宽基线立体影像点、线特征提取与匹配方法研究
|
摘要
随着高分辨率CCD技术及计算机技术的快速发展,基于非量测数码相机的数字近景摄影测量技术已成为崭新的发展领域,成为非接触、灵活、快捷的三维空间信息获取主要方式之一。这也使得该领域成为近年来的研究热点。其中,相机标定、特征提取与匹配(尤其是宽基线摄影条件下的特征提取与匹配)是应用该技术时的关键问题,是后续影像定向和三维重建、数据分析的基础。本文对上述内容进行了研究。论文研究涉及数字图像处理、影像匹配、模式识别等多学科的理论与方法。主要包括:
1.研究了基于平面格网的标志点识别与匹配方法及其相机标定应用。提出了一种基于物方几何约束的圆形标志点快速识别与匹配方法;结合平面场景的共线方程,论证和推导了分别基于灭点理论及二维直接线性变换的平面场景中相机外方位元素初值的计算方法;引入了一种基于逐次计算可靠性矩阵QVVP的自检校光束法平差中各类观测值权值的确定方法,提高计算的速度和稳健性。
2.提出了基于SIFT特征的宽基线立体影像最小二乘匹配方法。算法首先基于特征点的空间分布和信息熵选取一定数量的最优SIFT特征点集,并采用基于奇异值分解的SIFT特征匹配、基于SIFT特征尺度和方位信息的自适应归一化互相关(NCC)匹配获得精度较高的初始匹配点对用于立体像对的基本矩阵和单应矩阵估计;然后在对极几何和单应映射的双重约束下,采用基于自适应NCC及距离加权的多尺度最小二乘匹配算法进行扩展匹配并同时保留匹配定位精度较高的原始SIFT同名特征点对;此外,算法还综合应用了基于积分影像的NCC快速计算、金字塔影像匹配等方法和策略,以提高匹配的速度和可靠性。
3.提出了基于核线几何约束的尺度和旋转不变线特征描述符的提取与匹配方法。算法首先基于核线几何约束定义直线对的重叠距离、方位及线支持区,并据此构造了一种基于像素灰度及梯度分布统计信息的尺度和旋转不变线特征描述符;充分考虑了遮挡及视差断裂等因素的影响,采用双向多层次加权匹配策略完成直线段的匹配;采用核主成分分析对特征描述符进行降维处理,提高特征匹配的速度。
4.在Windows平台上基于Visual C++6.0高级编程语言及OpenCV开放计算机视觉库编制了上述算法的相关应用程序;试验验证了上述理论和方法的正确性和有效性。
论文的研究工作,丰富了数字近景摄影测量特征提取与匹配的相关理论和方法,并为后续的宽基线摄影测量三维重建打下了良好的基础。
该论文有图71幅,表9个,参考文献108篇。
With the fast development of high resolution Charged Coupled Device(CCD) and compute technology, digital close-range photogrammetry based on non-metric digital camera has become a very new research field, and at the same time, digital close-range photogrammetry has also become one of an important way to obtain the 3D spatial information with untouched, flexible and quick style . So, some problems related to this field have become hot topics around home and abroad recently. Among these, camera calibration, feature extraction and matching (especially feature extraction and matching for wide baseline stereo pairs) are the key problems when using this technology, because these problems are the basis for following photogrammetric processes, such as orientating the images, 3D reconstruction and data analysis, etc. The research work of this dissertation focus on previous problems and involved in multiple disciplinary theories and method, such as digital image process, image matching, and pattern recognition, etc, mainly include:
1. Recognizing and matching methods of circular signalized points and its application of digital camera calibration were studied. The method of recognizing and matching the circular signalized points based on object geometric constraints was proposed; Two practical algorithms to obtain the initial values of the exterior orientation elements based on the vanishing points theory and the two dimensional direct linear transformation were demonstrated and deduced by combining the collinearity equations in planar scenes; Mathematical model of the bundle block adjustment with self calibration was given and the method of determining the weight of every class of observations based on repeat calculating the QVVP was introduced to improve the calculating speed and the stability.
2. Least squares matching methods for wide base-line stereo images based on SIFT features were proposed. In this algorithm, the optimal SIFT features with good spatial distribution and large information content were first selected, then these SIFT features were matched by using the maching method based on singular value decompositon algorithm, adaptive NCC(Normalized Cross Correlation) matching method based on scale and orientation information of SIFT features, then the fundamental and homography matrix can be estimated by using these initial correspondences; Under the dual geometric constraints by using the fundamental and homography matrix, extended matching methods by using weighted least squares matching and multiple scale template windows were developed, further, by compared to the location error of the original correspondences of SIFT feature points, the least squares matching results were determined to adopted or not; In addition, some novel strategies such as NCC computing with high speed based on integral image, multi-level pyrmid image matching, etc, were adopted to improve the matching speed and reliability.
3. Line feature description with scale and rotation invariant and matching methods based on epipolar geometry constraint were proposed. In this algorithm, the overlap distances, orientations and line support regions of line segments pair were defined based epiploar geometry constraint, and then a line descriptor with scale and rotation invariant based on the mean and standard deviation of the gray values and gradient vectors was constructed; By fully considering the occlude and disparity discontinuity of the line segment pair, the weighted similarity measure for line segment matching based on the two side line support regions were adopted; Dimensionality reduction method based on kernel principal component analysis was introduced to improve the matching speed.
4. Application programms of the previous theories and methods were realized and established base on Windows platform with Visual C++6.0 high level programming languages and OpenCV(Open Compute Vision library), and relative experimental results indicate that the methods proposed in the dissertation is true and effective.
