规则物体影像特征提取及匹配研究
|
摘要
摄影测量的主要目标之一是从非接触式影像中获取精确可靠的量测信息,计算机视觉其研究的主要目标是使计算机系统具有类似于人类的视觉能力,从而获取三维场景的几何信息。无论是在摄影测量领域,还是在计算机视觉领域,特征提取及匹配都有广泛地应用。特征提取及匹配是三维重建、运动跟踪、序列影像分析、信息融合、模式识别等研究课题的必要环节,对特征提取及匹配进行研究具有重要的现实意义。
随着工业制造技术的不断提高和加工工艺的不断改进,在大批量工业生产中,用人工视觉检查产品质量效率低且精度不高,用计算机视觉技术可大大提高生产效率和自动化程度,而摄影测量中丰富的平差理论有助于获取极高的精度。近年来,高分辨率、高信噪比的数字成像CCD器件迅速发展,计算机图象处理和模式识别技术的快速进步,使得摄影测量计算机视觉技术成为目前具有广泛前景的一种精密测量技术。
本论文针对工业生产中的精密测量要求,结合工业规则物体中拥有的丰富线特征信息,采用摄影测量中严密的数据处理理论及计算机视觉前沿理论和技术,重点研究了点、线特征提取及匹配问题。提出了直线元离散化获取点特征的方法及线特征的高精度提取新算法;改进了相关系数影像匹配(加权相关系数);将计算机视觉中的核线约束引入到最小二乘影像匹配中,并给出了一种遮挡直线匹配的新方法。通过实验验证了特征提取及匹配的有效性,得到了较好的结果。
The dominant purpose of photogrammety is to use CCD images to obtain the accurate and reliable measurements while computer vision is to make computer have visible ability which resembles that of human's eyes and to regain the geometries of three-dimensional space.Feature extracting and matching,which is an essential component of such research as three-dimensional reconstruction, motion tracking, image sequence analysis, information fusion, pattern recognition, are widely used in both computer vision and photogrammetry. There exits important practical significance in such studying.
As the improving of industrial manufacturing technology and processing technic,we usually get a poor efficiency and short precision by human check in large quantities production although the production efficiency and automation can be greatly enhanced by computer vision and a high accuracy by the extensive adjustment theory. It makes a great progress in CCD devices with a high resolution and high signal to noise ratio and in image processing and pattern recognition, which enables photogrammetry-comuter vision to be a wide application way for technology of precise measurements.
In order to accommodate the demands of industrial precision measurement, This paper which combines with a wealth of line features in organized objects and adopts rigorous data processing theory of photogrammetry espically the advanced technology in computer vision,focuses on the feature extraction and matching. We mainly undertook the following findings that demonstrated by our experiments with a good results: proposing a new method for points extraction by line discretization and a high precision line extraction algorithm; improving the image matching based on correlation coefficient called weighted correlation coefficient; bringing epipolar constraint into the least squares matching and creating a new way for line matching especially blocked.
随着工业制造技术的不断提高和加工工艺的不断改进,在大批量工业生产中,用人工视觉检查产品质量效率低且精度不高,用计算机视觉技术可大大提高生产效率和自动化程度,而摄影测量中丰富的平差理论有助于获取极高的精度。近年来,高分辨率、高信噪比的数字成像CCD器件迅速发展,计算机图象处理和模式识别技术的快速进步,使得摄影测量计算机视觉技术成为目前具有广泛前景的一种精密测量技术。
本论文针对工业生产中的精密测量要求,结合工业规则物体中拥有的丰富线特征信息,采用摄影测量中严密的数据处理理论及计算机视觉前沿理论和技术,重点研究了点、线特征提取及匹配问题。提出了直线元离散化获取点特征的方法及线特征的高精度提取新算法;改进了相关系数影像匹配(加权相关系数);将计算机视觉中的核线约束引入到最小二乘影像匹配中,并给出了一种遮挡直线匹配的新方法。通过实验验证了特征提取及匹配的有效性,得到了较好的结果。
The dominant purpose of photogrammety is to use CCD images to obtain the accurate and reliable measurements while computer vision is to make computer have visible ability which resembles that of human's eyes and to regain the geometries of three-dimensional space.Feature extracting and matching,which is an essential component of such research as three-dimensional reconstruction, motion tracking, image sequence analysis, information fusion, pattern recognition, are widely used in both computer vision and photogrammetry. There exits important practical significance in such studying.
