基于序列图像的空间非合作目标三维重建关键技术研究
|
摘要
空间非合作目标三维模型获取是在轨服务的关键技术之一，在太空领域有着广阔的应用前景。本文以对空间非合作目标进行绕飞、伴飞为背景，研究基于序列图像的空间非合作目标三维结构重建问题，主要围绕空间平台相机在线标定、多种变换条件下的快速图像匹配和快速精确鲁棒的基本矩阵估计三项关键技术进行研究。
为了自动提取场景几何约束信息，对边缘检测算法进行了深入研究，提出了一种基于多结构元素复合滤波的形态学边缘检测算法。算法不仅能够有效检测图像的边缘，还具有抗噪性强、处理速度快的优点。为了降低场景约束条件，扩展空间平台相机在线标定的应用范围，提出了一种基于平行四边形相似不变量的相机自标定方法。同时，为了校正因相机畸变而产生的成像误差，提出了一种基于直线射影不变性的径向畸变参数估计算法。该标定方法不仅有效降低了场景约束条件，而且具有简单、灵活的特点。
在空间平台硬件计算资源有限的情况下，为了实现存在多种变化的图像间的快速匹配，首先提出了一种Harris角点检测硬件加速方法，并将其应用到高斯金字塔图像上，实现多尺度Harris角点检测硬件加速，采用内嵌并行运算的流水线结构，提高算法的实时处理能力，减少硬件资源消耗。然后，提出了一种基于SCCH的局部特征描述算法，具有计算简单、独特性好、鲁棒性强的特点。最后，将二者结合在一起，实现多种变换条件下的快速图像匹配。
为了快速、鲁棒、精确地估计基本矩阵，提出了应用序贯相似检测的快速鲁棒基本矩阵估计算法。算法引入SSDA加速策略提高其处理速度，用M估计算法优化初始内点集，降低估计余差较大内点的影响，提高算法的估计精度和鲁棒性。
在本文研究成果的基础上设计了一种三维重建实验系统，为建立实际的基于序列图像空间非合作目标三维重建系统奠定了基础。实验结果表明，该实验系统是有效的和可行的。
Three-dimensional (3D) model acquisition of non-cooperative space target is oneof the key technologies for on-orbit servicing, and has broad application prospects in thespace. Under the background that flying around or along with the non-cooperative spacetarget, this dissertation reseaches on3D structure reconstruction technologies fromimage sequences of non-cooperative space target. Three key technologies for3Dreconstruction are mainly investigated, including on-line camera calibration on spaceplatform, high-speed image matching with multiple transformations between images, aswell as fast, accurate and robust fundamental matrix estimation.
To extract the geometric constraint information automatically, edge detectionalgorithm is studied, and a morphological edge detection algorithm based onmulti-strucure elements compound filter is presented. The proposed algorithm performsbetter in edge detection, noise immunity and speed. In order to lower the sceneconstraint requirements and extend the application scope, a camera calibration methodbased on parallelogram similarity invariants is presented. The first two terms radialdistortion parameters are also estimated according to the fact that straight lines in thescence are projected as straight lines in the image. The proposed algorithm not onlyreduces the restriction of sence constraint effectively, but also is simple and flexible.
With the hardware computing resources limited, to match those images withmultiple transformations fastly, a hardware-accelerated method for Harris cornerdetector is developed firstly, and it is applied to the Gaussian pyramid images to achievehardware acceleration for multi-scale Harris corner detector. The method uses pipelinearchitecture with internal parallel operation to improve the real-time performance andreduce the hardware resources consumption. Secondly, a local feature descriptionalgorithm based on signed contrast context histogram (SCCH) is proposed, which issimple, distinctive and robust. Finally, the above two algorithm are integrated to matchimages fast under multiple transformations.
To estimate the fundamental matrix rapidly, robustly and accurately, a fundamentalmatrix estimation method based on sequential similarity detection algorithm (SSDA) ispresented. SSDA is introduced into the maximum a posteriori sample consensus(MAPSAC) to increase the speed. The initial inliers obtained by improved MAPSACare optimized with M-estimator. Those inliers with larger residual errors are removed toenhance the precision and improve the robustness of the algorithm.
A3D reconstruction system is designed based on the results of this study, whichlays a foundation for establishing actual3D reconstruction system for non-cooperativespace target using image sequences. The experimental results show that theexperimental system is effective and feasible.
为了自动提取场景几何约束信息，对边缘检测算法进行了深入研究，提出了一种基于多结构元素复合滤波的形态学边缘检测算法。算法不仅能够有效检测图像的边缘，还具有抗噪性强、处理速度快的优点。为了降低场景约束条件，扩展空间平台相机在线标定的应用范围，提出了一种基于平行四边形相似不变量的相机自标定方法。同时，为了校正因相机畸变而产生的成像误差，提出了一种基于直线射影不变性的径向畸变参数估计算法。该标定方法不仅有效降低了场景约束条件，而且具有简单、灵活的特点。
在空间平台硬件计算资源有限的情况下，为了实现存在多种变化的图像间的快速匹配，首先提出了一种Harris角点检测硬件加速方法，并将其应用到高斯金字塔图像上，实现多尺度Harris角点检测硬件加速，采用内嵌并行运算的流水线结构，提高算法的实时处理能力，减少硬件资源消耗。然后，提出了一种基于SCCH的局部特征描述算法，具有计算简单、独特性好、鲁棒性强的特点。最后，将二者结合在一起，实现多种变换条件下的快速图像匹配。
为了快速、鲁棒、精确地估计基本矩阵，提出了应用序贯相似检测的快速鲁棒基本矩阵估计算法。算法引入SSDA加速策略提高其处理速度，用M估计算法优化初始内点集，降低估计余差较大内点的影响，提高算法的估计精度和鲁棒性。
在本文研究成果的基础上设计了一种三维重建实验系统，为建立实际的基于序列图像空间非合作目标三维重建系统奠定了基础。实验结果表明，该实验系统是有效的和可行的。
Three-dimensional (3D) model acquisition of non-cooperative space target is oneof the key technologies for on-orbit servicing, and has broad application prospects in thespace. Under the background that flying around or along with the non-cooperative spacetarget, this dissertation reseaches on3D structure reconstruction technologies fromimage sequences of non-cooperative space target. Three key technologies for3Dreconstruction are mainly investigated, including on-line camera calibration on spaceplatform, high-speed image matching with multiple transformations between images, aswell as fast, accurate and robust fundamental matrix estimation.
