基于深度图像的三维目标识别技术研究
|
摘要
在最新的激光成像精确制导技术中,利用三维激光雷达图像获取的三维目标数据进行三维目标识别是需要解决的一个关键问题。在三维视觉理论中,三维目标识别是一个极富挑战性的难题,本文紧扣三维目标识别这个核心问题,对基于深度图像的三维目标识别技术进行了细致深入的研究。本文的主要工作和创新成果如下:
(1)深度图像的表示是实现三维目标识别的前提。在研究当前各种深度图像获取手段的基础上,提出了将深度图像分为伪灰度表示、网格表示和点云表示的分类方法,并对各种深度图像表示方法进行了分析。
(2)根据伪灰度表示深度图像的特性,研究了深度图像的曲面特性的直接计算、数值估计和曲面拟合等几种方法。针对现有拟合方法均为局部拟合的特点,创新地提出了利用移动最小二乘方法实现深度图像整体拟合的方法,得到待拟合曲面的一种隐式整体表达,仿真试验结果表明这种整体拟合方法不仅具备很好的拟合精度,而且便于对曲面特性进行计算。在此基础上,推广得到了基于最小二乘的曲面拟合一般性模型框架。该模型框架不仅对已有的各种不同拟合方法进行了本质上的理论区分,也为探索新的深度图像拟合方法指明了道路。
(3)针对现有三维目标表达方法无法有效解决自由形态物体整体表达的问题,提出了利用形状索引直方图和距离直方图这样的整体特征来进行三维目标识别的新方法,构建了基于形状索引直方图的目标识别算法流程。仿真结果表明,该方法可以有效避免了计算代价极大的特征点对的对应性搜索,并且能够较好地满足三维目标识别中的旋转和尺度不变性。
(4)为了解决三维目标姿态多样性所导致的不变量难以实现的问题,提出了三维目标识别中的相关不变性这一全新概念。并根据通过整体识别整体的思想提出了基于Tsallis熵和旋转图像的三维目标识别方法,首先利用旋转图像将三维目标识别问题映射成二维问题,然后采用Tsallis熵对旋转图像特征进行表达,实现了数据的急剧衰减,避免了繁琐的特征点对匹配搜索,并在理论上证明的该方法的平移、旋转和缩放变换下相关不变性,理论分析和实验数据表明该方法具有极高的三维目标识别正确率。
Making use of three-dimensional target data obtained from the three-dimensional laser radar to recognize three-dimensional object is the core process of lasted precision guided weapon technology. In three-dimensional computer vision, three-dimensional object recognition plays a prominent role and is a hard and challenging task. This thesis takes three-dimensional object recognition as the study’s core and has a detailed in-depth study to three-dimensional object recognition based on range images. The main work is summarized as follows:
(1) In three-dimensional computer vision range image’s representation is the base of three dimensional object recognition. These thesis summaries the range image’s representation as three types, these are pseudo-gray representation, gird representation and point cloud representation.
(2) According to the properties of range image with pseudo-gray representation, this thesis studies three methods of calculation of curvature properties, they are respectively direct calculation method; Numerical estimates method and Surface Fitting methods. since the existing fitting methods are local fitting methods, this thesis presents a new global surface fitting scheme by using moving least squares methods. Compared with the standard least squares, moving least squares method can obtain an implicit general representation and better fitting accuracy. This thesis generalizes the moving least squares methods and deduces a general model frame of surface fitting. This frame not only demonstrates the Theoretical difference of all the surface fitting methods and also indicates a direction to design new surface fitting method.
(3) As we all know, the existing representations of free-form 3D objects are local representations .In view of this, this thesis proposes a new three-dimensional object recognition method based on shape index histogram and range histogram. This method not only avoids the search of characteristic corresponding points and satisfies to a certain extent rotation invariance, translation invariance and scale invariance.
(4) In three-dimensional computer vision constructing pure invariant is very difficult. In view of this, the paper defines a correlation invariability with a relaxative standard and proposes a new three-dimensional object recognition method based on Tsallis entropy and spin images. This method achieve the rapid decay of data and avoid search of characteristic corresponding points, moreover this representation possesses rotation invariance, translation invariance and scale invariance. Theoretical analysis and simulations prove this method’s high performance in three dimensional object recognition.
(1)深度图像的表示是实现三维目标识别的前提。在研究当前各种深度图像获取手段的基础上,提出了将深度图像分为伪灰度表示、网格表示和点云表示的分类方法,并对各种深度图像表示方法进行了分析。
(2)根据伪灰度表示深度图像的特性,研究了深度图像的曲面特性的直接计算、数值估计和曲面拟合等几种方法。针对现有拟合方法均为局部拟合的特点,创新地提出了利用移动最小二乘方法实现深度图像整体拟合的方法,得到待拟合曲面的一种隐式整体表达,仿真试验结果表明这种整体拟合方法不仅具备很好的拟合精度,而且便于对曲面特性进行计算。在此基础上,推广得到了基于最小二乘的曲面拟合一般性模型框架。该模型框架不仅对已有的各种不同拟合方法进行了本质上的理论区分,也为探索新的深度图像拟合方法指明了道路。
(3)针对现有三维目标表达方法无法有效解决自由形态物体整体表达的问题,提出了利用形状索引直方图和距离直方图这样的整体特征来进行三维目标识别的新方法,构建了基于形状索引直方图的目标识别算法流程。仿真结果表明,该方法可以有效避免了计算代价极大的特征点对的对应性搜索,并且能够较好地满足三维目标识别中的旋转和尺度不变性。
(4)为了解决三维目标姿态多样性所导致的不变量难以实现的问题,提出了三维目标识别中的相关不变性这一全新概念。并根据通过整体识别整体的思想提出了基于Tsallis熵和旋转图像的三维目标识别方法,首先利用旋转图像将三维目标识别问题映射成二维问题,然后采用Tsallis熵对旋转图像特征进行表达,实现了数据的急剧衰减,避免了繁琐的特征点对匹配搜索,并在理论上证明的该方法的平移、旋转和缩放变换下相关不变性,理论分析和实验数据表明该方法具有极高的三维目标识别正确率。
Making use of three-dimensional target data obtained from the three-dimensional laser radar to recognize three-dimensional object is the core process of lasted precision guided weapon technology. In three-dimensional computer vision, three-dimensional object recognition plays a prominent role and is a hard and challenging task. This thesis takes three-dimensional object recognition as the study’s core and has a detailed in-depth study to three-dimensional object recognition based on range images. The main work is summarized as follows:
(1) In three-dimensional computer vision range image’s representation is the base of three dimensional object recognition. These thesis summaries the range image’s representation as three types, these are pseudo-gray representation, gird representation and point cloud representation.