As the improving of industrial manufacturing technology and processing technic,we usually get a poor efficiency and short precision by human check in large quantities production although the production efficiency and automation can be greatly enhanced by computer vision and a high accuracy by the extensive adjustment theory. It makes a great progress in CCD devices with a high resolution and high signal to noise ratio and in image processing and pattern recognition, which enables photogrammetry-comuter vision to be a wide application way for technology of precise measurements.
In order to accommodate the demands of industrial precision measurement, This paper which combines with a wealth of line features in organized objects and adopts rigorous data processing theory of photogrammetry espically the advanced technology in computer vision,focuses on the feature extraction and matching. We mainly undertook the following findings that demonstrated by our experiments with a good results: proposing a new method for points extraction by line discretization and a high precision line extraction algorithm; improving the image matching based on correlation coefficient called weighted correlation coefficient; bringing epipolar constraint into the least squares matching and creating a new way for line matching especially blocked.
引文
[1]章毓晋.影像理解与计算机视觉[M].北京:清华大学出版,2000.
[2]郑南宁.计算机视觉与模式识别[M].北京:国防工业出版社,1998.
[3]张祖勋.摄影测量与计算机视觉[J].武汉大学学报·信息科学版,2004.
[4]张永军.基于序列图像的工业钣金件三维重建与视觉检测[M].武汉:武汉大学出版社,2008.
[5]胡棋.标准工业饭金件三维立体量测[学位论文].武汉:武汉大学,2004.
[6]程蓉,刘建.三坐标测量机在模具加工中的应用[J].电加工与模具,2002.6.
[7]刘常杰,郝继贵,叶声华.汽车白车身机器视觉检测系统[J].汽车工程,2000. 6.
[8]李成贵,李行善,强锡富.三维表面微观形貌的测量方法[J].宇航计测技术,2000.8.
[9]沈艳杰,龚文琪,雷绍民.电子显微技术在矿物材料研究中的应用[J].中国非金属矿工业导刊,2004.3
[10]王玉富,王开颜.动态莫尔条纹在转镜式激光照排机中的应用[J].传感器技术,2002.9.
[11]王成武,晓东,韩昌元.投影型莫尔条纹中的相移技术[J].中国激光,1996. 3.
[12]刘海增,靳晋中.牛顿环现象及其应用[J].郑州轻工业学院学报·自然科学版,2003.9.
[13]郑莉.基于结构光的不规则工业饭金件三维曲面重建[学位论文].武汉:武汉大学,2004.
[14]郑德香,张岩,沈京玲,张存林,数字全息技术的原理和应用[J].物理学和高新技术,2004.11.
[15]李奇,冯华君等.计算机立体视觉技术综述[J].光学技术,1999.5.
[16]李建松,冯文灏,李欣等.大型钢结构工业部件的高精度检测与放样系统[J],钢结,2001.5.
[17]张永军.基于序列图像的工业饭金件的三维重建与视觉检测[学位论文].武汉:武汉大学,2003.
[18]冯文灏.工业测量方法及其选用的基本原则[J].武汉大学学报·信息科学版,2001.4.
[19]文贡坚,王润生.一种稳健的直线提取算法[J].软件学报,2001,12(11):1660-1665
[20]高成.Matlab图像处理与应用[M].北京:国防工业出版社,2007.