To extract the geometric constraint information automatically, edge detectionalgorithm is studied, and a morphological edge detection algorithm based onmulti-strucure elements compound filter is presented. The proposed algorithm performsbetter in edge detection, noise immunity and speed. In order to lower the sceneconstraint requirements and extend the application scope, a camera calibration methodbased on parallelogram similarity invariants is presented. The first two terms radialdistortion parameters are also estimated according to the fact that straight lines in thescence are projected as straight lines in the image. The proposed algorithm not onlyreduces the restriction of sence constraint effectively, but also is simple and flexible.
With the hardware computing resources limited, to match those images withmultiple transformations fastly, a hardware-accelerated method for Harris cornerdetector is developed firstly, and it is applied to the Gaussian pyramid images to achievehardware acceleration for multi-scale Harris corner detector. The method uses pipelinearchitecture with internal parallel operation to improve the real-time performance andreduce the hardware resources consumption. Secondly, a local feature descriptionalgorithm based on signed contrast context histogram (SCCH) is proposed, which issimple, distinctive and robust. Finally, the above two algorithm are integrated to matchimages fast under multiple transformations.
To estimate the fundamental matrix rapidly, robustly and accurately, a fundamentalmatrix estimation method based on sequential similarity detection algorithm (SSDA) ispresented. SSDA is introduced into the maximum a posteriori sample consensus(MAPSAC) to increase the speed. The initial inliers obtained by improved MAPSACare optimized with M-estimator. Those inliers with larger residual errors are removed toenhance the precision and improve the robustness of the algorithm.
A3D reconstruction system is designed based on the results of this study, whichlays a foundation for establishing actual3D reconstruction system for non-cooperativespace target using image sequences. The experimental results show that theexperimental system is effective and feasible.
引文
[1]崔乃刚,王平,郭继峰等.空间在轨服务技术发展综述[J].宇航学报,2007,28(4):805-811.
[2]段春梅.基于多视图的三维模型重建方法研究[D].济南,山东大学,2009.
[3]唐丽.由手提相机获得的序列图像进行三维重建[D].陕西,西安电子科技大学,2003.
[4]江泽涛.序列图象重建三维物体形状方法研究[D].西安,西北工业大学,2006.
[5] H.-Y. Shum, M. Han, R. Szeliski. Interactive Construction of3D Models fromPanoramic Mosaics[C]. In Proceedings of International Conference on ComputerVision and Pattern Recognition,1998,427-433.
[6] A. Criminisi, A. Zisserman. Single View Metrology[J]. International Journal ofComputer Vision,2000,40(2):123-148.
[7] L. Zhang, G. Dugas, Phocion, L.-S. Samson, S. M. Seitz. Single View Modeling ofFree-form Scenes[J]. Journal of Visualization and Computer Animation,2002,13(4):225-235.
[8] Li R, Sclaroff S. Multi-scale3D Scene Flow from Binocular Stereo Sequences[C].In Preceedings of the IEEE Workshop on Moton and Video Computing,2005:147-153.
[9] K. Kutulakos, S.M.Seitz. A Theory of Shape by Space Carving[J]. InternationalJournal of Computer Vision,2000,38(3):199-218.
[10]A. Broadhurst. A Probabilistic Framework for Spare Carving[D]. Ph.D. thesis,University of Cambfidge, UK,2001.
[11]刘钢,王锐,鲍虎军.一种可见外壳生成算法[J].软件学报,2002,13(9):1823-1829.
[12]Yang R, Pollefeys M, Welch G. Dealing with Textureless Regions and SpecularHighlights: A Progressive Space Carving Scheme using a Novel Photo-consistencyMeasure [C]. IEEE International Conference on Computer Vision, Piscataway, NJ,USA:2003,576-584.
[13]Y. Furukawa, J. Ponce. Carved Visual Hulls for Image-Based Modeling[C]. InProceedings of European Conference on Computer Vision,2006,1:564-577.
[14]S.Bougnoux, L.Roberto. TotalCalib: A Fast and Reliable System for Off-lineCalibration of Images Sequence[C]. In Proceedings of International Conference onComputer Vision and Pattern Recognition, Demo Session,1997.
[15]E. Poulin, M. Ouimet, M. C. Frasson. Interactively Modeling with Photogrammetry
[C]. In Proceedings of Eurographics Workshop on Rendering, Vienna, Austria,1998,93-104.
[16]Cipolla R, Robertson D P, Boyer E G. Photobuilder-3D Models of ArchitecturalScenes from Uncalibrated Images [C]. In Proc. IEEE International Conference onMultimedia Computing and Systems. Firenze,1999(1):25-31.
[17]D.Nister. Reconstruction from uncalibrated sequences with a hierarchy of trifocaltensors[C]. ln Proc. European Conference on Computer Vision(ECCV2000),2000,1:649-663.
[18]D.Nister. Calibration with robust use of cheirality by quasi-affine reconstruction ofthe set of camera projection centers[C]. In Proc. IEEE International Conference onComputerVision (ICCV2001),2001,2:116-123.
[19]D.Nister. Frame decimation for structure and motion[C]. In Proc.2nd Worrkshopon Structure from Multiple of Large Environments (SMILE2000), Springer LectureNotes on Computer Science,2001,2018:17-34.
[20]D.Nister. Automatic dense reconstruction from uncalibrated video sequences[D].PhD Thesis, Royal Institute of Technology KTH, Stockholm, Sweden,2001.
[21]R.Tsai, R. K. Lenz. A Technique for Fully Automomous and Efficient3D RoboticsHand/Eye Calibration[J]. IEEE Trans. Robotics and Automation,1989,5(3):345-358.
[22]W. Faig. Calibration of close-range photogrammetry systems: mathematicalformulation[J]. Photogrammetrie Engineering and Remote Sensing,1975,01(41):1479-1486.
[23]Hartley R. Self-calibration of stationary cameras[J]. International. Journal ofComputerVision,1997,22(1):5-23.
[24]李华,吴福朝,胡占义.一种新的线性摄像机自标定方法[J].计算机学报,2000,23(11):1121-1129.