(2) According to the properties of range image with pseudo-gray representation, this thesis studies three methods of calculation of curvature properties, they are respectively direct calculation method; Numerical estimates method and Surface Fitting methods. since the existing fitting methods are local fitting methods, this thesis presents a new global surface fitting scheme by using moving least squares methods. Compared with the standard least squares, moving least squares method can obtain an implicit general representation and better fitting accuracy. This thesis generalizes the moving least squares methods and deduces a general model frame of surface fitting. This frame not only demonstrates the Theoretical difference of all the surface fitting methods and also indicates a direction to design new surface fitting method.
(3) As we all know, the existing representations of free-form 3D objects are local representations .In view of this, this thesis proposes a new three-dimensional object recognition method based on shape index histogram and range histogram. This method not only avoids the search of characteristic corresponding points and satisfies to a certain extent rotation invariance, translation invariance and scale invariance.
(4) In three-dimensional computer vision constructing pure invariant is very difficult. In view of this, the paper defines a correlation invariability with a relaxative standard and proposes a new three-dimensional object recognition method based on Tsallis entropy and spin images. This method achieve the rapid decay of data and avoid search of characteristic corresponding points, moreover this representation possesses rotation invariance, translation invariance and scale invariance. Theoretical analysis and simulations prove this method’s high performance in three dimensional object recognition.
引文
[1] Arnold G, Klausutis T, Sturtz K. Three-Dimensional Laser Radar Recognition Approaches[C]. Computer Vision Beyond the Visible Spectrum,2005,71-114.
[2]范保虎,赵长明,纪荣炜.非扫描激光主动成像制导技术及导引规律的研究[J]. 2009, 30(9):1264-1267.
[3] Letalick D, Ahlberg J r, Andersson P. 3-D Imaging by Laser Radar and Applications in Preventing and Combating Crime and Terrorism[R]: FOI. 2004.
[4] Pierre A. Automatic Target Recognition from Laser Radar Data[R]: Swedish Defence Research Agency (FOI). 2003.
[5] Milan S, Vaclav H, Roger B. Image Processing,Analysis,and Machine Vision[M]: Thomson, 2002.
[6] Forsyth D A, Ponce J. Computer Vision: A Modern Approach[M]: Prentice Hall, 2003.
[7] Gordon I. Theories of visual perception[M].England: Wiley, 1989.
[8] Yantis S. Visual perception: essential readings[M].Philadelphia: Psychology Press, 2001.
[9] Darbandi H B, Ito M R, Little J. Clustered Signatures for Modeling and Recognizing 3D Rigid Objects[C]. Processings of the World Academy of Science, Engineering And Technology,2008,27-35.
[10] Fisher. Dictionary of computer vision and image processing[M]: John Wiley&Sons,Ltd, 2005.
[11] Arman F, Aggarwal J K. Model-based object recognition in dense-range images—a review[J]. ACM Comput Surv. 1993, 25(1):5-43.
[12] Salvi J, Matabosch C, Fofi D,et al. A review of recent range image registration methods with accuracy evaluation[J]. Image and Vision Computing. 2007, 25(5):578-596.
[13] Chua C S, Jarvis R. Point Signatures: A New Representation for 3D Object Recognition[J]. International Journal of Computer Vision. 1997, 25(1):63-85.
[14] Johnson A E, Sing B K. Registration and integration of textured 3-D data[C]. Processings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling,1997,234-241.
[15] Feldmar J, Ayache N. Rigid, affine and locally affine registration of free-form surfaces[R]: INRIA. 1994.
[16] Luciano S, Olga B, Kim B. Robust Range Image Registration Using Genetic Algorithms[M].Danvers: World Scientific Publishing Co. Pte. Ltd., 2005.
[17] Besl P J, McKay H D. A method for registration of 3-D shapes[J]. Transactions on Pattern Analysis and Machine Intelligence. 1992, 14(2):239-256.
[18]李世飞,王平,沈振康.迭代最近邻点算法研究进展[J].信号处理. 2009, 25(10):1582-1588.
[19] Levoy M. The digital Michelangelo project[C]. Processings of the Second International Conference on 3-D Digital Imaging and Modeling,1999,2-11.
[20] Masuda T, Sakaue K, Yokoya N. Registration and integration of multiple range images for 3-D model construction[C]. Processings of the 13th International Conference on Pattern Recognition,1996,879-883.
[21] Boissonnat. Geometric Structures for Three-Dimensional Shape Representation[J]. ACM Transactions on Graphics. 1984, 3(4):266-286.
[22] Chu-Song C, Yi-Ping H, Ja-Ling W. Model-based object recognition using range images by combining morphological feature extraction and geometric hashing[C]. Processings of the 13th International Conference on Pattern Recognition,1996,565-569.
[23] Edelsbrunner H, Mucke E P. Three-Dimensional Alpha Shapes[C]. Processings of,1992,75-82.
[24] Bajaj, Brenardini, Xu. Automatic reconstruction of surfaces and scalar fields from 3D scans[C]. Processings of the 22nd annual conference on Computer graphics and interactive techniques,1995,109-118.
[25]谢凯,汤晓安,郝建新,et al.一种基于多幅深度图像的混合建模方法[J].小型微型计算机系统. 2003, 24(1):94-96.
[26] Greg T, Marc L. Zippered Polygon Meshes from Range Images[C]. Processings of the 21st Annual Conference on Computer Graphics and Interactive Techniques,1994,311-318.