[21] Nevada R,Babu.K. Linear Feature Extraction and Description[J].Graphics and Image Processing,1980,13 (3).
[22] Zhou,Y, Venkateswar,V. Chellappa,R. Edge detection and linear feature extraction using a 2-D random field model[J].IEEE Trans PAMI,1989,11(1).
[23] Venkateswar,V,Chellappa,R.Texas Instrnments,etc. Extracting of straight lines in aerialimages[J].IEEE Trans PAMI,1999, 14(11).
[24] Burns J B,Hanson A R.Extracting straight lines[J]. IEEE Trans. Pattern Analysis and Machine Intelligence.1986,8(4).
[25] Boldt M, Weiss. R, Riseman. E., Token-Based extraction of straight lines[J]. IEEE Trans. Man Cybernetics, 1989, 19(7).
[26] Hough P.V.C. Methods and Means for Recognizing Complex Patterns[P]. U.S. Patent, 3069654, Dec. 1962.
[27]孙丰荣,刘积仁.快速霍夫变换算法[J].计算机学报,2001,24(10).
[28]杨顺辽.基于Hough变换提取直线的改进方法研究[J].电脑与信息技术,2006,14(5)
[29]门敬文,屈小波.超小波分析及应用[M].北京:国防工业出版社,2008.
[30]侯彪,刘芳,焦李成.基于脊波变换的直线特征检测[J].中国科学,2003,33(1).
[31] D. L. Donoho, Xiaoming Huo. Beamlets and Multiscale image analysis[R]. Springer Lecture Notes in Computer Science and Enginering: Multiresolution Methods, 2000.
[32] D. L. Donoho, Xiaoming Huo. Beamlet Pyramids: A New Form of Multiresolution Analysis.suited for Extracting Lines, Curves, and Objects from Very Noisy Image Data[J].SPIE, 2000.
[33]史勤峰.Beamlet及其在SAR图像边缘检测中的应用[学位论文].西安:西北工业大学,2006.
[34]杨明,尹勇,彭玉华等.Beamlet变换与多尺度线特征提取[J].电子学报.2007,35(1).
[35] S. Berlemont, A. Bensimon, J.-C. Olivo-Marin. Detection of Curvilinear Objects in Noisy Image using Feature-Adapted Beamlet Transform[C], Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on,2007(1):I1225-I1228.
[36] Deng Shuangcheng,Jiang Lipei,Xue Long,etc.Detecting linear features in weld seam images based on Beamlet transform [C], Signal Processing, 2008. ICSP 9th International Conference on, 2008: 1145-1148.
[37] S. Berlemont, A. Bensimon, Jean-Christophe Olivo-Marin.Detection of DNA Filaments in Fluorescent Microscopy Using Feature-adapted Beamlet Transforms. Proceedings of 2nd
[40] Xiangyun Hu,Zuxun Zhang,Jonathan Li. Linear feature extraction using adaptive Workshop on Microsopic Image Analysis with Applications in Biology, Piscataway, NJ, USA,2007.
[38] Ackemann F. High Precision Digital Image Correlation[M]. University of Stuttgart, 1983.
[39] Gruen A.Adaptive least square corrlation:a powerful image matching techinque[J]. South African Journal of Photogrammetry and Remote Sensing.1985(14)3:175-187least-squares template matching and a scalable slope edge mode[J]. International Journal of Remote Sensing. 2009.30(13), 3393–3407.
[41] Zhang Zuxun, Zhang Jianqing.Generalized Point Photogrammetry and Its Application [C].The 20th ISPRS Congress.Istanbul. Turkey. 2004.
[42]唐敏,张祖勋,张剑清.基于广义点理论的多基线影像饭金件3D重建与尺寸检测[J].武汉大学学报·信息科学版,2007,12.
[43] Cordelia Schmid,Andrew Zisserman. Automatic Line Matching across views[J]. IEEE Computer Vision and Pattern Recognition, 1997, 17(19).