Reseach work in this paper can enrich the relative theories and methods concerned on digital close-range photogrammetry, and good basis are provided for 3D reconstruction of wide baseline photogrammetry.
1.研究了基于平面格网的标志点识别与匹配方法及其相机标定应用。提出了一种基于物方几何约束的圆形标志点快速识别与匹配方法;结合平面场景的共线方程,论证和推导了分别基于灭点理论及二维直接线性变换的平面场景中相机外方位元素初值的计算方法;引入了一种基于逐次计算可靠性矩阵QVVP的自检校光束法平差中各类观测值权值的确定方法,提高计算的速度和稳健性。
2.提出了基于SIFT特征的宽基线立体影像最小二乘匹配方法。算法首先基于特征点的空间分布和信息熵选取一定数量的最优SIFT特征点集,并采用基于奇异值分解的SIFT特征匹配、基于SIFT特征尺度和方位信息的自适应归一化互相关(NCC)匹配获得精度较高的初始匹配点对用于立体像对的基本矩阵和单应矩阵估计;然后在对极几何和单应映射的双重约束下,采用基于自适应NCC及距离加权的多尺度最小二乘匹配算法进行扩展匹配并同时保留匹配定位精度较高的原始SIFT同名特征点对;此外,算法还综合应用了基于积分影像的NCC快速计算、金字塔影像匹配等方法和策略,以提高匹配的速度和可靠性。
3.提出了基于核线几何约束的尺度和旋转不变线特征描述符的提取与匹配方法。算法首先基于核线几何约束定义直线对的重叠距离、方位及线支持区,并据此构造了一种基于像素灰度及梯度分布统计信息的尺度和旋转不变线特征描述符;充分考虑了遮挡及视差断裂等因素的影响,采用双向多层次加权匹配策略完成直线段的匹配;采用核主成分分析对特征描述符进行降维处理,提高特征匹配的速度。
4.在Windows平台上基于Visual C++6.0高级编程语言及OpenCV开放计算机视觉库编制了上述算法的相关应用程序;试验验证了上述理论和方法的正确性和有效性。
论文的研究工作,丰富了数字近景摄影测量特征提取与匹配的相关理论和方法,并为后续的宽基线摄影测量三维重建打下了良好的基础。
该论文有图71幅,表9个,参考文献108篇。
With the fast development of high resolution Charged Coupled Device(CCD) and compute technology, digital close-range photogrammetry based on non-metric digital camera has become a very new research field, and at the same time, digital close-range photogrammetry has also become one of an important way to obtain the 3D spatial information with untouched, flexible and quick style . So, some problems related to this field have become hot topics around home and abroad recently. Among these, camera calibration, feature extraction and matching (especially feature extraction and matching for wide baseline stereo pairs) are the key problems when using this technology, because these problems are the basis for following photogrammetric processes, such as orientating the images, 3D reconstruction and data analysis, etc. The research work of this dissertation focus on previous problems and involved in multiple disciplinary theories and method, such as digital image process, image matching, and pattern recognition, etc, mainly include:
1. Recognizing and matching methods of circular signalized points and its application of digital camera calibration were studied. The method of recognizing and matching the circular signalized points based on object geometric constraints was proposed; Two practical algorithms to obtain the initial values of the exterior orientation elements based on the vanishing points theory and the two dimensional direct linear transformation were demonstrated and deduced by combining the collinearity equations in planar scenes; Mathematical model of the bundle block adjustment with self calibration was given and the method of determining the weight of every class of observations based on repeat calculating the QVVP was introduced to improve the calculating speed and the stability.
2. Least squares matching methods for wide base-line stereo images based on SIFT features were proposed. In this algorithm, the optimal SIFT features with good spatial distribution and large information content were first selected, then these SIFT features were matched by using the maching method based on singular value decompositon algorithm, adaptive NCC(Normalized Cross Correlation) matching method based on scale and orientation information of SIFT features, then the fundamental and homography matrix can be estimated by using these initial correspondences; Under the dual geometric constraints by using the fundamental and homography matrix, extended matching methods by using weighted least squares matching and multiple scale template windows were developed, further, by compared to the location error of the original correspondences of SIFT feature points, the least squares matching results were determined to adopted or not; In addition, some novel strategies such as NCC computing with high speed based on integral image, multi-level pyrmid image matching, etc, were adopted to improve the matching speed and reliability.
3. Line feature description with scale and rotation invariant and matching methods based on epipolar geometry constraint were proposed. In this algorithm, the overlap distances, orientations and line support regions of line segments pair were defined based epiploar geometry constraint, and then a line descriptor with scale and rotation invariant based on the mean and standard deviation of the gray values and gradient vectors was constructed; By fully considering the occlude and disparity discontinuity of the line segment pair, the weighted similarity measure for line segment matching based on the two side line support regions were adopted; Dimensionality reduction method based on kernel principal component analysis was introduced to improve the matching speed.
4. Application programms of the previous theories and methods were realized and established base on Windows platform with Visual C++6.0 high level programming languages and OpenCV(Open Compute Vision library), and relative experimental results indicate that the methods proposed in the dissertation is true and effective.
Reseach work in this paper can enrich the relative theories and methods concerned on digital close-range photogrammetry, and good basis are provided for 3D reconstruction of wide baseline photogrammetry.
引文
[1]张剑清,潘励,王树根.摄影测量学[M].武汉:武汉大学出版社, 2003.
[2]冯文灏.近景摄影测量[M].武汉:武汉大学出版社, 2002.
[3]黄桂平.数字近景工业摄影测量若干关键技术研究[D].郑州:解放军信息工程大学测绘学院, 2005.