[27]张宗华,彭翔,胡小唐.深度图像合成的主次缝合线方法[J].工程图学学报. 2001, 22(2):102-109.
[28] Jain A K, Dorai C. 3D object recognition: Representation and matching[J]. Statistics and Computing. 2000, 10(2):167-182.
[29] Lee Y-L, Park R-H. A surface-based approach to 3-D object recognition using a mean field annealing neural network[J]. Pattern Recognition. 2002, 35(2):299-316.
[30]方昭江,丁明跃.基于模型的自由形态物体匹配方法研究[J].红外与激光工程. 1999, 28(3):5-8.
[31] Suk M, Bhandarkar S. Three dimensianal object recognition from range images[M].New York: Spring-Verlag, 1992.
[32]李庆,周曼丽.三维物体识别研究进展[J].中国图象图形学报:A辑. 2000, 5(12):985-993.
[33] Chen H, Bhanu B. 3D free-form object recognition in range images using local surface patches[J]. Pattern Recognition Letters. 2007, 28(10):1252-1262.
[34] Schütz C. Geometric point matching of free-form 3D objects[D].Neuchatel, Switzerland: University of Neuchatel, 1998.
[35] Campbell R J, Flynn P J. A Survey Of Free-Form Object representation and Recognition Techniques[J]. Computer Vision and Image Understanding. 2001, 81(2):166-210.
[36] Besl P J. The free-form surface matching problem[C],1990,25–71.
[37] Stein F, Medioni G. Structural Indexing: Efficient 3-D Object Recognition[J]. IEEE Trans Pattern Anal Mach Intell. 1992, 14(2):125-145.
[38] Dorai C, Jain A K. COSMOS--A representation scheme for 3D free-form objects[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 1997, 19(10):1115-1130.
[39] Zhang D, Hebert M. Harmonic maps and their applications in surface matching[C]. Processings of the IEEE Computer Society Conference on. Computer Vision and Pattern Recognition,1999,524-530.
[40] Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2002, 24(24):509–522.
[41] Frome A, Huber D, Kolluri R,et al. Recognizing Objects in Range Data Using Regional Point Descriptors[C]. Processings of the Eighth European Conference on Computer Vision,2004,224-237.
[42] Chin R T, Dyer C R. Model-based recognition in robot vision[J]. ACM Comput Surv. 1986, 18(1):67-108.
[43] Mahmoudi S, Daoudi M. 3D models retrieval by using characteristic views[C]. Processings of the 16th International Conference on Pattern Recognition,2002,457-460.
[44] Hui C, Bir B. 3D free-form object recognition in range images using local surface patches[C]. Processings of the 17th International Conference on Pattern Recognition,2004,136- 139
[45]何文峰.大型场景三维重建中的深度图像配准[D].北京:北京大学, 2004.
[46] Takeguchi T, Kaneko S. Using Depth Aspect Images for Robust and Efficient Search of Multiple Objects in Optomechatronic Sensing[J]. IEEE Transactions on Industrial Electronics. 2005, 52(4):1041- 1049.
[47] Cantzler H. An overview of range images[Z]. http://homepages.inf.ed.ac.uk/ rbf/CVonline/LOCAL_COPIES/CANTZLER2/range.html, 2008.
[48] Bosche F, Haas C T. Investigation of Data Formats for the Integration of 3D Sensed and 3D CAD data for Improved Equipment Operation Safety[C]. Processings of the 1st International Construction Specialty Conference,2006,1-9.
[49] Lu T. Triangular mesh generation for surfaces of 3D objects[D].Hawaii: University of Hawaii, 2000.
[50]周颖.深度图像的获取及其处理[D].陕西西安:西安电子科技大学, 2008.
[51]蔺宏伟.离散几何信息处理——从点到面[D].浙江杭州:浙江大学, 2003.
[52]章大勇,吴文启,吴美平,et al.基于三维Hough变换的机载激光雷达平面地标提取[J].国防科技大学学报. 2010, 32(2):130-134.
[53]龚俊斌.激光成像雷达图像融合匹配系统的设计与实现[D]:华中科技大学,模式识别与智能系统, 2005.
[54]蒋颖.深度图像配准方法的研究与实现[D].北京:北京航空航天大学, 2007.
[55] Shilane P, Min P, Kazhdan M. The Princeton Shape Benchmark[C]. Processings of the Shape Modeling International,2004.
[56]贾云得.机器视觉[M].北京:科学出版社, 2000.
[57] Ball M. Terrestrial 3D Laser Scanner Capture Reality[Z]. www.geoworld.com, 2004.
[58] Suk-Ho L, Jin Keun S. Noise removal with Gauss curvature-driven diffusion[J]. Image Processing, IEEE Transactions on. 2005, 14(7):904-909.
[59]方惠兰,王国瑾, Ping X,et al.三角网格曲面上离散曲率估算方法的比较与分析[J].计算机辅助设计与图形学学报. 2005, 17(11):2500-2507.
[60] Lipschutz M M. Differential Geometry[M].New York: McGraw-Hill, 1969.
[61]孟道骥,梁科.微分几何[M].北京:科学出版社, 1999.
[62]吴剑煌,刘伟军,王天然,et al.点采样曲面曲率估计[J].仪器仪表学报. 2006, (12).
[63] Rugis J, Klette R. A Scale Invariant Surface Curvature Estimator[J]. Advances in Image and Video Technology. 2006:138-147.
[64] Magid E, Soldea O, Rivlin E. A comparison of Gaussian and mean curvature estimation methods on triangular meshes of range image data[J]. Computer Vision and Image Understanding. 2007, 107(3):139-159.
[65]张涛,平西建,柳葆芳,et al.一种深度图像中的表面曲率估计算法[J].数据采集与处理. 2001, 16(01):47-51.
[66] El-Fallah A I, Ford G E. Mean curvature evolution and surface area scaling in image filtering[J]. Image Processing, IEEE Transactions on. 1997, 6(5):750-753.