[44] Medioni G, Nevada R. Matching images using straight lines [J].IEEE Trans PAMI, 1984, 6(6).
[45] Liu Yuncai, Huang T S.Determining straight line corresponedce from intensity images[J]. Pattern Recognition,1991,6(24).
[46] Sang Ho Park,Kyong Mu Lee,Sang Uk Lee.A Line feature matching technique based on an eigenvector approach[J].Computer Vision and ImageUnderstanding, 2000, 3(77).
[47] WK Gu,JY Yang,TS Huang.Matching perspective views of a polyhedron using circuits[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1987,9(3).
[48] Mcintosh J H,Mutch K M.Matching straight lines[J].CVGIP,1998,43.
[49] J.Brian Burns,Allen R.Hanson,Edward M. Riseman.Extracting straight lines[J].IEEE Transcations on PAMI, 1986, 8(4).
[50]陈宁江,李介谷.基于支持区域的直线段匹配[J].红外与激光,2000, 29(5).
[51] Li Z N.Stereo correspondence based on line matching in hough space using dynamic programming[J].IEEE Transactions on SMC,1994,24(1).
[52]曾接贤,张桂梅,储珺.基于直线的线流场计算技术[J].中国图象图形学报,2003,8(A).
[53]冈萨雷斯(Gonzalez,R.C.)等著,阮秋琦等译.数字图像处理[M](第二版).北京:电子工业出版社,2003.3.
[54]章毓晋.图像工程(上册)—图像处理和分析[M].北京:清华大学出版社,2000.10.
[55]贾永红.数字图像处理[M].武汉:武汉大学出版社,2003.
[56] Linda, George C.S著,赵清杰等译.计算机视觉[M].北京:机械工业出版社,2005.3.
[57]贾云得.机器视觉[M].北京:科学出版社,2000.4.
[58]张春森.基于Hough变换的空间点位自动检测[J].计算机工程,2006,Vol32(13).
[59]陈胜勇等.基于OpenCV的计算机视觉技术实现[M].北京:科学出版社,2008.
[60]于起峰等.基于影像的精密测量与运动测量[M].北京:科学出版社,2002.
[61]翟国栋等.从AutoCAD中提取实体数据的研究[J].河北煤炭,2000(4).
[62]吴敬文等.基于DXF的数字地图投影与坐标系转换方法研究[J].海洋测绘,2009,Vol29(1).
[63]史玉红等.浅谈AutoCAD的接口—DXF文件[J].山东煤炭科技,2002(1).
[64] Harris.C, Stephens.M. A combined corner and edge detector[J].Proceedings Alvey Conference, 1988.92.
[65]张祖勋,张剑清.数字摄影测量学[M].武汉:武汉大学出版社,1997.
[66] Gruen A. Adaptive least square correlation: a powerful image matching technique[J].South African Journal of Photogrammetry and Remote Sensing.1985(14)3.
[67]胡翔云.航空遥感影像线状地物与房屋的自动提取[学位论文].武汉大学,2001
[68]武汉大学测绘学院测量平差学科组.误差理论与测量平差基础[M].武汉:武汉大学出版社,2003.
[69]周骥,石教英,赵友兵.图像特征点匹配的强壮算法[J].计算机辅助设计与图形学学报,2002,14(8).
[70] Zhang Z,Deriche R,Faugeras 0. A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry[J]. Artificial Intelligence, 1995.
[71]王之卓.摄影测量原理.北京:测绘出版社,2009.
[72]游素亚,徐光佑.立体视觉研究的现状与进展[J].中国图象图形学报,1997, 2(l).
[73]冯文撷.近景摄影测量[M].武汉:武汉大学出版社,2002.
[74] Richard Hartley,Andrew Zisserman. Multiple View Geometry in Computer Vision.合肥:安徽大学出版社,2001.
