主成分分析的仿射不变特征图像匹配方法[J].系统仿真学报,2008,20(4):977-980.
[71]王志衡,吴福朝,王旭光. Corner detection and sub-pixel localization based on local orientation distribution [J].软件学报,2008,19(11):2932-2942.
[72]谭铁牛,黄凯奇,余轶南.一种基于亚像素级特征点检测的图像匹配方法[P].中国专利,200910241542.7. 2009-10-24.
[73]谭铁牛,黄凯奇,余轶南。一种基于特征检测的图像匹配方法[P].中国专利,200910241543.1. 2009-10-24.
[74]谭铁牛,黄凯奇,张叶银。一种基于几何不变量的视角不变的行为识别方法[P].中国专利,200910081092.X. 2009-10-08.
[75]刘方.目标3D不变特征的提取与应用[D]:[博士学位论文].长沙:国防科学技术大学,2001.
[76]陈涛.图像仿射不变特征提取方法研究[D]:[博士学位论文].长沙:国防科学技术大学信息与通信工程系,2006.
[77]邓熠,李智勇,粟毅.仿射不变特征提取算法在遥感影像配准中的应用[J].中国图象图形学报,2009,14(4):615-621.
[78]雷琳,陈涛,李智勇,等.全局仿射变换条件下图像不变量提取新方法[J].国防科技大学学报,2008,30(4):64-70.
[79]陈涛,粟毅,蒋咏梅,等.利用仿射几何特性提取图像中的仿射不变特征[J].中国图象图形学报,2007,12(9):1633-1641.
[80]路鹰,张天序,史继川.基于仿射不变矩的三维多面体特征匹配识别[J].计算机与数字工程,2007,35(10):104-106.
[81]张天序,曹杨,刘进,等.基于不变矩的前视红外图像机场目标识别[J].华中科技大学学报(自然科学版),2007,35(1):17-19.
[82]刘进.不变量特征的构造及其在目标识别中的应用[D]:[博士学位论文].武汉:华中科技大学模式识别与智能系统专业,2004.
[83]邓宝松,高宇,魏迎梅,等.图像匹配中具有仿射不变性特征的定量分析[J].信号处理,2008,24(2):227-232.
[84]纪华,王大伟,赵建,等.基于协方差矩阵的目标二维姿态测量[J].光学精密工程,2009,17(11):2835-2841.
[85] Ji H, Li G J, Wang Y J. Affine object recognition and affine parameters estimation based on covariant matrix[C]. IEEE, ISISE 2008:14-18.
[86]张叶,曲宏松,王延杰,等.对数极坐标图像匹配在目标姿态测量中的应用[J].光电工程,2007,34(6):11-14.
[87]张伟,任仙怡,张桂林,等.基于对数极坐标变换和仿射变换的目标识别定位方法[J].中国图象图形学报,2006,11(9):1255-1259.
[88]纪华,张叶,韩广良,等.结合MSA与方向编码的快速景象匹配[J].光学精密工程,2010(6).
[89] Rahtu E, Salo M, Heikkila J. Multiscale convolution histogram for affine invariant pattern recognition [J]. Proc. the 16th British Machine Vision Conference, 2006.
[90]纪华,陈小林,王延杰.基于MSA直方图的景象匹配算法研究[J].激光与红外,2009,39(7):788-792.
[91]纪华,吴元昊,孙宏海,等.结合全局信息的SIFT特征匹配算法[J].光学精密工程,2009(2): 439-444.
[92]邸男.基于SIFT的末制导系统目标自动识别技术研究[D]:[博士学位论文].长春:中国科学院长春光学精密机械与物理研究所,2009.
[93] Tuo H Y, Jing ZH L, Zhang T H. Aerial sequence image mosaic using reduced sift dexcriptors [J]. Proc of SPIE, 2007, 6786:67862V-1-67862V-9.
[2]鲁小锁.图像特征提取与匹配技术研究及其在对象识别中的应用[D]:[硕士学位论文].长春:吉林大学计算机科学与技术学院,2007.
[3]冷雪飞.基于图像特征的景象匹配辅助导航系统中关键技术研究[D]:[博士学位论文].南京:南京航空航天大学自动化学院,2007.
[4]孙即祥.模式识别中的特征提取与计算机视觉不变量[M].长沙:国防工业出版社,2001.228-230.
[5]唐涛.图像仿射不变特征及其在遥感图像目标识别中的应用[D]:[硕士学位论文].长沙:国防科学技术大学,2006.