[67]王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京:科学出版社, 2008.
[68] Flynn P J, Jain A K. On Reliable Curvature Estimation[C]. Processings of the Internaltional Conference on Computer Vision and Pattern Recogintion,1989,110-116.
[69] Krsek P, Lukacs G, Martin R R. Algorithms for computing curvatures from range data[C]. The Mathematics of Surfaces VIII, Information Geometers,1999,1-16.
[70]邹宁.深度图像分析方法研究[D]:华中理工大学,通信与信息系统, 2000.
[71]刘恩国.基于深度图象的三维视觉关键问题的研究[D]:上海交通大学, N1 - 2009-05-27 12:29:00, 1999.
[72] Sapiro G. Geometric Partial differential Equations and Image Analysis[M].Cambridge: Cambridge University Press, 2001.
[73]李松涛.深度图像处理方法的研究[D].北京:清华大学, 1999.
[74]于寅.高等工程数学(第三版)[M].武汉:华中科技大学出版社, 2001.
[75]李松涛,张长水,荣钢,et al.一种基于最小二乘估计的深度图像曲面拟合方法[J].自动化学报. 2002, 28(02):310-313.
[76] Chen H. Human ear recognition in three dimensions[D]: University of California, Riverside., M1 - Ph.D., 2006.
[77] Gautschi W. Orthogonal polynomials: computation and approximation[M]: Oxford University Press, 2004.
[78]施法中.计算机辅助几何设计于非均匀有理B样条[M].北京:北京航空航天大学出版社, 1994.
[79]王秀丽,宁正元.基于高斯曲率的曲面光顺方法研究[J].计算机工程. 2006, 32(16):207-210.
[80]李涛. Matlab工具箱应用指南:应用数学篇[M].北京:电子工业出版社, 2000.
[81] Lancaster P, Salkauskas K. Surfaces generated by moving least squares methods[J]. Mathematics of Computation. 1981, 37(155):141-158.
[82] Belytschko T, Lu Y Y, Gu L. Element-free galerkin methods[J]. International Journal for Numerical Methods in Engineering. 1994, 37:229~256.
[83]李世飞,王平,沈振康.利用移动最小二乘法进行深度图像曲面拟合[J].吉林大学学报(工学版). 2010, 40(1):229-233.
[84] Liu G R, Gu Y T. An Introduction to Meshfree Methods and Their Programming[M]: Springer, 2005.
[85]左传伟,聂玉峰,赵美玲.移动最小二乘法中影响半径的选取[J].工程数学学报. 2005, 22(5):833-838.
[86]陈美娟,程玉民.改进的移动最小二乘法[J].力学季刊. 2003, (02).
[87]张雄,刘岩.无网格法[M].北京:清华大学出版社/Springer, 2004.
[88]朱浩,方宗德,杨宏斌.基于NURBS曲面拟合的图像边缘检测方法[J].洛阳工学院学报. 2001, 22(1).
[89] Marr D. Vision[M].San Francisco: Freeman, 1982.
[90] Ko K H. Algorithms for Three-Dimensional Free-Form Object Matching[D].Boston: Massachusetts Institute of Technology, 2003.
[91] Ko K H, Maekawa T, Patrikalakis N M. An algorithm for optimal free-form object matching[J]. Computer-Aided Design. 2003, 35(10):913-923.
[92] Mokhtarian F, Khalili N, Yuen P. Multi-scale free-form 3D object recognition using 3D models[J]. Image and Vision Computing. 2001, (19):271-281.
[93]胡薇.基于子空间的3D目标识别和姿态估计方法[J].红外与激光工程. 2004, 33(6).
[94] Dinh H Q, Kropac S. Multi-Resolution Spin-Images[C]. Processings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006,863- 870.
[95]周明全,樊亚春,耿国华.一种基于空间对称的三维模型形状描述方法[J].电子学报. 2010, 38(4):853-858.
[96] Salgian A S. Using Multiple Patches for 3D Object Recognition[J]. 2007.
[97] Johnson A E. Spin-Images: A Representation for 3-D Surface Matching[D].Pittsburgh: Carnegie Mellon University, 1997.
[98]王子璇.利用角度签名进行3维表面配准[J].中国图象图形学报. 2008, 13(08):1538-1543.
[99] Lowe D G. Object recognition from local scale-invariant features[C]. Processings of the The Proceedings of the Seventh IEEE International Conference on Computer Vision,1999,1150-1157.
[100] Abdel-Hakim A E, Farag A A. CSIFT: A SIFT Descriptor with Color Invariant Characteristics[C]. Processings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006,1978-1983.
[101] Ke Y, Sukthankar R. PCA-SIFT: A More Distinctive Representation for Local Image Descriptors[C]. Processings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2004,506-513.
[102] Mikolajczyk K. Detection of local features invariant to affine transformations[D].France,Grenoble Institute National Polytechnique de Grenoble, 2002.
[103]陈涛.图像仿射不变特性研究[D]:湖南长沙:国防科技大学, 2006.
[104] Laxmikanthamma.统计与真理——怎样运用偶然性[M].北京:科学出版社, 2005.
[105] Hetzel G, Leibe B, Levi P,et al. 3D object recognition from range images using local feature histograms[C]. Processings of the Computer Vision and Pattern Recognition,2001,394-399.
[106] Schenider P J, Eberly D H. Geometric Tools for Computer Graphics[M]: Elsevier, 2004.
[107] Koenderink J J, Doorn A V. Surface shape and curvature scales[J]. Image Vision Comput. 1992, 10(8):557–565.
[108] Cantzler H, Fisher R B. Comparison of HK and SC curvature description methods[C]. Processings of the Third International Conference on 3-D Digital Imaging and Modeling,2001,285-291.
[109] Iyer N, Jayanti S, Lou K,et al. Three-dimensional shape searching: state-of-the-art review and future trends[J]. Computer-Aided Design Geometric Modelingand Processing 2004. 2005, 37(5):509-530.
[110]孙即祥.数字图像处理[M].石家庄:河北教育出版社, 1992.