[75] Schmid C, Zisserman A. Automatic Line Matching Across Views [A]. In: Procceding of the Conference on Computer Vision and Pattern Recognition [C]. Puerlo Rico, UAS, 1997, 666671.
[76] Noronha S, Nevatia R. Detection and Modeling of Buildings from Multiple Aerial Imges[A]. In.IEEE International Conference on Computer Vision and Pattern Recognition[C]. San Juan,Puerto 1997. 588594.
[77]傅丹,王超,徐一丹,周剑,于起峰.一种直线段匹配的新方法[J].国防科技大学学报,2008,30(1): 115-119.
[78]席学强,王润生.基于直线特征的图像一模型匹配算法[J].国防科技大学学报,2000,22(6): 7074.
[79] Fischler.M.A, Bolles.R.C. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography[J]. Communications of the ACM, 1981,24(6): 381–395.
[2]郑南宁.计算机视觉与模式识别[M].北京:国防工业出版社,1998.
[3]张祖勋.摄影测量与计算机视觉[J].武汉大学学报·信息科学版,2004.
[4]张永军.基于序列图像的工业钣金件三维重建与视觉检测[M].武汉:武汉大学出版社,2008.
[5]胡棋.标准工业饭金件三维立体量测[学位论文].武汉:武汉大学,2004.
[6]程蓉,刘建.三坐标测量机在模具加工中的应用[J].电加工与模具,2002.6.
[7]刘常杰,郝继贵,叶声华.汽车白车身机器视觉检测系统[J].汽车工程,2000. 6.
[8]李成贵,李行善,强锡富.三维表面微观形貌的测量方法[J].宇航计测技术,2000.8.
[9]沈艳杰,龚文琪,雷绍民.电子显微技术在矿物材料研究中的应用[J].中国非金属矿工业导刊,2004.3
[10]王玉富,王开颜.动态莫尔条纹在转镜式激光照排机中的应用[J].传感器技术,2002.9.
[11]王成武,晓东,韩昌元.投影型莫尔条纹中的相移技术[J].中国激光,1996. 3.
[12]刘海增,靳晋中.牛顿环现象及其应用[J].郑州轻工业学院学报·自然科学版,2003.9.
[13]郑莉.基于结构光的不规则工业饭金件三维曲面重建[学位论文].武汉:武汉大学,2004.
[14]郑德香,张岩,沈京玲,张存林,数字全息技术的原理和应用[J].物理学和高新技术,2004.11.
[15]李奇,冯华君等.计算机立体视觉技术综述[J].光学技术,1999.5.
[16]李建松,冯文灏,李欣等.大型钢结构工业部件的高精度检测与放样系统[J],钢结,2001.5.
[17]张永军.基于序列图像的工业饭金件的三维重建与视觉检测[学位论文].武汉:武汉大学,2003.
[18]冯文灏.工业测量方法及其选用的基本原则[J].武汉大学学报·信息科学版,2001.4.
[19]文贡坚,王润生.一种稳健的直线提取算法[J].软件学报,2001,12(11):1660-1665
[20]高成.Matlab图像处理与应用[M].北京:国防工业出版社,2007.
[21] Nevada R,Babu.K. Linear Feature Extraction and Description[J].Graphics and Image Processing,1980,13 (3).
[22] Zhou,Y, Venkateswar,V. Chellappa,R. Edge detection and linear feature extraction using a 2-D random field model[J].IEEE Trans PAMI,1989,11(1).
[23] Venkateswar,V,Chellappa,R.Texas Instrnments,etc. Extracting of straight lines in aerialimages[J].IEEE Trans PAMI,1999, 14(11).
[24] Burns J B,Hanson A R.Extracting straight lines[J]. IEEE Trans. Pattern Analysis and Machine Intelligence.1986,8(4).
[25] Boldt M, Weiss. R, Riseman. E., Token-Based extraction of straight lines[J]. IEEE Trans. Man Cybernetics, 1989, 19(7).