[4]孙敏.多视几何与传统摄影测量理论[J].北京大学学报(自然科学版), 2007, 43(4): 453-459.
[5] Luhmann T, Stuart R, Kyle S, et al. Close range photogrammetry: principles, techniques and applications[M]. John Wiley & Sons, 2007.
[6]刘亚文.利用数码相机进行房产测量与建筑物的精细三维重建[D].武汉:武汉大学遥感信息工程学院, 2004.
[7]邱茂林.计算机视觉中摄像机定标综述[J].自动化学报, 2000, 26(1): 44-56.
[8] Abdel-Aziz Y I, Karara H M. Direct linear transformation into object space coordinates in close-range photogrammetry[C]. Proc. Symp. Close-Range Photogrammetry, Falls Church: American Society of Photogrammetry, 1971: 1-18.
[9] Yakimovsky Y, Cunningham R. A system for extracting three dimensional measurements from a stereo pair of TV cameras[J]. Computer Graphics and Image Processing, 1978, 7: 195-210.
[10] Hall E L, Tio M B K, McPherson C A, et al. Measuring curved surfaces for robot vision[J]. Computer, 1982, 15(12): 42-54.
[11] Sid-Ahmed M A, Boraie M T. Dual camera calibration for 3-D machine vision metrology[J]. IEEE Transactions on Instrumentation and Measurement, 1990, 39(3): 512-516.
[12] Luh J Y, Klaasen J A. A three dimensional vision by off-shelf system with multi-cameras[J]. IEEE Trans. PAMI, 1985, 7(1): 143-150.
[13] Tsai R Y. An efficient and accurate camera calibration technique for 3D machine vision[C]. Proc of IEEE Conference on Computer Vision and Pattern Recognition, Washington: IEEE Computer Science Press, 1986: 364-374.
[14] Grosky W I, Tamburino L A. A unified spproach to the linear camera calibration problem[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7): 663-671.
[15] Faugeras O D, Maybank S. Motion from point matches: multiplicity of solutions[J]. International Journal of Computer Vision, 1990, 4: 225-246.
[16] Maybank S J, Faugeras O D. A theory of self-calibration of a moving camera[J]. International Journal of Computer Vision, 1992, 8(2): 123-151.
[17] Frank A, Van den Heuvel. Estimation of interior orientation parameters from constraints on line measurements in a single image[J]. Internation Archives of Photogrammetry and Remote Sensing, 1999, 32: 81-88.
[18] Frank A, Van den Heuvel. Exterior orientation using coplanar parallel lines[C]. Proceedings of the Scandinavian Conference on Image Analysis, Lappeeranta: Pattern Recognition Society, 1997: 71-78.
[19] Hans-Gred Mass. Image sequence based automatic multi-camera system calibration technique[EB/OL]. http://www.geo.tudelft.nl/frs/papers/1998/MassImage.pdf.
[20] Tianen Chen, R.S Shibasaki. Determination of camera’s orientation parameters based on line features. International Archives of Photogrammetry and Remote Sensing, 1998, xxxl1: 104-109.
[21]谢文寒.基于多像灭点进行相机标定的方法研究[D].武汉:武汉大学遥感信息工程学院, 2004.
[22] Zhang Z Y. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine ntelligence, 2000, 22(11): 1330 -1334.
[23]张永军,张祖勋,张剑清.利用二维DLT及光束法平差进行数字摄像机标定[J].武汉大学学报(信息科学版), 2002, 27(6): 566-571.
[24]周拥军.基于未检校CCD相机的三维测量方法及其在结构变形监测中的应用[D].上海:上海交通大学船舶海洋与建筑工程学院, 2007.
[25]邓宝松.基于点线特征的大基线图像序列三维重建技术研究[D].长沙:国防科学技术大学研究生院, 2006.
[26] Mokhtarian F, Suomela R. Robust image corner detection through curvature scale space[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12): 1376-1381.
[27] Mokhtarian F, Mackworth A. Scale-based description and recognition of planar curves and two-dimensional shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(1): 34-43.
[28] Abbasi S, Mokhtarian F, Kitter J. Enhancing CSS-based shape retrieval for objects with shadow concavities[J]. Image Vision Computing, 2000, 18: 199-211.
[29] Rohr K. Recognizing corners by fitting parametric models[J]. International Journal of Computer Vision, 1992, 9(3): 213-230.
[30] Harris C G, Stephens M J. A combined corner and edge detector[C]. Proceedings FourthAlvey Vision Conference, Manchester: Plessey Research Roke Manor, 1988: 147-151.
[31] F?rstner W, Gulch E. A fast operator for detection and precise location of distinct points, corners and centres of circular features[C]. Intercommision Conference on Fast Processing of Photogrammetric Data, Stuttgart: Institute for Photogrammetry at Stuttgart University, 1987: 281-305.
[32]柯涛.旋转多基线数字近景摄影测量[D].武汉:武汉大学遥感信息工程学院, 2008.
[33]袁修孝,明洋.一种综合利用像方和物方信息的多影像匹配方法[J].测绘学报, 2009, 38(3): 216-222.
[34]张祖勋,杨生春,张剑清,等.多基线-数字近景摄影测量[J].武汉大学学报(信息科学版), 2007, 5(1): 1-4.
[35]朱庆,吴波,赵杰.基于自适应三角形约束的可靠影像匹配方法[J].计算机学报, 2005, 28(1): 1734-1739.
[36] Zhu Q, Wu B, Tian Y X. Propagation strategies for stereo image matching based on the dynamic triangle constraint[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2007, 62: 295-308.