[111] Schiele B, Crowley J L. Recognition without Correspondence using Multidimensional Receptive Field Histograms[J]. International Journal of Computer Vision. 2000, 36(1):31-50.
[112] Basseville M. Information:entropies,divergences et moyennes[R]: IRISA. 1996.
[113] Press W H, Teukolsky S A, Vettering W T. Numerical Recipes in C[M]: Cambridge University Press, 1992.
[114] Swain M J, Ballard D H. Color indexing[J]. International Journal of Computer Vision. 1991, 7(1):11-32.
[115]周海芳.遥感图像并行处理算法的研究和应用[D], 2003.
[116] Johnson A E, Hebert M. Using spin images for efficient object recognition in cluttered 3D scenes[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 1999, 21(5):433-449.
[117] Assfalg J, Bertini M, Del B A,et al. Content-based retrieval of 3-D objects using Spin Image Signatures[J]. IEEETransactions on Multimedia. 2007, 9(3):589-599.
[118] Bock M E, Cortelazzo G M, Ferrari C,et al. Identifying similar surface patches on proteins using a spin-image surface representation[C]. Lecture Notes in Computer Science,2005,417-428.
[119] Darbandi H B, Ito M R, Little J. Content-based retrieval of 3-D objects using Spin Image Signatures[C]. Processings of the World Academy Of Science, Engineering And Technology,2008,27-35.
[120] Wang Y M, Pan G, Wu Z H,et al. Sphere-spin-image: A viewpoint-invariant surface representation for 3D face recognition[C]. Processings of the SPIE Volume 3037,2004,427-434.
[121]郭树华,胡平,李运兴.基于旋转图像和高度图像的曲面局部形状识别[J].中国机械工程. 2003, 14(16):1413-1417.
[122] Matzka S, Petillot Y R, Wallace A M. Determining Efficient Scan-Patterns for 3-D Object Recognition Using Spin Images[C]. Lecture Notes in Computer Science,2007,559-570.
[123] Besl P J, Jain R C. Invariant surface characteristics for 3D object recognition in range images[J]. Computer Vision, Graphics and Image Processing. 1986, 33(1):33-80.
[124] Forsyth D, Mundy J L, Zisserman A,et al. Invariant descriptors for 3D object recognition and pose[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1991, 13(10):971-991.
[125] Wood J. Invariant pattern recognition: A review[J]. Pattern Recognition. 1996, 29(1):1-17.
[126] Jinhui C, Ishii S. Invariant recognition and segmentation of 3D object using Liealgebra models Invariant recognition and segmentation of 3D object using Lie algebra models[C]. Processings of,1999,550-554 vol.551.
[127] Manay S, Hong B-W, Yezzi A J,et al. Integral Invariant Signatures[C]. Processings of the Eighth European Conference on Computer Vision,2004,87-99.
[128] Rothganger F, Lazebnik S, Schmid C,et al. 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints[J]. International Journal of Computer Vision. 2006, 66(3):231-259.
[129] Chen C-C. Improved moment invariants for shape discrimination[J]. Pattern Recognition. 1993, 26(5):683-686.
[130] Mercimek M, Gulez K. 3D Real Object Recognition on the Basis of Moment Invariants and Neural Networks[C]. Processings of the The 19th International Symposium on Computer and Information Sciences,2004,410-419.
[131] Chen J-L, Stockman G C. 3D Free-Form Object Recognition Using Indexing by Contour Features[J]. Computer Vision and Image Understanding. 1998, 71(3):334-355.
[132] Johnson A E, Hebert M. Surface matching for object recognition in complex three-dimensional scenes[J]. Image and Vision Computing. 1998, 16(9-10):635-651.
[133] Tsallis C. Possible generalization of Boltzmann-gibbs statistics[J]. Journal of Statistics Physics. 1988, 52(1-2):479-487.
[134] Anonymous. Konstanz 3D Model Repository[Z]. http://www.inf.uni-konstanz. de/, 2009.
[135] Stamos I, Allen P K. 3-D Model Construction Using Range and Image Data[C]. Processings of the IEEE Conference on Computer Vision and Pattern 2000,1531-1538.
[2]范保虎,赵长明,纪荣炜.非扫描激光主动成像制导技术及导引规律的研究[J]. 2009, 30(9):1264-1267.
[3] Letalick D, Ahlberg J r, Andersson P. 3-D Imaging by Laser Radar and Applications in Preventing and Combating Crime and Terrorism[R]: FOI. 2004.
[4] Pierre A. Automatic Target Recognition from Laser Radar Data[R]: Swedish Defence Research Agency (FOI). 2003.
[5] Milan S, Vaclav H, Roger B. Image Processing,Analysis,and Machine Vision[M]: Thomson, 2002.
[6] Forsyth D A, Ponce J. Computer Vision: A Modern Approach[M]: Prentice Hall, 2003.
[7] Gordon I. Theories of visual perception[M].England: Wiley, 1989.
[8] Yantis S. Visual perception: essential readings[M].Philadelphia: Psychology Press, 2001.
[9] Darbandi H B, Ito M R, Little J. Clustered Signatures for Modeling and Recognizing 3D Rigid Objects[C]. Processings of the World Academy of Science, Engineering And Technology,2008,27-35.
[10] Fisher. Dictionary of computer vision and image processing[M]: John Wiley&Sons,Ltd, 2005.
[11] Arman F, Aggarwal J K. Model-based object recognition in dense-range images—a review[J]. ACM Comput Surv. 1993, 25(1):5-43.
[12] Salvi J, Matabosch C, Fofi D,et al. A review of recent range image registration methods with accuracy evaluation[J]. Image and Vision Computing. 2007, 25(5):578-596.
[13] Chua C S, Jarvis R. Point Signatures: A New Representation for 3D Object Recognition[J]. International Journal of Computer Vision. 1997, 25(1):63-85.
[14] Johnson A E, Sing B K. Registration and integration of textured 3-D data[C]. Processings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling,1997,234-241.