[6] Hu M K. Visual pattern recognition by moment invariants [J].IRE Trans.Inform Theory, 1962, IT-8(2):179-187.
[7] Dudani S A. Aircraft identification by moment invariants [J]. IEEE Trans., 1977, 26(1):39-45.
[8] Wong R Y.,Hall E L. Scene matching with invariant moments [J]. Comput. Graphics Image Process, 1978, 8:16-24.
[9] Goshtasby A. Template matching in rotated images [J]. IEEE Trans. PAMI, 1985, 7:338-344.
[10] Flusser J, Suk T. A moment-based approach to registration of images with affine geometric distortion [J]. IEEE Transactions on GeoScience and Remote Sensing, 1994, 32(2):382-387.
[11] Flusser J, Suk T. Pattern recognition by affine moment invariant [J]. Pattern recognition, 1993, 26:167-174.
[12] Mukundan R, Malik N K. Attitude estimation using moment invariants [J]. Pattern Recognition Letters, 1993, 14:199-205.
[13] Sluzek A. Identification and inspection of 2-D objects using new moment-based shape descriptors [J]. Pattern recognition Letters, 1995, 16:687-697.
[14] Teb C H, Chin R T. On image analysis by the methods of moments [J]. IEEE Trans., PAMI, 1988, 10(4):496-513.
[15] Chen C C. Improved moment invariant for shape discrimination [J]. Pattern recognition, 1993, 26:683-686.
[16] Khotanzad A. Zernike moment based rotation invariant features for pattern recognition [J].SPIE, 1988, 1002:212-219.
[17]张天序.成像自动目标识别[M].武汉:湖北科学技术出版社,2003.51-56.
[18] Teague M R. Image analysis via the general theory of moments [J]. J.Opt.Soc.Amer. 1980, 70:920-930.
[19] Flusser J. On Independence of rotation moment invariants [J]. Pattern Recognition, 2000, 33:1405-1410.
[20] Khotanzad A, Hong Y H. Invariant image recognition by Zernike moments [J]. IEEE Trans.on PAMI, 1990, 12(5):489-497.
[21] Yang ZH W, Cohen F S. Cross-weighted moments and affine invariants for image registration and matching [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1999, 21(8).
[22]赵军,曲仕茹.基于同底三角形面积比的飞机外形识别方法研究[J].兰州交通大学学报(自然科学版),2005,24(6):94-97.
[23] Rothe I, Susse H, Voss K. The method of normalization to determine invariants [J]. IEEE Transactions on pattern analysis and machine intelligence, 1996, 18(4):366-370.
[24] Shen D G, Horace H.S. Generalized affine invariant image normalization [J]. IEEE Transactions on PAMI, 1997, 19(5):431-440.
[25] Zahn C T, Roskies R Z.Fourier descriptors for plane closed curves [J]. IEEE Transactions on Computers, 1972, 21(3):269-281.
[26] Arbter K, Snyder W E, Burkhardt H, et al.. Application of affine-invariant Fourier descriptors to recognition 3-D objects [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1990, 12(1):640-647.
[27] Gotze N, Drue S, Hartmann G. Invariant object recognition with discriminant features based on local fast-Fourier Mellin transform [J]. In Proceeding of International Conference on Pattern Recognition, 2000:950-951.
[28]张叶.基于人眼视觉机制的景象匹配制导技术研究[D]:[博士学位论文].长春:中国科学院长春光学精密机械与物理研究所,2008.
[29] Kadyrov A,Petrou M. The Trace transform and its application [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,23(8),2005:811-828.
[30] Petrou M,Kadyrov A. Affine invariant features from the Trace transform [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1):30-44.
[31] Rahtu E. Object recognition using multi-scale autoconvolution: M. Sc. thesis.Oulu, Finland:University of Oulu,2004
[32] Janne H. Multi-scale autoconvolution for affine invariant pattern recognition[C].In: Proceedings 16th International Conference on PatternRecognition (ICPR’02), 2002. 119-122.
[33] Rahtu E, Salo M,Heikkila J. Affine invariant pattern recognition using multiscale autoconvolution [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2005, 27(6):908-918.
[34] Khalil M I., Bayoumi M M. Affine invariants for object recognition using the Wavelet transform [J]. ELSEVIER Pattern Recognition Letters, 2002, 23, 57-72.
[35] Harris C, Stephens M. A combined corner and edge detector[C]. Proceedings of the 4th Alvey Vision Conference, 1988: 147-151.