[25]雷成,吴福朝,胡占义.一种新的基于主动视觉系统的摄像机自标定方法[J].计算机学报,2000,23(11):1130-1139.
[26]吴福朝,李华,胡占义.基于主动视觉的摄像机自标定方法研究[J].自动化学报,2001,27(6):736-746.
[27]吴福朝,胡占义.摄像机自定标的线性理论与算法[J].计算机学报,2001,24(9):1121-1135.
[28]Guanghui Wang, Q.M.Jonathan Wu, Wei Zhang. Kruppa equation based cameracalibration from homography induced by remote plane[J]. Pattern RecognitionLetters,2008,29:2137-2144.
[29]A. Habed, B. Boufama. Camera self-calibration from bivariate polynomials derivedfrom Kruppa’s equations[J]. Pattern Recognition,2008,41:2484-2492.
[30]S.Maybank, O.Faugeras. A theory of self-calibration of a moving camera[J].International Journal of Computer Vision,1992,8(2):123-151.
[31]O. Faugeras, Q. T. Luong, S. Maybank. Camera self-calibration: theory andexperiments[C]. In Proceedings of the2th European Conference on ComputerVision, Italy,1992,321-334.
[32]R. Hartley. Kruppa's Equations Derived from the Fundamental Matrix[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1997,19(2):133-135.
[33]M.1. Lourakis, R.Deriche. Camera Self-Calibration Using the Singular ValueDecomposition of the Fundamental Matrix: From Point Correspondences to3dMeasurements[J]. In4th Asian Conference on Computer Vision, Taibei, China,2000:403-408.
[34]C.Lei, F. Wu, Z. Hu, H.T. Tsui. A New Approach to Solving Kruppa Equations forCamera Se lf-Calibration[C]. In ICPR02, Quebec,2002,308-311.
[35]B.Triggs. Auto-calibration and the absolute quadric[C]. In Proceedings ofComputer Vision and Pattern Recognition,1997,609-614.
[36]R.Hartley. Euclidean reconstruction and invariants from multiple images[J]. IEEETrans. PAMI,1994,16(10):1036-1041.
[37]M.Pollefeys, L.V.Gool, A.Oosterlinck. The modulus constraint: a new constraintfor self-calibration[C]. In Proceedings of International Conference of PatternRecognition, Vienna,1996,349-353.
[38]吴福朝,王光辉,胡占义.由矩形确定相机内参数与位置的线性方法[J].软件学报,2003,14(3):703-712.
[39]全红艳,张天文.一种新的利用模板进行相机自标定的方法[J].电子学报,2005,33(11):1941-1945.
[40]王年,梁栋,范益政等.一种基于矩形的相机自标定方法[J].中国科学技术大学学报,2005,35(5):693-700.
[41]Lazaros Grammatikopoulos, George Karras, Elli Petsa. An automatic approach forcamera calibration from vanishing points[J]. Photogrammetry&Remote Sensing,2007,62:64-76.
[42]B.W. He, Y.F. Li. Camera calibration from vanishing points in a vision system[J].Optics&Laser Technology,2008,40:555-561.
[43]Wang G., Tsui H.T., Hu Z. Reconstruction of structured scenes from twouncalibrated images[J]. Pattern Recognition Lett.2005,26(2):207-220.
[44]M.Wilczkowiak, E.Boyer, P. Sturm.3d Modelling Using Geometric Constraints: AParallelepiped Based Approach[C]. In Proceedings of the7th European Conferenceon Computer Vision, Copenhagen, Denmark: Springer-Verlag,2002,221-236.
[45]E Schaffalitzky, A.Zissermam. Multi-view Matching for Unordered Imsge Sets, or“How Do I Organise My Holiday Snaps?”[C]. In Proceedings of EuropeanConference on Computer Vision, Copeahaguen,2002,1:414-431.
[46]陈夏艳,伍先达.基于距离特征的自适应阈值视频拼接算法[J].模式识别与人工智能,2010,23(5):727-730.
[47]Lee L, Ko H. Gradient-based local affine invariant feature extraction for mobilerobot localization in indoor environments[J]. Pattern Recognition Letters,2008,29(14):1934-1940.
[48]Dongjoe Shin, Tardi Tjahjadi. Clique Descriptor of Affine Invariant Regions forRobust Wide Baseline Image Matching[J]. Pattern Recognition,2010,43:3261-3272.
[49]Loris Nanni, Alessandra Lumini, Sheryl Brahnam. Local binary patterns variants astexture descriptors for medical image analysis[J]. Artificial Intelligence in Medicine,2010,49:117-125
[50]杨恒,王庆.一种新的局部不变特征检测和描述算法[J].计算机学报,2010,33(5):935-944.
[51]Yang Duan-duan, Sluzek Andrzej. A low-dimensional local descriptorincorporating TPS warping for image matching[J]. Image and Vision Computing.2010,28:1184-1195.
[52]H.Wang, M.Brady. Real-time corner detection algorithm for motion estimation[J].Image and Vision Computing,1995,13(9):695-703
[53]Mokhtarian F, Suomela R. Robust image corner detection through curvature scalespace[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(12):1376-1381
[54]He X C, Yung N H C. Curvature scale space corner detector with adaptivethreshold and dynamic region of support[C]. In: Proceedings of the17thInternational Conference on Pattern Recognition. Washington D.C., USA: IEEE,2004,791-794.
[55]Zhang X H, Lei M, Yang D, Wang Y Z et al. Multi-scale curvature product forrobust image corner detection in curvature scale space[J]. Pattern RecognitionLetters,2007,28(5):545-554.
[56]Moravec H. Towards automatic visual obstacle avoidance[C]. In: Proceedings oftheInternational Joint Conference on Artificial Intelligence.1977.
[57]C. Harris, M. Stephens. A Combined Corner and Edge Detector[C]. Proc. FourthAlvey Vision Conference,1988,189-192.
[58]Dufournaud Y, Schmid C, Horaud R. Matching images with different resolutions[C]Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Hilton Head Island, South Carolina,2000,612-618.
[59]Mikolajczyk K, Schmid C. Indexing based on scale invariant interest points[C].Proceedings of the8th International Conference on Computer Vision, Vancouer,Canda,2001,525-531.