[15] Feldmar J, Ayache N. Rigid, affine and locally affine registration of free-form surfaces[R]: INRIA. 1994.
[16] Luciano S, Olga B, Kim B. Robust Range Image Registration Using Genetic Algorithms[M].Danvers: World Scientific Publishing Co. Pte. Ltd., 2005.
[17] Besl P J, McKay H D. A method for registration of 3-D shapes[J]. Transactions on Pattern Analysis and Machine Intelligence. 1992, 14(2):239-256.
[18]李世飞,王平,沈振康.迭代最近邻点算法研究进展[J].信号处理. 2009, 25(10):1582-1588.
[19] Levoy M. The digital Michelangelo project[C]. Processings of the Second International Conference on 3-D Digital Imaging and Modeling,1999,2-11.
[20] Masuda T, Sakaue K, Yokoya N. Registration and integration of multiple range images for 3-D model construction[C]. Processings of the 13th International Conference on Pattern Recognition,1996,879-883.
[21] Boissonnat. Geometric Structures for Three-Dimensional Shape Representation[J]. ACM Transactions on Graphics. 1984, 3(4):266-286.
[22] Chu-Song C, Yi-Ping H, Ja-Ling W. Model-based object recognition using range images by combining morphological feature extraction and geometric hashing[C]. Processings of the 13th International Conference on Pattern Recognition,1996,565-569.
[23] Edelsbrunner H, Mucke E P. Three-Dimensional Alpha Shapes[C]. Processings of,1992,75-82.
[24] Bajaj, Brenardini, Xu. Automatic reconstruction of surfaces and scalar fields from 3D scans[C]. Processings of the 22nd annual conference on Computer graphics and interactive techniques,1995,109-118.
[25]谢凯,汤晓安,郝建新,et al.一种基于多幅深度图像的混合建模方法[J].小型微型计算机系统. 2003, 24(1):94-96.
[26] Greg T, Marc L. Zippered Polygon Meshes from Range Images[C]. Processings of the 21st Annual Conference on Computer Graphics and Interactive Techniques,1994,311-318.
[27]张宗华,彭翔,胡小唐.深度图像合成的主次缝合线方法[J].工程图学学报. 2001, 22(2):102-109.
[28] Jain A K, Dorai C. 3D object recognition: Representation and matching[J]. Statistics and Computing. 2000, 10(2):167-182.
[29] Lee Y-L, Park R-H. A surface-based approach to 3-D object recognition using a mean field annealing neural network[J]. Pattern Recognition. 2002, 35(2):299-316.
[30]方昭江,丁明跃.基于模型的自由形态物体匹配方法研究[J].红外与激光工程. 1999, 28(3):5-8.
[31] Suk M, Bhandarkar S. Three dimensianal object recognition from range images[M].New York: Spring-Verlag, 1992.
[32]李庆,周曼丽.三维物体识别研究进展[J].中国图象图形学报:A辑. 2000, 5(12):985-993.
[33] Chen H, Bhanu B. 3D free-form object recognition in range images using local surface patches[J]. Pattern Recognition Letters. 2007, 28(10):1252-1262.
[34] Schütz C. Geometric point matching of free-form 3D objects[D].Neuchatel, Switzerland: University of Neuchatel, 1998.
[35] Campbell R J, Flynn P J. A Survey Of Free-Form Object representation and Recognition Techniques[J]. Computer Vision and Image Understanding. 2001, 81(2):166-210.
[36] Besl P J. The free-form surface matching problem[C],1990,25–71.
[37] Stein F, Medioni G. Structural Indexing: Efficient 3-D Object Recognition[J]. IEEE Trans Pattern Anal Mach Intell. 1992, 14(2):125-145.
[38] Dorai C, Jain A K. COSMOS--A representation scheme for 3D free-form objects[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 1997, 19(10):1115-1130.
[39] Zhang D, Hebert M. Harmonic maps and their applications in surface matching[C]. Processings of the IEEE Computer Society Conference on. Computer Vision and Pattern Recognition,1999,524-530.
[40] Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2002, 24(24):509–522.
[41] Frome A, Huber D, Kolluri R,et al. Recognizing Objects in Range Data Using Regional Point Descriptors[C]. Processings of the Eighth European Conference on Computer Vision,2004,224-237.
[42] Chin R T, Dyer C R. Model-based recognition in robot vision[J]. ACM Comput Surv. 1986, 18(1):67-108.
[43] Mahmoudi S, Daoudi M. 3D models retrieval by using characteristic views[C]. Processings of the 16th International Conference on Pattern Recognition,2002,457-460.
[44] Hui C, Bir B. 3D free-form object recognition in range images using local surface patches[C]. Processings of the 17th International Conference on Pattern Recognition,2004,136- 139
[45]何文峰.大型场景三维重建中的深度图像配准[D].北京:北京大学, 2004.
[46] Takeguchi T, Kaneko S. Using Depth Aspect Images for Robust and Efficient Search of Multiple Objects in Optomechatronic Sensing[J]. IEEE Transactions on Industrial Electronics. 2005, 52(4):1041- 1049.
[47] Cantzler H. An overview of range images[Z]. http://homepages.inf.ed.ac.uk/ rbf/CVonline/LOCAL_COPIES/CANTZLER2/range.html, 2008.
[48] Bosche F, Haas C T. Investigation of Data Formats for the Integration of 3D Sensed and 3D CAD data for Improved Equipment Operation Safety[C]. Processings of the 1st International Construction Specialty Conference,2006,1-9.
[49] Lu T. Triangular mesh generation for surfaces of 3D objects[D].Hawaii: University of Hawaii, 2000.
[50]周颖.深度图像的获取及其处理[D].陕西西安:西安电子科技大学, 2008.
[51]蔺宏伟.离散几何信息处理——从点到面[D].浙江杭州:浙江大学, 2003.
[52]章大勇,吴文启,吴美平,et al.基于三维Hough变换的机载激光雷达平面地标提取[J].国防科技大学学报. 2010, 32(2):130-134.
[53]龚俊斌.激光成像雷达图像融合匹配系统的设计与实现[D]:华中科技大学,模式识别与智能系统, 2005.