[37]王志和,张剑清,江万寿.一种基于序列影像匹配的独立树冠可视化方法[J].测绘与空间地理信息, 2005, 28(1): 39-54.
[38]华顺刚,曾令宜.一种基于角点检测的图像密集匹配算法[J].计算机工程与设计, 2007, 28(5): 1092-1095.
[39] Tang L, Wu C K, Chen Z Z. Image dense matching based on region growth with adaptive window[J]. Pattern Recognition Letters, 2002, 23(10): 1169-1178.
[40] Lhuillier M, Quan L. A quasi-dense approach to surface reconstruction from uncalibrated images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 418-433.
[41] Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors[J]. International Journal of Computer Vision, 2000, 37(2):151-172.
[42] Lowe D. Distinctive Image Features from Scale-invariant Keypoints[J]. International Journal on Computer Vision. 2004, 60(2): 91-110.
[43] Mikolajczyk K. Interest point detection invariant to affine transformations[D]. Leuven: Institute National Polytechnique de Grenoble, 2002.
[44] Mikolajczyk K, Schmid C. An affine invariant interest point detector[C]. In: Proceedings of the 7th European Conference on Computer Vision, Montbonnot: INRIA, 2002, vol. I: 128-142.
[45] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.
[46] Kannala J, Brandt S. Quasi-dense wide baseline matching using match propagation[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis: IEEE Computer Science Press, 2007: 1-8.
[47]许振辉,张峰,孙凤梅,等.基于邻域传递的鱼眼图像的准稠密匹配[J].自动化学报, 2009, 35(9): 1159-1167.
[48]程亮,龚健雅,宋小刚,等.面向宽基线立体影像匹配的高质量仿射不变特征提取方法[J].测绘学报, 2008, 37(1): 76-81.
[49] Yue S C, Wang Q, Zhao R C. Robust wide baseline point matching based on scale invariant feature descriptor[J]. Chinese Journal of Aeronautics, 2009, 22: 70-74.
[50] Goederne T, Tuytelaars T, Van Gool L. Fast wide baseline matching for visual navigation[C]. Proceedings of International Conference on Computer Vision and Pattern Recognition, Washington: IEEE Computer Science Press, 2004: 24-29.
[51] Pritchett P, Zisserman A. Wide baseline stereo matching[C]. Proceedings of International Conference on Computer Vision, Bombay: IEEE Computer Science Press, 1998: 754-760.
[52] Canny J. A Computational approach to edge detection[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8: 679-714.
[53] Banarse D S, Duller A W G. Deformation invariant pattern classification for recognizing hand gestures[C]. Proceedings of IEEE International Conference on Neural Networks, Washington, IEEE Computer Science Press, 1996, Vol. 3: 1812-1817.
[54] Medioni G, Nevatia R. Segment-based stereo matching[J]. Computer Vision, Graphics and Image Processing, 1985, 31: 2-18.
[55]席学强,王润生.基于直线特征的图像-模型匹配算法[J].国防科技大学学报, 2000, 22 (6): 70-74.
[56] Deriche R, Faugeras O. Tracking line segments[C]. European Conference on Computer Vision, Antibes: Butterworth-Heinemann, Newton, MA, USA, 1990: 259–267.
[57] Huttenlocher D P, Klanderman G A, Rucklidge W J. Comparing images using the Hausdorff distance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(9): 850-863.
[58]文贡坚.一种基于特征编组的直线立体匹配全局算法[J].软件学报, 2006, 17(12): 2471?2484.
[59] Horaud R. and Skordas T. Stereo correspondence through feature grouping and maximal cliques[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(11):1168-1180.
[60] Gros P. Matching and clustering: two steps towards object modelling in computer vision[J]. International Journal of Robotics Research, 1995, 14(6):633-642.
[61] Ayache N, Faverjon B. Efficient registration of stereo images by matching graph descriptions of edge segments[J]. International Journal of Computer Vision, 1987, 1(2): 107-132.
[62] Rothwell C, Mundy J L, Hoffman B. Representing objects using topology[J]. Lecture Notes in Computer Science, 1996, Vol.1144: 79-108.
[63] Herbert, Vittorio F, Van Gool L. Wide-Baseline Stereo Matching with Line Segments[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, IEEE Computer Science Press, 2005, Vol.1: 329- 336.
[64] Wang Z H, Wu F C, Hu Z Y. MSLD: A robust descriptor for line matching[J]. Pattern Recognition, 2009, 42: 941-953.
[65] Schmid C, Zisserman A. The geometry and matching of lines and curves over multiple views[J]. International Journal of Computer Vision, 2000, 40(3): 199-233.
[66] Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J]. IEEE Journal of Robotics and Automation, 1987, 3(4): 323-344.
[67] Weng J, Cohen P, Herniou M. Camera calibration with distortion models and accuracy evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(10): 965-980.
[68] Zhang Z Y. Determining the epipolar geometry and its uncertainty: A review[J]. International Journal of Computer Vision, 1998, 27(2): 161-195.
[69]马颂德,张正友,计算机视觉-计算理论与算法基础[M].北京:科学出版社,1998.
[70] Hartley R, Zisserman A. Multiview geometry in computer vision[M]. Cambridge: Cambridge University Press, 2000.
[71] Longuet-Higgins H C. A computer algorithm for constructing a scene from two projections[J]. Nature, 1981, 29(3): 133-135.
[72] Hartley R. In defence of the 8-point algorithm[C]. Proceedings of the 5th ICCV, Cambridge: IEEE Computer Science Press, 1995: 1064-1070.
[73] Faugeras O D. The fundamental matrix: theory, algorithms and stability analysis[J]. IJCV, 1996, 17(1): 43-75.