[60]Mikolajczyk K, Schmid C. An affine invariant interest point detector[C].Proceedings of the7th European Conference on Computer Vision, Copenhagen,Denmark,2002,128-142.
[61]Mikolajczyk K, Schmid C. Scale&affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86
[62]Lindeberg T. Feature detection with automatic scale selection[J]. InternationalJournal of Computer Vision,1998,30(2):79-116
[63]Lowe D G. Distinctive image features from scale invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110
[64]Bay H, Tuytelaars T, Gool L V. SURF: Speeded up robust features[C].Proceedings of the9th European Conference on Computer Vision, Graz, Austria,2006:404-417
[65]Tuytelaars T, Gool LV. Matching widely separated views based on affine invariantregions[J]. International Journal of Computer Vision,2004,59(1):61-85.
[66]Matas J, Chum O, Urban M, Pajdla T. Robust wide-baseline stereo from maximallystable extremal regions[C]. In Proceedings of the British Machine VisionConference,2002.
[67]Tuytelaars T, Mikolajczyk K. Local invariant feature detectors: a survey[J].Foundations and Trends in Computer Graphics andVision,2007,3(3):177-280.
[68]T.Lee. Image Representation Using2-D Gabor Wavelets[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1996,18(10):959-971.
[69]Florack L, Romeny BtH, Koenderink J, Viergever M. General intensitytransformations and second order invariants[C]. In the7th ScandinavianConference on Image Analysis, Aalborg, Denmark,1991.
[70]Baumberg A. Reliable feature matching across widely separated views [C].Proceedings of International Conference on Computer Vision and PatternRecognition. New York, USA: ACM Press,2000,774-781.
[71]Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets [C].Proceedings of the7th European Conference on Computer Vision, Cambridge, MA,USA: MIT Press,2002,414-431.
[72]Leung T, Malik J. Representing and recognizing the visual appearance of materialsusing three-dimensional textons[J]. International Journal of Computer Vision,2001,43(1):29-44.
[73]Varma M, Zisserman A. Classifying images of materials: achieving viewpoint andillumination independence[C]. In: Proceedings of the European Conference onComputer Vision,2002.
[74]Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[75]Li J, Allinson N M. A comprehensive review of current local features for computervision[J]. Neurocomputing,2008,71(10-12):1771-1787.
[76]Lazebnik S, Schmid C, Ponce J. Sparse texture representation using affine-invariantneighborhoods[C]. Proc. Conf. Computer Vision and Pattern Recognition,2003:319-324.
[77]F.C. Wu, Z.H.Wang, X.G.Wang. Feature Vector Field and Feature Matching[J].Pattern Recognition,2010,43:3273-3281.
[78]王旭光,王志衡,吴福朝. Harris相关与特征匹配[J].模式识别与人工智能,2009,22(4):505-513.
[79]Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotationinvariant texture classification with local binary patterns[J]．IEEE Transactions onPattern Analysis and Machine Intelligence,2002,24(7):971-987.
[80]M. Heikkila, M. Pietikainen, C. Schmid. Description of interest regions with localbinary patterns[J]. Pattern Recognition,2009,42(3):425-436.
[81]郑永斌,黄新生,丰松江. SIFT和LBP相结合的图像匹配算法[J].计算机辅助设计与图形学学报,2010,22(2):286-291.
[82]HUANG C R, CHEN C R, CHUNG P C. Contrast context histogram—An efficientdiscriminating local descriptor for object recognition and image matching [J].Pattern Recognition,2008,41(10):3071-3077.
[83]刘萍萍,赵宏伟,臧雪柏等.移动机器人定位图像匹配的快速局部特征算法[J].仪器仪表学报,2009,30(8):1714-1719.
[84]刘萍萍,赵宏伟,臧雪柏等.一种快速局部特征描述算法[J].自动化学报,2010,36(1):40-45.
[85]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shapecontexts [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,2(4):509-522.
[86]Weijer JVD, Schmid C. Coloring local feature extraction[C]. In: the EuropeanConference on Computer Vision,2006.
[87]陈付幸.基于非定标图像序列的三维重建关键技术研究[D].长沙,国防科学技术大学,2005.
[88]Huiyu Zhou, Patrick R. Green, Andrew M. Wallace. Estimation of epipolargeometry by linear mixed-effect modelling[J]. Neurocomputing,2009,72(16-18):3881-3890.
[89]Onay Urfalioglu, Thorsten Thorm hlen, Hellward Broszio, et al. Algebraic erroranalysis of collinear feature points for camera parameter estimation[J]. ComputerVision and Image Understanding,2011,115(4):467-475.
[90]Sergiu Nedevschi, Catalin Golban, Cosmin Mitran. Improving Accuracy for EgoVehicle Motion Estimation using Epipolar Geometry[C]. Proceedings of the12thInternational IEEE Conference on Intelligent Transportation Systems, St. Louis,MO, USA,2009,596-602.
[91]Qi Li, Guangming Xing. New similarity measures of localities for a two-layermatching scheme and estimation of fundamental matrices [J]. Neurocomputing,2010,73(16-18):3114-3122.
[92]Armangue Xavier, Salvi Joaquim. Overall view regarding fundamental matrixestimation[J]. Image and Vision Computing,2003,21:205-220.
[93]Z. Zhang. Determining the epipolar geometry and its uncertainty: a review[J].International Journal of Computer Vision,1998,27(2):161-198.
[94]R. Hartley. In Defense of the Eight-Point Algorithm[J]. IEEE Transactions onPattern Recognition and Machine Intelligence,1997,19(6):580-593.
[95]陈泽志,吴成柯.一种高精度估计的基础矩阵的线性算法[J].软件学报,2002,13(4):840-845.
[96]H. Longuet-Higgins. A computer algorithm for reconstructing a scene from twoprojections[J]. Nature,1981,293:133-135.
[97]Faugeras, O. What can be seen in three dimensions with an uncalibrated stereorig[C]. In G. Sandini(ed.), Proceedings of the2nd European Conference onComputer Vision, Vol.588of Lecture Notes in Computer Science, Springer-Verlag,Santa Margherita Ligure, Italy,1992,563-578.
[98]R. Hartley. Estimation of relative camera position for uncalibrated cameras[C].European Conference on Computer Vision,1992,579-587.