[36] Crowley J. A representation for visual information [D]. Ph.D thesis, Carnegie Mellon University, 1981: 2-20.
[37] Koenderink J. The structure of image [J]. Biological Cybernetics, 1984, 50:363-396.
[38] Lindeberg T. Scale-space for discrete signals [J]. IEEE Transaction PAMI, 1980, 207:187-207.
[39] Lindeberg T. Feature detection with automatic scale selection [J]. International Journal of Computer Vision, 1998, 30(2): 79-116.
[40] Tuytelaars T, Gool V. Wide baseline stereo matching based on local, affinely invariant regions[C]. In: British Machine Vision Conference, BMVC 2000.
[41] Matas J, Chum O, Urban M, et al...Robust wide baseline stereo from maximally stable extremal regions[C]. In: British Machine Vision Conference, BMVC 2002.
[42] Mikolajczyk K, Schmid C. Scale&affine invariant interest point detectors [J]. International Journal of Computer Vision, 2004, 60(1):63-86.
[43] Mikolajczyk K, Schmid C. Indexing based on scale invariant interest points[C]. In: Proceeding of the 8th International Conference on Computer Vision, 2001:525-531.
[44] Lowe D G. Object recognition from local scale-invariant features[C]. Proceeding of the International Conference on Computer Vision (ICCV’1999), 1999:20-27.
[45] Lowe D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2):99-110.
[46] Mikolajczyk K, Tuytelaars T, Schmid C, et al.. A comparison of affine region detectors [J]. J. Computer Vision.
[47] Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2002, 2(4): 509-522.
[48] Canny J. A computational approach to edge detection [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
[49] Ke Y, Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors[C]. Proc. Conf. Computer Vision and Pattern Recognition, 2004: 511-517.
[50] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1615-1630.
[51] Gool V, Moons T, Ungureanu D. Affine/photometric invariants for planar intensity patterns[C]. Proc. Fourth European Conf. Computer Vision, 1996:642-651.
[52] Mindru F, Moons T, Gool L V. Recognition color patterns irrespective of viewpoint and illumination[C]. IEEE Conference on Computer Vision and Pattern Recognition, 1999, 1:368-373.
[53] Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets[C]. Proc. Seventh European Conf. Computer Vision, 2002: 414-431.
[54] Lazebnik S, Schmid C, Ponce J. Sparse texture representation using affine-invariant neighborhoods[C]. Proc. Conf. Computer Vision and Pattern Recognition, 2003: 319-324.
[55] Freeman W, Adelson E. The design and use of steerable filters [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1991, 13(9): 891-906.
[56] Koenderink J, Doorn A. Representation of local geometry in the visual system [J]. Biological Cybernetics, 1987, 55: 367-375.
[57]加拿大British Columbia大学智能计算实验室[EB/OL]. http://www.cs.ubc.ca/spider/lower/research.html.
[58] Brown M,Lowe D G. Recognising panoramas[C]. In: Proceedings 9th IEEE International Conference on Computer Vision (ICCV’2003), 2003, 2:1218-1225.
[59] Iryna G, Lowe D G. Scene modelling, recognition and tracking with invariant image features[C].In: Third IEEE and ACM International Symposium on Mixed and Augmented Reality, 2004.110-119.
[60] Stephen S, Lowe D G, Jim L. Local and global localization for mobile robots using visual landmarks[C]. Proceedings of the IEEE/RJS International Conference on Intelligent Robots and Systems, 2001. 414-420.
[61] Azad S, Farrokh J S. Using scale-invariant feature points in visual servoing[C]. In: Proceedings of the SPIE, 5603, 2004. 63-70.
[62]芬兰oulu大学机器视觉小组[EB/OL].http://www.ee.oulu.fi/mvg/mvg.php.
[63] Rahtu E, Salo M, Heikkila J. Convexity recognition using multi-scale autoconvolution[C]. In: Proceeding of the IEEE 17th International Conference on Pattern Recognition (ICPR’04), 2004. 692-695.
[64] Rahtu E, Heikkila J. Object classification with multi-scale autoconvolution[C]. In: Proceeding of the IEEE 17th International Conference onPattern Recognition (ICPR’04), 2004. 37-40.
[65] Kannala J, Rahtu E, Heikkila J. Affine registration with multi-scale autoconvolution[C]. In: IEEE International Conference on Image Processing (ICIP 2005), 2005. 1064-1067.