[74] Murray P T D. The development and comparison of robust methods for estimating the fundamental matrix[J]. International Journal of ComputerVision, 1996, 38(3): 1-33.
[75] Fischler M A, Bolles R C. Random sample consensus: A paradigm for model fitting with applications to image analysis andautomated cartography[J]. CACM, 1981, 24(6): 381-395.
[76] Rousseeuw P J. Robust regression and outlier detection[M]. New York: John Wiley & Sons, 1987.
[77] Torr P H S, Murray D W. Outlier detection and motion segmentation[C]. Proceedings of SPIE, Denver: SPIE Press, 1993: 432-443.
[78] Shortis M, Fraser C S. Current trends in close range optical 3D measurement for industrial and engineering applications[J]. Survey Review, 1991, 31(24): 188-200.
[79] Fraser C S. Some thoughts on the emergence of digital close range photogrammetry[J]. Photogrammetric Record, 1998, 16(91): 37-50.
[80] Fraser C S, Bj?rn R. Monitoring the thermal deformation of steel beams via vision metrology[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2000, 55(4): 268-276.
[81]寇新建,黄醒春.数字化近景摄影及其在大型沉井工程中的应用[J].勘查科学技术,2000, 1: 45-49.
[82]林磊,叶列平,程锦.数字摄影技术在结构试验变形测量中的应用[J].实验技术与管理,2003,20(1): 34-38.
[83]徐芳,于承新,黄桂兰,等.利用数字摄影测量进行钢结构挠度的变形监测[J].武汉大学学报(信息科学版),2001,26(3): 256-260.
[84]周拥军,寇新建,任伟中.数字近景摄影测量在模型试验平面位移场测量中的应用[J].勘察科学技术,2004(5): 26-30.
[85]冯文灏,李建松,阎利,等.基于数码相机的孔群定位与数控钻孔[J].测绘学报, 2003, 32(3): 229-233.
[86] Ng H F. Automatic thresholding for defect detection[J]. Pattern Recognition Letters, 2006, 27(14): 259-268.
[87] Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation[J]. Journal of Electrical Imaging, 2004, 13(1): 146-165.
[88]常发亮,刘静,乔谊正.基于遗传算法的彩色图像二维熵多阈值自适应分割[J].控制与决策, 2005, 20(6): 674-678.
[89]唐英干,刘冬,关新平.基于粒子群和二维Otsu方法的快速图像分割[J].控制与决策, 2007, 22(2): 202-205.
[90]许永华,吴敏,何勇,等.一种基于经验知识和信息熵的阈值选择策略[J].化工学报, 2008, 7(59): 1803-1807.
[91]李德仁.自检校光束法区域网平差中的验后权估计[J].武汉测绘学院学报, 1982,1: 16-24.
[92]单杰.多次计算可靠性矩阵QVVP的逐次递归快速算法[J].测绘学报, 1988, 17(4): 269-286.
[93] Lindeberg T. Scale-space theory: A basic tool for analysing structures at different scales [J]. Journal Applied Statistics, 1994, 21(2): 223-261.
[94] Pilu M. A direct method for stereo correspondencebased on singular value decomposition[C]. Proceedings of CVPR, San Juan: IEEE Computer Science Press, 1997: 261-266.
[95] Delponte E, Isgro F, Odone F. SVD-matching using SIFT features[C]. Special Issue on the Vision, Video and Graphics Conference, San Diego: Academic Press Professional, Inc., 2005: 415-431.
[96] Xiao J J, Shah M. Two-frame wide baseline Matching[C]. Proceedings of the 9th IEEE International Conference on Computer Vision, Nice: IEEE Computer Science Press, 2003: 603-609.
[97]邓宝松,高宇,魏迎梅,等.基于仿射迭代方法的大基线图像匹配技术研究[J].信号处理, 2007, 23(6): 823-828.
[98] Georgescu B, Meer P. Point Matching under Large Image Deformations and illumination changes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(6): 674-688.
[99]梁栋,童强,屈磊,等.一种基于极几何和单应约束的图像匹配算法[J].系统仿真学报, 2006, 18(1): 44-46.
[100]陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报, 2005, 16(8): 1431?1437.
[101] Du M T, Chien T L. Fast normalized cross correlation for defect detection[J]. Pattern Recognition Letters, 2003, 24(15): 2625-2631.
[102] Briechle K, Hanebeck U D. Template matching using fast normalized cross correlation[C]. Proceedings of SPIE, Orlando: SPIE Press, 2001, Vol 4387: 95-102.
[103]方建斌.基于KPCA的图像匹配算法研究[D].武汉:武汉理工大学理学院, 2006.
[104]杜卓明,屠宏,耿国华. KPCA方法过程研究与应用[J].计算机工程与应用, 2010, 46(7): 8-10.
[105] Khurd P, Verma R, Davatzikos C. Kernel-Based manifold learning for statisticalanalysis of diffusion tensor images[J]. LNCS, 2007, 4584: 581-593.
[106] Yang J, Alejandro F, Yang J Y, et al. KPCA Plus LDA: A complete kernel fisherdiscriminant framework for feature extraction and recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(2): 230-244.
[107]李晓明,郑链,胡占义.基于SIFT特征的遥感影像自动配准[J].遥感学报, 2006, 10(6): 885-892.
[108] Sangho P, Mohan M. Homography-based analysis of people and vehicle activities in crowded scenes[C]. Eighth IEEE Workshop on Applications of Computer Vision, Austin: IEEE Computer Science Press, 2007: 51-57.
[2]冯文灏.近景摄影测量[M].武汉:武汉大学出版社, 2002.