[99]R. Hartley. In defence of the8-point algorithm[C]. Proceedings of the InternationalConference on Computer Vision, IEEE Computer Society Press, Boston,1995,1064-1070.
[100] Armangue Xavier, Salvi Joaquim. Overall view regarding fundamental matrixestimation[J]. Image and Vision Computing,2003,21:205-220.
[101] Q.-T. Luong, O.D. Faugeras. Determining the Fundamental matrix with planes:unstability and new algorithms[C]. In Proc. Conference on Computer Vision andPattern Recognition, New-York,1993,489-494.
[102] R. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision[M].Cambridge University Press, London,2000.
[103] M. Fischler, R.Bolles. Random sample consensus: A paradigm for model fittingwith applications to image analysis and automated cartography[J]. Communicationsof the ACM,1981,24,381-385.
[104]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(08):1431-1437.
[105] Tordoff Ben, Murray David W. Guided-MLESAC: faster image transformestimation by using matching priors[J]. IEEE Transaction on Pattern analysis andmachine intelligence,2005,27(10):1523-1535.
[106] P.H.S. Torr. Bayesian model estimation and selection for epipolar geometry andgeneric manifold fitting[J]. International Journal of Computer Vision.2002,50(1):35-61.
[107] Gonzalez R C, Woods R E. Digital image processing[M].阮秋琦,阮宇智译.北京:电子工业出版社,2003:176-197.
[108] Li Z H, Yang Y P, Jiang W. Multi-scale morphologic tracking approach for edgedetection[C]. The4th International Conference on image and Graphics, NY: IEEE,2007:358-362.
[109]王坤,高立群,郭丽等.多尺度结构元素的数学形态学边缘检测新方法[J].东北大学学报(自然科学版),2008,29(4):473-476.
[110]付永庆,王咏胜.一种基于数学形态学的灰度图像边缘检测算法[J].哈尔滨工程大学学报,2005,26(5):685-687.
[111]费浦生,王文波.基于小波增强的改进多尺度形态梯度边缘检测算法[J].武汉大学学报·信息科学版,2007,32(2):120-123.
[112]姜涌,曹杰,谢求成等.一种基于形态学梯度矢量和自适应模糊的目标边缘提取算法[J].武汉大学学报·信息科学版,2006,31(6):484-488.
[113]范立南,韩晓微,张广渊著.图像处理与模式识别[M].北京:科学出版社,2007.
[114] M. A. Schulze, J. A. Pearce. Linear combinations of morphological operators: themidrange pseudomedian, and LOCO-filters[C]. Proceedings of the1993IEEEInternational Conference on Acoustics, Speech, and Signal Processing,1993,57-60.
[115] Yanfeng Fan, Gang Cui, Fei Lei. Application of edge detection algorithm basedon morphology in robot vision system[C].2009International Conference onIntelligent Human-Machine Systems and Cybernetics,2009,2:304-307.
[116] J. Canny. A computational approach to edge detection[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1986, PAMI-8(6):679-698.
[117]吴福朝.计算机视觉中的数学方法[M].科学出版社,2008.
[118] Huimin Lu, Zhiqiang Zheng. Two novel real-time local visual features foromnidirectional vision[J]. Pattern Recognition,2010,43:3938-3949.
[119] ZHANG Zheng-you. A flexible new technique for camera calibration[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[120]向长波,刘太辉,宋建中.基本矩阵的鲁棒贪心估计算法[J].计算机辅助设计与图形学学报,2007,19(5):651-655.
[121]仲训昱,朱齐丹,张智.数字稳像中的快速和鲁棒运动估计研究[J].电子学报,2010,38(1):251-256.
[122] P.H.S. Torr, D.W. Murray. The development and comparison of robust methodsfor estimating the fundamental matrix[J]. International Journal of Computer Vision,1997,24(3):271-300.
[123] Sturm P, Triggs B. A Factorization Based Algorithm for Multi-image ProjectiveStructure and Motion[C]. Proceedings of the4th European Conference onComputer Vision. Cambridge, England,1996:709-720.
[124] Poelman C, Kanade T. A Paraperspective Factorization Method for Shape andMotion Recovery[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1997,19(3):580-593.
[125] Liu S, Zhao L, Li J, etc.. The Research of3D Reconstruction from UncalibratedImage Sequences Combined with3D Models[C]. Proceedings of2008Internationalconference on computer science and software engineering.2008:1117-1119.
[126] Micusik B, Kosecka J. Piecewise Planar City Modeling from Street ViewPanoramic Sequences[C]. In CVPR,2009:2906-2912.
[127] Pollefeys M et al. Detailed Real-time Urban3d Reconstruction from Video[J].IJCV,2008,78(2-3):143-167.
[2]段春梅.基于多视图的三维模型重建方法研究[D].济南,山东大学,2009.
[3]唐丽.由手提相机获得的序列图像进行三维重建[D].陕西,西安电子科技大学,2003.
[4]江泽涛.序列图象重建三维物体形状方法研究[D].西安,西北工业大学,2006.
[5] H.-Y. Shum, M. Han, R. Szeliski. Interactive Construction of3D Models fromPanoramic Mosaics[C]. In Proceedings of International Conference on ComputerVision and Pattern Recognition,1998,427-433.
[6] A. Criminisi, A. Zisserman. Single View Metrology[J]. International Journal ofComputer Vision,2000,40(2):123-148.
[7] L. Zhang, G. Dugas, Phocion, L.-S. Samson, S. M. Seitz. Single View Modeling ofFree-form Scenes[J]. Journal of Visualization and Computer Animation,2002,13(4):225-235.
[8] Li R, Sclaroff S. Multi-scale3D Scene Flow from Binocular Stereo Sequences[C].In Preceedings of the IEEE Workshop on Moton and Video Computing,2005:147-153.
[9] K. Kutulakos, S.M.Seitz. A Theory of Shape by Space Carving[J]. InternationalJournal of Computer Vision,2000,38(3):199-218.
[10]A. Broadhurst. A Probabilistic Framework for Spare Carving[D]. Ph.D. thesis,University of Cambfidge, UK,2001.
[11]刘钢,王锐,鲍虎军.一种可见外壳生成算法[J].软件学报,2002,13(9):1823-1829.