[26] Hough P.V.C. Methods and Means for Recognizing Complex Patterns[P]. U.S. Patent, 3069654, Dec. 1962.
[27]孙丰荣,刘积仁.快速霍夫变换算法[J].计算机学报,2001,24(10).
[28]杨顺辽.基于Hough变换提取直线的改进方法研究[J].电脑与信息技术,2006,14(5)
[29]门敬文,屈小波.超小波分析及应用[M].北京:国防工业出版社,2008.
[30]侯彪,刘芳,焦李成.基于脊波变换的直线特征检测[J].中国科学,2003,33(1).
[31] D. L. Donoho, Xiaoming Huo. Beamlets and Multiscale image analysis[R]. Springer Lecture Notes in Computer Science and Enginering: Multiresolution Methods, 2000.
[32] D. L. Donoho, Xiaoming Huo. Beamlet Pyramids: A New Form of Multiresolution Analysis.suited for Extracting Lines, Curves, and Objects from Very Noisy Image Data[J].SPIE, 2000.
[33]史勤峰.Beamlet及其在SAR图像边缘检测中的应用[学位论文].西安:西北工业大学,2006.
[34]杨明,尹勇,彭玉华等.Beamlet变换与多尺度线特征提取[J].电子学报.2007,35(1).
[35] S. Berlemont, A. Bensimon, J.-C. Olivo-Marin. Detection of Curvilinear Objects in Noisy Image using Feature-Adapted Beamlet Transform[C], Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on,2007(1):I1225-I1228.
[36] Deng Shuangcheng,Jiang Lipei,Xue Long,etc.Detecting linear features in weld seam images based on Beamlet transform [C], Signal Processing, 2008. ICSP 9th International Conference on, 2008: 1145-1148.
[37] S. Berlemont, A. Bensimon, Jean-Christophe Olivo-Marin.Detection of DNA Filaments in Fluorescent Microscopy Using Feature-adapted Beamlet Transforms. Proceedings of 2nd
[40] Xiangyun Hu,Zuxun Zhang,Jonathan Li. Linear feature extraction using adaptive Workshop on Microsopic Image Analysis with Applications in Biology, Piscataway, NJ, USA,2007.
[38] Ackemann F. High Precision Digital Image Correlation[M]. University of Stuttgart, 1983.
[39] Gruen A.Adaptive least square corrlation:a powerful image matching techinque[J]. South African Journal of Photogrammetry and Remote Sensing.1985(14)3:175-187least-squares template matching and a scalable slope edge mode[J]. International Journal of Remote Sensing. 2009.30(13), 3393–3407.
[41] Zhang Zuxun, Zhang Jianqing.Generalized Point Photogrammetry and Its Application [C].The 20th ISPRS Congress.Istanbul. Turkey. 2004.
[42]唐敏,张祖勋,张剑清.基于广义点理论的多基线影像饭金件3D重建与尺寸检测[J].武汉大学学报·信息科学版,2007,12.
[43] Cordelia Schmid,Andrew Zisserman. Automatic Line Matching across views[J]. IEEE Computer Vision and Pattern Recognition, 1997, 17(19).
[44] Medioni G, Nevada R. Matching images using straight lines [J].IEEE Trans PAMI, 1984, 6(6).
[45] Liu Yuncai, Huang T S.Determining straight line corresponedce from intensity images[J]. Pattern Recognition,1991,6(24).
[46] Sang Ho Park,Kyong Mu Lee,Sang Uk Lee.A Line feature matching technique based on an eigenvector approach[J].Computer Vision and ImageUnderstanding, 2000, 3(77).
[47] WK Gu,JY Yang,TS Huang.Matching perspective views of a polyhedron using circuits[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1987,9(3).
[48] Mcintosh J H,Mutch K M.Matching straight lines[J].CVGIP,1998,43.
[49] J.Brian Burns,Allen R.Hanson,Edward M. Riseman.Extracting straight lines[J].IEEE Transcations on PAMI, 1986, 8(4).