[54]蒋颖.深度图像配准方法的研究与实现[D].北京:北京航空航天大学, 2007.
[55] Shilane P, Min P, Kazhdan M. The Princeton Shape Benchmark[C]. Processings of the Shape Modeling International,2004.
[56]贾云得.机器视觉[M].北京:科学出版社, 2000.
[57] Ball M. Terrestrial 3D Laser Scanner Capture Reality[Z]. www.geoworld.com, 2004.
[58] Suk-Ho L, Jin Keun S. Noise removal with Gauss curvature-driven diffusion[J]. Image Processing, IEEE Transactions on. 2005, 14(7):904-909.
[59]方惠兰,王国瑾, Ping X,et al.三角网格曲面上离散曲率估算方法的比较与分析[J].计算机辅助设计与图形学学报. 2005, 17(11):2500-2507.
[60] Lipschutz M M. Differential Geometry[M].New York: McGraw-Hill, 1969.
[61]孟道骥,梁科.微分几何[M].北京:科学出版社, 1999.
[62]吴剑煌,刘伟军,王天然,et al.点采样曲面曲率估计[J].仪器仪表学报. 2006, (12).
[63] Rugis J, Klette R. A Scale Invariant Surface Curvature Estimator[J]. Advances in Image and Video Technology. 2006:138-147.
[64] Magid E, Soldea O, Rivlin E. A comparison of Gaussian and mean curvature estimation methods on triangular meshes of range image data[J]. Computer Vision and Image Understanding. 2007, 107(3):139-159.
[65]张涛,平西建,柳葆芳,et al.一种深度图像中的表面曲率估计算法[J].数据采集与处理. 2001, 16(01):47-51.
[66] El-Fallah A I, Ford G E. Mean curvature evolution and surface area scaling in image filtering[J]. Image Processing, IEEE Transactions on. 1997, 6(5):750-753.
[67]王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京:科学出版社, 2008.
[68] Flynn P J, Jain A K. On Reliable Curvature Estimation[C]. Processings of the Internaltional Conference on Computer Vision and Pattern Recogintion,1989,110-116.
[69] Krsek P, Lukacs G, Martin R R. Algorithms for computing curvatures from range data[C]. The Mathematics of Surfaces VIII, Information Geometers,1999,1-16.
[70]邹宁.深度图像分析方法研究[D]:华中理工大学,通信与信息系统, 2000.
[71]刘恩国.基于深度图象的三维视觉关键问题的研究[D]:上海交通大学, N1 - 2009-05-27 12:29:00, 1999.
[72] Sapiro G. Geometric Partial differential Equations and Image Analysis[M].Cambridge: Cambridge University Press, 2001.
[73]李松涛.深度图像处理方法的研究[D].北京:清华大学, 1999.
[74]于寅.高等工程数学(第三版)[M].武汉:华中科技大学出版社, 2001.
[75]李松涛,张长水,荣钢,et al.一种基于最小二乘估计的深度图像曲面拟合方法[J].自动化学报. 2002, 28(02):310-313.
[76] Chen H. Human ear recognition in three dimensions[D]: University of California, Riverside., M1 - Ph.D., 2006.
[77] Gautschi W. Orthogonal polynomials: computation and approximation[M]: Oxford University Press, 2004.
[78]施法中.计算机辅助几何设计于非均匀有理B样条[M].北京:北京航空航天大学出版社, 1994.
[79]王秀丽,宁正元.基于高斯曲率的曲面光顺方法研究[J].计算机工程. 2006, 32(16):207-210.
[80]李涛. Matlab工具箱应用指南:应用数学篇[M].北京:电子工业出版社, 2000.
[81] Lancaster P, Salkauskas K. Surfaces generated by moving least squares methods[J]. Mathematics of Computation. 1981, 37(155):141-158.
[82] Belytschko T, Lu Y Y, Gu L. Element-free galerkin methods[J]. International Journal for Numerical Methods in Engineering. 1994, 37:229~256.
[83]李世飞,王平,沈振康.利用移动最小二乘法进行深度图像曲面拟合[J].吉林大学学报(工学版). 2010, 40(1):229-233.
[84] Liu G R, Gu Y T. An Introduction to Meshfree Methods and Their Programming[M]: Springer, 2005.
[85]左传伟,聂玉峰,赵美玲.移动最小二乘法中影响半径的选取[J].工程数学学报. 2005, 22(5):833-838.
[86]陈美娟,程玉民.改进的移动最小二乘法[J].力学季刊. 2003, (02).
[87]张雄,刘岩.无网格法[M].北京:清华大学出版社/Springer, 2004.
[88]朱浩,方宗德,杨宏斌.基于NURBS曲面拟合的图像边缘检测方法[J].洛阳工学院学报. 2001, 22(1).
[89] Marr D. Vision[M].San Francisco: Freeman, 1982.
[90] Ko K H. Algorithms for Three-Dimensional Free-Form Object Matching[D].Boston: Massachusetts Institute of Technology, 2003.
[91] Ko K H, Maekawa T, Patrikalakis N M. An algorithm for optimal free-form object matching[J]. Computer-Aided Design. 2003, 35(10):913-923.
[92] Mokhtarian F, Khalili N, Yuen P. Multi-scale free-form 3D object recognition using 3D models[J]. Image and Vision Computing. 2001, (19):271-281.
[93]胡薇.基于子空间的3D目标识别和姿态估计方法[J].红外与激光工程. 2004, 33(6).
[94] Dinh H Q, Kropac S. Multi-Resolution Spin-Images[C]. Processings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006,863- 870.
[95]周明全,樊亚春,耿国华.一种基于空间对称的三维模型形状描述方法[J].电子学报. 2010, 38(4):853-858.
[96] Salgian A S. Using Multiple Patches for 3D Object Recognition[J]. 2007.
[97] Johnson A E. Spin-Images: A Representation for 3-D Surface Matching[D].Pittsburgh: Carnegie Mellon University, 1997.