[12]Yang R, Pollefeys M, Welch G. Dealing with Textureless Regions and SpecularHighlights: A Progressive Space Carving Scheme using a Novel Photo-consistencyMeasure [C]. IEEE International Conference on Computer Vision, Piscataway, NJ,USA:2003,576-584.
[13]Y. Furukawa, J. Ponce. Carved Visual Hulls for Image-Based Modeling[C]. InProceedings of European Conference on Computer Vision,2006,1:564-577.
[14]S.Bougnoux, L.Roberto. TotalCalib: A Fast and Reliable System for Off-lineCalibration of Images Sequence[C]. In Proceedings of International Conference onComputer Vision and Pattern Recognition, Demo Session,1997.
[15]E. Poulin, M. Ouimet, M. C. Frasson. Interactively Modeling with Photogrammetry
[C]. In Proceedings of Eurographics Workshop on Rendering, Vienna, Austria,1998,93-104.
[16]Cipolla R, Robertson D P, Boyer E G. Photobuilder-3D Models of ArchitecturalScenes from Uncalibrated Images [C]. In Proc. IEEE International Conference onMultimedia Computing and Systems. Firenze,1999(1):25-31.
[17]D.Nister. Reconstruction from uncalibrated sequences with a hierarchy of trifocaltensors[C]. ln Proc. European Conference on Computer Vision(ECCV2000),2000,1:649-663.
[18]D.Nister. Calibration with robust use of cheirality by quasi-affine reconstruction ofthe set of camera projection centers[C]. In Proc. IEEE International Conference onComputerVision (ICCV2001),2001,2:116-123.
[19]D.Nister. Frame decimation for structure and motion[C]. In Proc.2nd Worrkshopon Structure from Multiple of Large Environments (SMILE2000), Springer LectureNotes on Computer Science,2001,2018:17-34.
[20]D.Nister. Automatic dense reconstruction from uncalibrated video sequences[D].PhD Thesis, Royal Institute of Technology KTH, Stockholm, Sweden,2001.
[21]R.Tsai, R. K. Lenz. A Technique for Fully Automomous and Efficient3D RoboticsHand/Eye Calibration[J]. IEEE Trans. Robotics and Automation,1989,5(3):345-358.
[22]W. Faig. Calibration of close-range photogrammetry systems: mathematicalformulation[J]. Photogrammetrie Engineering and Remote Sensing,1975,01(41):1479-1486.
[23]Hartley R. Self-calibration of stationary cameras[J]. International. Journal ofComputerVision,1997,22(1):5-23.
[24]李华,吴福朝,胡占义.一种新的线性摄像机自标定方法[J].计算机学报,2000,23(11):1121-1129.
[25]雷成,吴福朝,胡占义.一种新的基于主动视觉系统的摄像机自标定方法[J].计算机学报,2000,23(11):1130-1139.
[26]吴福朝,李华,胡占义.基于主动视觉的摄像机自标定方法研究[J].自动化学报,2001,27(6):736-746.
[27]吴福朝,胡占义.摄像机自定标的线性理论与算法[J].计算机学报,2001,24(9):1121-1135.
[28]Guanghui Wang, Q.M.Jonathan Wu, Wei Zhang. Kruppa equation based cameracalibration from homography induced by remote plane[J]. Pattern RecognitionLetters,2008,29:2137-2144.
[29]A. Habed, B. Boufama. Camera self-calibration from bivariate polynomials derivedfrom Kruppa’s equations[J]. Pattern Recognition,2008,41:2484-2492.
[30]S.Maybank, O.Faugeras. A theory of self-calibration of a moving camera[J].International Journal of Computer Vision,1992,8(2):123-151.
[31]O. Faugeras, Q. T. Luong, S. Maybank. Camera self-calibration: theory andexperiments[C]. In Proceedings of the2th European Conference on ComputerVision, Italy,1992,321-334.
[32]R. Hartley. Kruppa's Equations Derived from the Fundamental Matrix[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1997,19(2):133-135.
[33]M.1. Lourakis, R.Deriche. Camera Self-Calibration Using the Singular ValueDecomposition of the Fundamental Matrix: From Point Correspondences to3dMeasurements[J]. In4th Asian Conference on Computer Vision, Taibei, China,2000:403-408.
[34]C.Lei, F. Wu, Z. Hu, H.T. Tsui. A New Approach to Solving Kruppa Equations forCamera Se lf-Calibration[C]. In ICPR02, Quebec,2002,308-311.
[35]B.Triggs. Auto-calibration and the absolute quadric[C]. In Proceedings ofComputer Vision and Pattern Recognition,1997,609-614.
[36]R.Hartley. Euclidean reconstruction and invariants from multiple images[J]. IEEETrans. PAMI,1994,16(10):1036-1041.
[37]M.Pollefeys, L.V.Gool, A.Oosterlinck. The modulus constraint: a new constraintfor self-calibration[C]. In Proceedings of International Conference of PatternRecognition, Vienna,1996,349-353.
[38]吴福朝,王光辉,胡占义.由矩形确定相机内参数与位置的线性方法[J].软件学报,2003,14(3):703-712.
[39]全红艳,张天文.一种新的利用模板进行相机自标定的方法[J].电子学报,2005,33(11):1941-1945.
[40]王年,梁栋,范益政等.一种基于矩形的相机自标定方法[J].中国科学技术大学学报,2005,35(5):693-700.
[41]Lazaros Grammatikopoulos, George Karras, Elli Petsa. An automatic approach forcamera calibration from vanishing points[J]. Photogrammetry&Remote Sensing,2007,62:64-76.
[42]B.W. He, Y.F. Li. Camera calibration from vanishing points in a vision system[J].Optics&Laser Technology,2008,40:555-561.
[43]Wang G., Tsui H.T., Hu Z. Reconstruction of structured scenes from twouncalibrated images[J]. Pattern Recognition Lett.2005,26(2):207-220.
[44]M.Wilczkowiak, E.Boyer, P. Sturm.3d Modelling Using Geometric Constraints: AParallelepiped Based Approach[C]. In Proceedings of the7th European Conferenceon Computer Vision, Copenhagen, Denmark: Springer-Verlag,2002,221-236.
[45]E Schaffalitzky, A.Zissermam. Multi-view Matching for Unordered Imsge Sets, or“How Do I Organise My Holiday Snaps?”[C]. In Proceedings of EuropeanConference on Computer Vision, Copeahaguen,2002,1:414-431.