[3]黄桂平.数字近景工业摄影测量若干关键技术研究[D].郑州:解放军信息工程大学测绘学院, 2005.
[4]孙敏.多视几何与传统摄影测量理论[J].北京大学学报(自然科学版), 2007, 43(4): 453-459.
[5] Luhmann T, Stuart R, Kyle S, et al. Close range photogrammetry: principles, techniques and applications[M]. John Wiley & Sons, 2007.
[6]刘亚文.利用数码相机进行房产测量与建筑物的精细三维重建[D].武汉:武汉大学遥感信息工程学院, 2004.
[7]邱茂林.计算机视觉中摄像机定标综述[J].自动化学报, 2000, 26(1): 44-56.
[8] Abdel-Aziz Y I, Karara H M. Direct linear transformation into object space coordinates in close-range photogrammetry[C]. Proc. Symp. Close-Range Photogrammetry, Falls Church: American Society of Photogrammetry, 1971: 1-18.
[9] Yakimovsky Y, Cunningham R. A system for extracting three dimensional measurements from a stereo pair of TV cameras[J]. Computer Graphics and Image Processing, 1978, 7: 195-210.
[10] Hall E L, Tio M B K, McPherson C A, et al. Measuring curved surfaces for robot vision[J]. Computer, 1982, 15(12): 42-54.
[11] Sid-Ahmed M A, Boraie M T. Dual camera calibration for 3-D machine vision metrology[J]. IEEE Transactions on Instrumentation and Measurement, 1990, 39(3): 512-516.
[12] Luh J Y, Klaasen J A. A three dimensional vision by off-shelf system with multi-cameras[J]. IEEE Trans. PAMI, 1985, 7(1): 143-150.
[13] Tsai R Y. An efficient and accurate camera calibration technique for 3D machine vision[C]. Proc of IEEE Conference on Computer Vision and Pattern Recognition, Washington: IEEE Computer Science Press, 1986: 364-374.
[14] Grosky W I, Tamburino L A. A unified spproach to the linear camera calibration problem[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7): 663-671.
[15] Faugeras O D, Maybank S. Motion from point matches: multiplicity of solutions[J]. International Journal of Computer Vision, 1990, 4: 225-246.
[16] Maybank S J, Faugeras O D. A theory of self-calibration of a moving camera[J]. International Journal of Computer Vision, 1992, 8(2): 123-151.
[17] Frank A, Van den Heuvel. Estimation of interior orientation parameters from constraints on line measurements in a single image[J]. Internation Archives of Photogrammetry and Remote Sensing, 1999, 32: 81-88.
[18] Frank A, Van den Heuvel. Exterior orientation using coplanar parallel lines[C]. Proceedings of the Scandinavian Conference on Image Analysis, Lappeeranta: Pattern Recognition Society, 1997: 71-78.
[19] Hans-Gred Mass. Image sequence based automatic multi-camera system calibration technique[EB/OL]. http://www.geo.tudelft.nl/frs/papers/1998/MassImage.pdf.
[20] Tianen Chen, R.S Shibasaki. Determination of camera’s orientation parameters based on line features. International Archives of Photogrammetry and Remote Sensing, 1998, xxxl1: 104-109.
[21]谢文寒.基于多像灭点进行相机标定的方法研究[D].武汉:武汉大学遥感信息工程学院, 2004.
[22] Zhang Z Y. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine ntelligence, 2000, 22(11): 1330 -1334.
[23]张永军,张祖勋,张剑清.利用二维DLT及光束法平差进行数字摄像机标定[J].武汉大学学报(信息科学版), 2002, 27(6): 566-571.
[24]周拥军.基于未检校CCD相机的三维测量方法及其在结构变形监测中的应用[D].上海:上海交通大学船舶海洋与建筑工程学院, 2007.
[25]邓宝松.基于点线特征的大基线图像序列三维重建技术研究[D].长沙:国防科学技术大学研究生院, 2006.
[26] Mokhtarian F, Suomela R. Robust image corner detection through curvature scale space[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12): 1376-1381.
[27] Mokhtarian F, Mackworth A. Scale-based description and recognition of planar curves and two-dimensional shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(1): 34-43.
[28] Abbasi S, Mokhtarian F, Kitter J. Enhancing CSS-based shape retrieval for objects with shadow concavities[J]. Image Vision Computing, 2000, 18: 199-211.
[29] Rohr K. Recognizing corners by fitting parametric models[J]. International Journal of Computer Vision, 1992, 9(3): 213-230.
[30] Harris C G, Stephens M J. A combined corner and edge detector[C]. Proceedings FourthAlvey Vision Conference, Manchester: Plessey Research Roke Manor, 1988: 147-151.
[31] F?rstner W, Gulch E. A fast operator for detection and precise location of distinct points, corners and centres of circular features[C]. Intercommision Conference on Fast Processing of Photogrammetric Data, Stuttgart: Institute for Photogrammetry at Stuttgart University, 1987: 281-305.
[32]柯涛.旋转多基线数字近景摄影测量[D].武汉:武汉大学遥感信息工程学院, 2008.
[33]袁修孝,明洋.一种综合利用像方和物方信息的多影像匹配方法[J].测绘学报, 2009, 38(3): 216-222.
[34]张祖勋,杨生春,张剑清,等.多基线-数字近景摄影测量[J].武汉大学学报(信息科学版), 2007, 5(1): 1-4.
[35]朱庆,吴波,赵杰.基于自适应三角形约束的可靠影像匹配方法[J].计算机学报, 2005, 28(1): 1734-1739.
[36] Zhu Q, Wu B, Tian Y X. Propagation strategies for stereo image matching based on the dynamic triangle constraint[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2007, 62: 295-308.