[50]陈宁江,李介谷.基于支持区域的直线段匹配[J].红外与激光,2000, 29(5).
[51] Li Z N.Stereo correspondence based on line matching in hough space using dynamic programming[J].IEEE Transactions on SMC,1994,24(1).
[52]曾接贤,张桂梅,储珺.基于直线的线流场计算技术[J].中国图象图形学报,2003,8(A).
[53]冈萨雷斯(Gonzalez,R.C.)等著,阮秋琦等译.数字图像处理[M](第二版).北京:电子工业出版社,2003.3.
[54]章毓晋.图像工程(上册)—图像处理和分析[M].北京:清华大学出版社,2000.10.
[55]贾永红.数字图像处理[M].武汉:武汉大学出版社,2003.
[56] Linda, George C.S著,赵清杰等译.计算机视觉[M].北京:机械工业出版社,2005.3.
[57]贾云得.机器视觉[M].北京:科学出版社,2000.4.
[58]张春森.基于Hough变换的空间点位自动检测[J].计算机工程,2006,Vol32(13).
[59]陈胜勇等.基于OpenCV的计算机视觉技术实现[M].北京:科学出版社,2008.
[60]于起峰等.基于影像的精密测量与运动测量[M].北京:科学出版社,2002.
[61]翟国栋等.从AutoCAD中提取实体数据的研究[J].河北煤炭,2000(4).
[62]吴敬文等.基于DXF的数字地图投影与坐标系转换方法研究[J].海洋测绘,2009,Vol29(1).
[63]史玉红等.浅谈AutoCAD的接口—DXF文件[J].山东煤炭科技,2002(1).
[64] Harris.C, Stephens.M. A combined corner and edge detector[J].Proceedings Alvey Conference, 1988.92.
[65]张祖勋,张剑清.数字摄影测量学[M].武汉:武汉大学出版社,1997.
[66] Gruen A. Adaptive least square correlation: a powerful image matching technique[J].South African Journal of Photogrammetry and Remote Sensing.1985(14)3.
[67]胡翔云.航空遥感影像线状地物与房屋的自动提取[学位论文].武汉大学,2001
[68]武汉大学测绘学院测量平差学科组.误差理论与测量平差基础[M].武汉:武汉大学出版社,2003.
[69]周骥,石教英,赵友兵.图像特征点匹配的强壮算法[J].计算机辅助设计与图形学学报,2002,14(8).
[70] Zhang Z,Deriche R,Faugeras 0. A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry[J]. Artificial Intelligence, 1995.
[71]王之卓.摄影测量原理.北京:测绘出版社,2009.
[72]游素亚,徐光佑.立体视觉研究的现状与进展[J].中国图象图形学报,1997, 2(l).
[73]冯文撷.近景摄影测量[M].武汉:武汉大学出版社,2002.
[74] Richard Hartley,Andrew Zisserman. Multiple View Geometry in Computer Vision.合肥:安徽大学出版社,2001.
[75] Schmid C, Zisserman A. Automatic Line Matching Across Views [A]. In: Procceding of the Conference on Computer Vision and Pattern Recognition [C]. Puerlo Rico, UAS, 1997, 666671.
[76] Noronha S, Nevatia R. Detection and Modeling of Buildings from Multiple Aerial Imges[A]. In.IEEE International Conference on Computer Vision and Pattern Recognition[C]. San Juan,Puerto 1997. 588594.
[77]傅丹,王超,徐一丹,周剑,于起峰.一种直线段匹配的新方法[J].国防科技大学学报,2008,30(1): 115-119.
[78]席学强,王润生.基于直线特征的图像一模型匹配算法[J].国防科技大学学报,2000,22(6): 7074.
[79] Fischler.M.A, Bolles.R.C. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography[J]. Communications of the ACM, 1981,24(6): 381–395.