[98]王子璇.利用角度签名进行3维表面配准[J].中国图象图形学报. 2008, 13(08):1538-1543.
[99] Lowe D G. Object recognition from local scale-invariant features[C]. Processings of the The Proceedings of the Seventh IEEE International Conference on Computer Vision,1999,1150-1157.
[100] Abdel-Hakim A E, Farag A A. CSIFT: A SIFT Descriptor with Color Invariant Characteristics[C]. Processings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006,1978-1983.
[101] Ke Y, Sukthankar R. PCA-SIFT: A More Distinctive Representation for Local Image Descriptors[C]. Processings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2004,506-513.
[102] Mikolajczyk K. Detection of local features invariant to affine transformations[D].France,Grenoble Institute National Polytechnique de Grenoble, 2002.
[103]陈涛.图像仿射不变特性研究[D]:湖南长沙:国防科技大学, 2006.
[104] Laxmikanthamma.统计与真理——怎样运用偶然性[M].北京:科学出版社, 2005.
[105] Hetzel G, Leibe B, Levi P,et al. 3D object recognition from range images using local feature histograms[C]. Processings of the Computer Vision and Pattern Recognition,2001,394-399.
[106] Schenider P J, Eberly D H. Geometric Tools for Computer Graphics[M]: Elsevier, 2004.
[107] Koenderink J J, Doorn A V. Surface shape and curvature scales[J]. Image Vision Comput. 1992, 10(8):557–565.
[108] Cantzler H, Fisher R B. Comparison of HK and SC curvature description methods[C]. Processings of the Third International Conference on 3-D Digital Imaging and Modeling,2001,285-291.
[109] Iyer N, Jayanti S, Lou K,et al. Three-dimensional shape searching: state-of-the-art review and future trends[J]. Computer-Aided Design Geometric Modelingand Processing 2004. 2005, 37(5):509-530.
[110]孙即祥.数字图像处理[M].石家庄:河北教育出版社, 1992.
[111] Schiele B, Crowley J L. Recognition without Correspondence using Multidimensional Receptive Field Histograms[J]. International Journal of Computer Vision. 2000, 36(1):31-50.
[112] Basseville M. Information:entropies,divergences et moyennes[R]: IRISA. 1996.
[113] Press W H, Teukolsky S A, Vettering W T. Numerical Recipes in C[M]: Cambridge University Press, 1992.
[114] Swain M J, Ballard D H. Color indexing[J]. International Journal of Computer Vision. 1991, 7(1):11-32.
[115]周海芳.遥感图像并行处理算法的研究和应用[D], 2003.
[116] Johnson A E, Hebert M. Using spin images for efficient object recognition in cluttered 3D scenes[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 1999, 21(5):433-449.
[117] Assfalg J, Bertini M, Del B A,et al. Content-based retrieval of 3-D objects using Spin Image Signatures[J]. IEEETransactions on Multimedia. 2007, 9(3):589-599.
[118] Bock M E, Cortelazzo G M, Ferrari C,et al. Identifying similar surface patches on proteins using a spin-image surface representation[C]. Lecture Notes in Computer Science,2005,417-428.
[119] Darbandi H B, Ito M R, Little J. Content-based retrieval of 3-D objects using Spin Image Signatures[C]. Processings of the World Academy Of Science, Engineering And Technology,2008,27-35.
[120] Wang Y M, Pan G, Wu Z H,et al. Sphere-spin-image: A viewpoint-invariant surface representation for 3D face recognition[C]. Processings of the SPIE Volume 3037,2004,427-434.
[121]郭树华,胡平,李运兴.基于旋转图像和高度图像的曲面局部形状识别[J].中国机械工程. 2003, 14(16):1413-1417.
[122] Matzka S, Petillot Y R, Wallace A M. Determining Efficient Scan-Patterns for 3-D Object Recognition Using Spin Images[C]. Lecture Notes in Computer Science,2007,559-570.
[123] Besl P J, Jain R C. Invariant surface characteristics for 3D object recognition in range images[J]. Computer Vision, Graphics and Image Processing. 1986, 33(1):33-80.
[124] Forsyth D, Mundy J L, Zisserman A,et al. Invariant descriptors for 3D object recognition and pose[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1991, 13(10):971-991.
[125] Wood J. Invariant pattern recognition: A review[J]. Pattern Recognition. 1996, 29(1):1-17.
[126] Jinhui C, Ishii S. Invariant recognition and segmentation of 3D object using Liealgebra models Invariant recognition and segmentation of 3D object using Lie algebra models[C]. Processings of,1999,550-554 vol.551.
[127] Manay S, Hong B-W, Yezzi A J,et al. Integral Invariant Signatures[C]. Processings of the Eighth European Conference on Computer Vision,2004,87-99.
[128] Rothganger F, Lazebnik S, Schmid C,et al. 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints[J]. International Journal of Computer Vision. 2006, 66(3):231-259.
[129] Chen C-C. Improved moment invariants for shape discrimination[J]. Pattern Recognition. 1993, 26(5):683-686.
[130] Mercimek M, Gulez K. 3D Real Object Recognition on the Basis of Moment Invariants and Neural Networks[C]. Processings of the The 19th International Symposium on Computer and Information Sciences,2004,410-419.
[131] Chen J-L, Stockman G C. 3D Free-Form Object Recognition Using Indexing by Contour Features[J]. Computer Vision and Image Understanding. 1998, 71(3):334-355.
[132] Johnson A E, Hebert M. Surface matching for object recognition in complex three-dimensional scenes[J]. Image and Vision Computing. 1998, 16(9-10):635-651.
[133] Tsallis C. Possible generalization of Boltzmann-gibbs statistics[J]. Journal of Statistics Physics. 1988, 52(1-2):479-487.
[134] Anonymous. Konstanz 3D Model Repository[Z]. http://www.inf.uni-konstanz. de/, 2009.
[135] Stamos I, Allen P K. 3-D Model Construction Using Range and Image Data[C]. Processings of the IEEE Conference on Computer Vision and Pattern 2000,1531-1538.