[37]王志和,张剑清,江万寿.一种基于序列影像匹配的独立树冠可视化方法[J].测绘与空间地理信息, 2005, 28(1): 39-54.
[38]华顺刚,曾令宜.一种基于角点检测的图像密集匹配算法[J].计算机工程与设计, 2007, 28(5): 1092-1095.
[39] Tang L, Wu C K, Chen Z Z. Image dense matching based on region growth with adaptive window[J]. Pattern Recognition Letters, 2002, 23(10): 1169-1178.
[40] Lhuillier M, Quan L. A quasi-dense approach to surface reconstruction from uncalibrated images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 418-433.
[41] Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors[J]. International Journal of Computer Vision, 2000, 37(2):151-172.
[42] Lowe D. Distinctive Image Features from Scale-invariant Keypoints[J]. International Journal on Computer Vision. 2004, 60(2): 91-110.
[43] Mikolajczyk K. Interest point detection invariant to affine transformations[D]. Leuven: Institute National Polytechnique de Grenoble, 2002.
[44] Mikolajczyk K, Schmid C. An affine invariant interest point detector[C]. In: Proceedings of the 7th European Conference on Computer Vision, Montbonnot: INRIA, 2002, vol. I: 128-142.
[45] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.
[46] Kannala J, Brandt S. Quasi-dense wide baseline matching using match propagation[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis: IEEE Computer Science Press, 2007: 1-8.
[47]许振辉,张峰,孙凤梅,等.基于邻域传递的鱼眼图像的准稠密匹配[J].自动化学报, 2009, 35(9): 1159-1167.
[48]程亮,龚健雅,宋小刚,等.面向宽基线立体影像匹配的高质量仿射不变特征提取方法[J].测绘学报, 2008, 37(1): 76-81.
[49] Yue S C, Wang Q, Zhao R C. Robust wide baseline point matching based on scale invariant feature descriptor[J]. Chinese Journal of Aeronautics, 2009, 22: 70-74.
[50] Goederne T, Tuytelaars T, Van Gool L. Fast wide baseline matching for visual navigation[C]. Proceedings of International Conference on Computer Vision and Pattern Recognition, Washington: IEEE Computer Science Press, 2004: 24-29.
[51] Pritchett P, Zisserman A. Wide baseline stereo matching[C]. Proceedings of International Conference on Computer Vision, Bombay: IEEE Computer Science Press, 1998: 754-760.
[52] Canny J. A Computational approach to edge detection[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8: 679-714.
[53] Banarse D S, Duller A W G. Deformation invariant pattern classification for recognizing hand gestures[C]. Proceedings of IEEE International Conference on Neural Networks, Washington, IEEE Computer Science Press, 1996, Vol. 3: 1812-1817.
[54] Medioni G, Nevatia R. Segment-based stereo matching[J]. Computer Vision, Graphics and Image Processing, 1985, 31: 2-18.
[55]席学强,王润生.基于直线特征的图像-模型匹配算法[J].国防科技大学学报, 2000, 22 (6): 70-74.
[56] Deriche R, Faugeras O. Tracking line segments[C]. European Conference on Computer Vision, Antibes: Butterworth-Heinemann, Newton, MA, USA, 1990: 259–267.
[57] Huttenlocher D P, Klanderman G A, Rucklidge W J. Comparing images using the Hausdorff distance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(9): 850-863.
[58]文贡坚.一种基于特征编组的直线立体匹配全局算法[J].软件学报, 2006, 17(12): 2471?2484.
[59] Horaud R. and Skordas T. Stereo correspondence through feature grouping and maximal cliques[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(11):1168-1180.
[60] Gros P. Matching and clustering: two steps towards object modelling in computer vision[J]. International Journal of Robotics Research, 1995, 14(6):633-642.
[61] Ayache N, Faverjon B. Efficient registration of stereo images by matching graph descriptions of edge segments[J]. International Journal of Computer Vision, 1987, 1(2): 107-132.
[62] Rothwell C, Mundy J L, Hoffman B. Representing objects using topology[J]. Lecture Notes in Computer Science, 1996, Vol.1144: 79-108.
[63] Herbert, Vittorio F, Van Gool L. Wide-Baseline Stereo Matching with Line Segments[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, IEEE Computer Science Press, 2005, Vol.1: 329- 336.
[64] Wang Z H, Wu F C, Hu Z Y. MSLD: A robust descriptor for line matching[J]. Pattern Recognition, 2009, 42: 941-953.
[65] Schmid C, Zisserman A. The geometry and matching of lines and curves over multiple views[J]. International Journal of Computer Vision, 2000, 40(3): 199-233.
[66] Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J]. IEEE Journal of Robotics and Automation, 1987, 3(4): 323-344.
[67] Weng J, Cohen P, Herniou M. Camera calibration with distortion models and accuracy evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(10): 965-980.
[68] Zhang Z Y. Determining the epipolar geometry and its uncertainty: A review[J]. International Journal of Computer Vision, 1998, 27(2): 161-195.
[69]马颂德,张正友,计算机视觉-计算理论与算法基础[M].北京:科学出版社,1998.
[70] Hartley R, Zisserman A. Multiview geometry in computer vision[M]. Cambridge: Cambridge University Press, 2000.
[71] Longuet-Higgins H C. A computer algorithm for constructing a scene from two projections[J]. Nature, 1981, 29(3): 133-135.
[72] Hartley R. In defence of the 8-point algorithm[C]. Proceedings of the 5th ICCV, Cambridge: IEEE Computer Science Press, 1995: 1064-1070.