[46]陈夏艳,伍先达.基于距离特征的自适应阈值视频拼接算法[J].模式识别与人工智能,2010,23(5):727-730.
[47]Lee L, Ko H. Gradient-based local affine invariant feature extraction for mobilerobot localization in indoor environments[J]. Pattern Recognition Letters,2008,29(14):1934-1940.
[48]Dongjoe Shin, Tardi Tjahjadi. Clique Descriptor of Affine Invariant Regions forRobust Wide Baseline Image Matching[J]. Pattern Recognition,2010,43:3261-3272.
[49]Loris Nanni, Alessandra Lumini, Sheryl Brahnam. Local binary patterns variants astexture descriptors for medical image analysis[J]. Artificial Intelligence in Medicine,2010,49:117-125
[50]杨恒,王庆.一种新的局部不变特征检测和描述算法[J].计算机学报,2010,33(5):935-944.
[51]Yang Duan-duan, Sluzek Andrzej. A low-dimensional local descriptorincorporating TPS warping for image matching[J]. Image and Vision Computing.2010,28:1184-1195.
[52]H.Wang, M.Brady. Real-time corner detection algorithm for motion estimation[J].Image and Vision Computing,1995,13(9):695-703
[53]Mokhtarian F, Suomela R. Robust image corner detection through curvature scalespace[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(12):1376-1381
[54]He X C, Yung N H C. Curvature scale space corner detector with adaptivethreshold and dynamic region of support[C]. In: Proceedings of the17thInternational Conference on Pattern Recognition. Washington D.C., USA: IEEE,2004,791-794.
[55]Zhang X H, Lei M, Yang D, Wang Y Z et al. Multi-scale curvature product forrobust image corner detection in curvature scale space[J]. Pattern RecognitionLetters,2007,28(5):545-554.
[56]Moravec H. Towards automatic visual obstacle avoidance[C]. In: Proceedings oftheInternational Joint Conference on Artificial Intelligence.1977.
[57]C. Harris, M. Stephens. A Combined Corner and Edge Detector[C]. Proc. FourthAlvey Vision Conference,1988,189-192.
[58]Dufournaud Y, Schmid C, Horaud R. Matching images with different resolutions[C]Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Hilton Head Island, South Carolina,2000,612-618.
[59]Mikolajczyk K, Schmid C. Indexing based on scale invariant interest points[C].Proceedings of the8th International Conference on Computer Vision, Vancouer,Canda,2001,525-531.
[60]Mikolajczyk K, Schmid C. An affine invariant interest point detector[C].Proceedings of the7th European Conference on Computer Vision, Copenhagen,Denmark,2002,128-142.
[61]Mikolajczyk K, Schmid C. Scale&affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86
[62]Lindeberg T. Feature detection with automatic scale selection[J]. InternationalJournal of Computer Vision,1998,30(2):79-116
[63]Lowe D G. Distinctive image features from scale invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110
[64]Bay H, Tuytelaars T, Gool L V. SURF: Speeded up robust features[C].Proceedings of the9th European Conference on Computer Vision, Graz, Austria,2006:404-417
[65]Tuytelaars T, Gool LV. Matching widely separated views based on affine invariantregions[J]. International Journal of Computer Vision,2004,59(1):61-85.
[66]Matas J, Chum O, Urban M, Pajdla T. Robust wide-baseline stereo from maximallystable extremal regions[C]. In Proceedings of the British Machine VisionConference,2002.
[67]Tuytelaars T, Mikolajczyk K. Local invariant feature detectors: a survey[J].Foundations and Trends in Computer Graphics andVision,2007,3(3):177-280.
[68]T.Lee. Image Representation Using2-D Gabor Wavelets[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1996,18(10):959-971.
[69]Florack L, Romeny BtH, Koenderink J, Viergever M. General intensitytransformations and second order invariants[C]. In the7th ScandinavianConference on Image Analysis, Aalborg, Denmark,1991.
[70]Baumberg A. Reliable feature matching across widely separated views [C].Proceedings of International Conference on Computer Vision and PatternRecognition. New York, USA: ACM Press,2000,774-781.
[71]Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets [C].Proceedings of the7th European Conference on Computer Vision, Cambridge, MA,USA: MIT Press,2002,414-431.
[72]Leung T, Malik J. Representing and recognizing the visual appearance of materialsusing three-dimensional textons[J]. International Journal of Computer Vision,2001,43(1):29-44.
[73]Varma M, Zisserman A. Classifying images of materials: achieving viewpoint andillumination independence[C]. In: Proceedings of the European Conference onComputer Vision,2002.
[74]Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[75]Li J, Allinson N M. A comprehensive review of current local features for computervision[J]. Neurocomputing,2008,71(10-12):1771-1787.
[76]Lazebnik S, Schmid C, Ponce J. Sparse texture representation using affine-invariantneighborhoods[C]. Proc. Conf. Computer Vision and Pattern Recognition,2003:319-324.
[77]F.C. Wu, Z.H.Wang, X.G.Wang. Feature Vector Field and Feature Matching[J].Pattern Recognition,2010,43:3273-3281.
[78]王旭光,王志衡,吴福朝. Harris相关与特征匹配[J].模式识别与人工智能,2009,22(4):505-513.
[79]Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotationinvariant texture classification with local binary patterns[J]．IEEE Transactions onPattern Analysis and Machine Intelligence,2002,24(7):971-987.
[80]M. Heikkila, M. Pietikainen, C. Schmid. Description of interest regions with localbinary patterns[J]. Pattern Recognition,2009,42(3):425-436.
[81]郑永斌,黄新生,丰松江. SIFT和LBP相结合的图像匹配算法[J].计算机辅助设计与图形学学报,2010,22(2):286-291.
[82]HUANG C R, CHEN C R, CHUNG P C. Contrast context histogram—An efficientdiscriminating local descriptor for object recognition and image matching [J].Pattern Recognition,2008,41(10):3071-3077.
[83]刘萍萍,赵宏伟,臧雪柏等.移动机器人定位图像匹配的快速局部特征算法[J].仪器仪表学报,2009,30(8):1714-1719.
[84]刘萍萍,赵宏伟,臧雪柏等.一种快速局部特征描述算法[J].自动化学报,2010,36(1):40-45.