[66]英国Oxford大学机器人研究小组[EB/OL]. http://www.robots.ox.ac.Uk/%7Evgg/ research/affine/detectors.html.
[67]张建国.不变性纹理分析[D]:学位论文.北京:中国科学院自动化所,2002.
[68]周凤岐,孙剑,周军.一类基于模型的仿射代数不变量[J].火力与指挥控制,2007,32(7):126-131.
[69]黄智轶,张丽清.基于深度信息与尺度空间的仿射不变特征检测[J].计算机应用研究,2009,11:4338-4341.
[70]刘小军,杨杰,刘惠,等.基于主成分分析的仿射不变特征图像匹配方法[J].系统仿真学报,2008,20(4):977-980.
[71]王志衡,吴福朝,王旭光. Corner detection and sub-pixel localization based on local orientation distribution [J].软件学报,2008,19(11):2932-2942.
[72]谭铁牛,黄凯奇,余轶南.一种基于亚像素级特征点检测的图像匹配方法[P].中国专利,200910241542.7. 2009-10-24.
[73]谭铁牛,黄凯奇,余轶南。一种基于特征检测的图像匹配方法[P].中国专利,200910241543.1. 2009-10-24.
[74]谭铁牛,黄凯奇,张叶银。一种基于几何不变量的视角不变的行为识别方法[P].中国专利,200910081092.X. 2009-10-08.
[75]刘方.目标3D不变特征的提取与应用[D]:[博士学位论文].长沙:国防科学技术大学,2001.
[76]陈涛.图像仿射不变特征提取方法研究[D]:[博士学位论文].长沙:国防科学技术大学信息与通信工程系,2006.
[77]邓熠,李智勇,粟毅.仿射不变特征提取算法在遥感影像配准中的应用[J].中国图象图形学报,2009,14(4):615-621.
[78]雷琳,陈涛,李智勇,等.全局仿射变换条件下图像不变量提取新方法[J].国防科技大学学报,2008,30(4):64-70.
[79]陈涛,粟毅,蒋咏梅,等.利用仿射几何特性提取图像中的仿射不变特征[J].中国图象图形学报,2007,12(9):1633-1641.
[80]路鹰,张天序,史继川.基于仿射不变矩的三维多面体特征匹配识别[J].计算机与数字工程,2007,35(10):104-106.
[81]张天序,曹杨,刘进,等.基于不变矩的前视红外图像机场目标识别[J].华中科技大学学报(自然科学版),2007,35(1):17-19.
[82]刘进.不变量特征的构造及其在目标识别中的应用[D]:[博士学位论文].武汉:华中科技大学模式识别与智能系统专业,2004.
[83]邓宝松,高宇,魏迎梅,等.图像匹配中具有仿射不变性特征的定量分析[J].信号处理,2008,24(2):227-232.
[84]纪华,王大伟,赵建,等.基于协方差矩阵的目标二维姿态测量[J].光学精密工程,2009,17(11):2835-2841.
[85] Ji H, Li G J, Wang Y J. Affine object recognition and affine parameters estimation based on covariant matrix[C]. IEEE, ISISE 2008:14-18.
[86]张叶,曲宏松,王延杰,等.对数极坐标图像匹配在目标姿态测量中的应用[J].光电工程,2007,34(6):11-14.
[87]张伟,任仙怡,张桂林,等.基于对数极坐标变换和仿射变换的目标识别定位方法[J].中国图象图形学报,2006,11(9):1255-1259.
[88]纪华,张叶,韩广良,等.结合MSA与方向编码的快速景象匹配[J].光学精密工程,2010(6).
[89] Rahtu E, Salo M, Heikkila J. Multiscale convolution histogram for affine invariant pattern recognition [J]. Proc. the 16th British Machine Vision Conference, 2006.
[90]纪华,陈小林,王延杰.基于MSA直方图的景象匹配算法研究[J].激光与红外,2009,39(7):788-792.
[91]纪华,吴元昊,孙宏海,等.结合全局信息的SIFT特征匹配算法[J].光学精密工程,2009(2): 439-444.
[92]邸男.基于SIFT的末制导系统目标自动识别技术研究[D]:[博士学位论文].长春:中国科学院长春光学精密机械与物理研究所,2009.
[93] Tuo H Y, Jing ZH L, Zhang T H. Aerial sequence image mosaic using reduced sift dexcriptors [J]. Proc of SPIE, 2007, 6786:67862V-1-67862V-9.