[73] Faugeras O D. The fundamental matrix: theory, algorithms and stability analysis[J]. IJCV, 1996, 17(1): 43-75.
[74] Murray P T D. The development and comparison of robust methods for estimating the fundamental matrix[J]. International Journal of ComputerVision, 1996, 38(3): 1-33.
[75] Fischler M A, Bolles R C. Random sample consensus: A paradigm for model fitting with applications to image analysis andautomated cartography[J]. CACM, 1981, 24(6): 381-395.
[76] Rousseeuw P J. Robust regression and outlier detection[M]. New York: John Wiley & Sons, 1987.
[77] Torr P H S, Murray D W. Outlier detection and motion segmentation[C]. Proceedings of SPIE, Denver: SPIE Press, 1993: 432-443.
[78] Shortis M, Fraser C S. Current trends in close range optical 3D measurement for industrial and engineering applications[J]. Survey Review, 1991, 31(24): 188-200.
[79] Fraser C S. Some thoughts on the emergence of digital close range photogrammetry[J]. Photogrammetric Record, 1998, 16(91): 37-50.
[80] Fraser C S, Bj?rn R. Monitoring the thermal deformation of steel beams via vision metrology[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2000, 55(4): 268-276.
[81]寇新建,黄醒春.数字化近景摄影及其在大型沉井工程中的应用[J].勘查科学技术,2000, 1: 45-49.
[82]林磊,叶列平,程锦.数字摄影技术在结构试验变形测量中的应用[J].实验技术与管理,2003,20(1): 34-38.
[83]徐芳,于承新,黄桂兰,等.利用数字摄影测量进行钢结构挠度的变形监测[J].武汉大学学报(信息科学版),2001,26(3): 256-260.
[84]周拥军,寇新建,任伟中.数字近景摄影测量在模型试验平面位移场测量中的应用[J].勘察科学技术,2004(5): 26-30.
[85]冯文灏,李建松,阎利,等.基于数码相机的孔群定位与数控钻孔[J].测绘学报, 2003, 32(3): 229-233.
[86] Ng H F. Automatic thresholding for defect detection[J]. Pattern Recognition Letters, 2006, 27(14): 259-268.
[87] Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation[J]. Journal of Electrical Imaging, 2004, 13(1): 146-165.
[88]常发亮,刘静,乔谊正.基于遗传算法的彩色图像二维熵多阈值自适应分割[J].控制与决策, 2005, 20(6): 674-678.
[89]唐英干,刘冬,关新平.基于粒子群和二维Otsu方法的快速图像分割[J].控制与决策, 2007, 22(2): 202-205.
[90]许永华,吴敏,何勇,等.一种基于经验知识和信息熵的阈值选择策略[J].化工学报, 2008, 7(59): 1803-1807.
[91]李德仁.自检校光束法区域网平差中的验后权估计[J].武汉测绘学院学报, 1982,1: 16-24.
[92]单杰.多次计算可靠性矩阵QVVP的逐次递归快速算法[J].测绘学报, 1988, 17(4): 269-286.
[93] Lindeberg T. Scale-space theory: A basic tool for analysing structures at different scales [J]. Journal Applied Statistics, 1994, 21(2): 223-261.
[94] Pilu M. A direct method for stereo correspondencebased on singular value decomposition[C]. Proceedings of CVPR, San Juan: IEEE Computer Science Press, 1997: 261-266.
[95] Delponte E, Isgro F, Odone F. SVD-matching using SIFT features[C]. Special Issue on the Vision, Video and Graphics Conference, San Diego: Academic Press Professional, Inc., 2005: 415-431.
[96] Xiao J J, Shah M. Two-frame wide baseline Matching[C]. Proceedings of the 9th IEEE International Conference on Computer Vision, Nice: IEEE Computer Science Press, 2003: 603-609.
[97]邓宝松,高宇,魏迎梅,等.基于仿射迭代方法的大基线图像匹配技术研究[J].信号处理, 2007, 23(6): 823-828.
[98] Georgescu B, Meer P. Point Matching under Large Image Deformations and illumination changes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(6): 674-688.
[99]梁栋,童强,屈磊,等.一种基于极几何和单应约束的图像匹配算法[J].系统仿真学报, 2006, 18(1): 44-46.
[100]陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报, 2005, 16(8): 1431?1437.
[101] Du M T, Chien T L. Fast normalized cross correlation for defect detection[J]. Pattern Recognition Letters, 2003, 24(15): 2625-2631.
[102] Briechle K, Hanebeck U D. Template matching using fast normalized cross correlation[C]. Proceedings of SPIE, Orlando: SPIE Press, 2001, Vol 4387: 95-102.
[103]方建斌.基于KPCA的图像匹配算法研究[D].武汉:武汉理工大学理学院, 2006.
[104]杜卓明,屠宏,耿国华. KPCA方法过程研究与应用[J].计算机工程与应用, 2010, 46(7): 8-10.
[105] Khurd P, Verma R, Davatzikos C. Kernel-Based manifold learning for statisticalanalysis of diffusion tensor images[J]. LNCS, 2007, 4584: 581-593.
[106] Yang J, Alejandro F, Yang J Y, et al. KPCA Plus LDA: A complete kernel fisherdiscriminant framework for feature extraction and recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(2): 230-244.
[107]李晓明,郑链,胡占义.基于SIFT特征的遥感影像自动配准[J].遥感学报, 2006, 10(6): 885-892.
[108] Sangho P, Mohan M. Homography-based analysis of people and vehicle activities in crowded scenes[C]. Eighth IEEE Workshop on Applications of Computer Vision, Austin: IEEE Computer Science Press, 2007: 51-57.