[85]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shapecontexts [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,2(4):509-522.
[86]Weijer JVD, Schmid C. Coloring local feature extraction[C]. In: the EuropeanConference on Computer Vision,2006.
[87]陈付幸.基于非定标图像序列的三维重建关键技术研究[D].长沙,国防科学技术大学,2005.
[88]Huiyu Zhou, Patrick R. Green, Andrew M. Wallace. Estimation of epipolargeometry by linear mixed-effect modelling[J]. Neurocomputing,2009,72(16-18):3881-3890.
[89]Onay Urfalioglu, Thorsten Thorm hlen, Hellward Broszio, et al. Algebraic erroranalysis of collinear feature points for camera parameter estimation[J]. ComputerVision and Image Understanding,2011,115(4):467-475.
[90]Sergiu Nedevschi, Catalin Golban, Cosmin Mitran. Improving Accuracy for EgoVehicle Motion Estimation using Epipolar Geometry[C]. Proceedings of the12thInternational IEEE Conference on Intelligent Transportation Systems, St. Louis,MO, USA,2009,596-602.
[91]Qi Li, Guangming Xing. New similarity measures of localities for a two-layermatching scheme and estimation of fundamental matrices [J]. Neurocomputing,2010,73(16-18):3114-3122.
[92]Armangue Xavier, Salvi Joaquim. Overall view regarding fundamental matrixestimation[J]. Image and Vision Computing,2003,21:205-220.
[93]Z. Zhang. Determining the epipolar geometry and its uncertainty: a review[J].International Journal of Computer Vision,1998,27(2):161-198.
[94]R. Hartley. In Defense of the Eight-Point Algorithm[J]. IEEE Transactions onPattern Recognition and Machine Intelligence,1997,19(6):580-593.
[95]陈泽志,吴成柯.一种高精度估计的基础矩阵的线性算法[J].软件学报,2002,13(4):840-845.
[96]H. Longuet-Higgins. A computer algorithm for reconstructing a scene from twoprojections[J]. Nature,1981,293:133-135.
[97]Faugeras, O. What can be seen in three dimensions with an uncalibrated stereorig[C]. In G. Sandini(ed.), Proceedings of the2nd European Conference onComputer Vision, Vol.588of Lecture Notes in Computer Science, Springer-Verlag,Santa Margherita Ligure, Italy,1992,563-578.
[98]R. Hartley. Estimation of relative camera position for uncalibrated cameras[C].European Conference on Computer Vision,1992,579-587.
[99]R. Hartley. In defence of the8-point algorithm[C]. Proceedings of the InternationalConference on Computer Vision, IEEE Computer Society Press, Boston,1995,1064-1070.
[100] Armangue Xavier, Salvi Joaquim. Overall view regarding fundamental matrixestimation[J]. Image and Vision Computing,2003,21:205-220.
[101] Q.-T. Luong, O.D. Faugeras. Determining the Fundamental matrix with planes:unstability and new algorithms[C]. In Proc. Conference on Computer Vision andPattern Recognition, New-York,1993,489-494.
[102] R. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision[M].Cambridge University Press, London,2000.
[103] M. Fischler, R.Bolles. Random sample consensus: A paradigm for model fittingwith applications to image analysis and automated cartography[J]. Communicationsof the ACM,1981,24,381-385.
[104]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(08):1431-1437.
[105] Tordoff Ben, Murray David W. Guided-MLESAC: faster image transformestimation by using matching priors[J]. IEEE Transaction on Pattern analysis andmachine intelligence,2005,27(10):1523-1535.
[106] P.H.S. Torr. Bayesian model estimation and selection for epipolar geometry andgeneric manifold fitting[J]. International Journal of Computer Vision.2002,50(1):35-61.
[107] Gonzalez R C, Woods R E. Digital image processing[M].阮秋琦,阮宇智译.北京:电子工业出版社,2003:176-197.
[108] Li Z H, Yang Y P, Jiang W. Multi-scale morphologic tracking approach for edgedetection[C]. The4th International Conference on image and Graphics, NY: IEEE,2007:358-362.
[109]王坤,高立群,郭丽等.多尺度结构元素的数学形态学边缘检测新方法[J].东北大学学报(自然科学版),2008,29(4):473-476.
[110]付永庆,王咏胜.一种基于数学形态学的灰度图像边缘检测算法[J].哈尔滨工程大学学报,2005,26(5):685-687.
[111]费浦生,王文波.基于小波增强的改进多尺度形态梯度边缘检测算法[J].武汉大学学报·信息科学版,2007,32(2):120-123.
[112]姜涌,曹杰,谢求成等.一种基于形态学梯度矢量和自适应模糊的目标边缘提取算法[J].武汉大学学报·信息科学版,2006,31(6):484-488.
[113]范立南,韩晓微,张广渊著.图像处理与模式识别[M].北京:科学出版社,2007.
[114] M. A. Schulze, J. A. Pearce. Linear combinations of morphological operators: themidrange pseudomedian, and LOCO-filters[C]. Proceedings of the1993IEEEInternational Conference on Acoustics, Speech, and Signal Processing,1993,57-60.
[115] Yanfeng Fan, Gang Cui, Fei Lei. Application of edge detection algorithm basedon morphology in robot vision system[C].2009International Conference onIntelligent Human-Machine Systems and Cybernetics,2009,2:304-307.
[116] J. Canny. A computational approach to edge detection[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1986, PAMI-8(6):679-698.
[117]吴福朝.计算机视觉中的数学方法[M].科学出版社,2008.
[118] Huimin Lu, Zhiqiang Zheng. Two novel real-time local visual features foromnidirectional vision[J]. Pattern Recognition,2010,43:3938-3949.
[119] ZHANG Zheng-you. A flexible new technique for camera calibration[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[120]向长波,刘太辉,宋建中.基本矩阵的鲁棒贪心估计算法[J].计算机辅助设计与图形学学报,2007,19(5):651-655.
[121]仲训昱,朱齐丹,张智.数字稳像中的快速和鲁棒运动估计研究[J].电子学报,2010,38(1):251-256.
[122] P.H.S. Torr, D.W. Murray. The development and comparison of robust methodsfor estimating the fundamental matrix[J]. International Journal of Computer Vision,1997,24(3):271-300.
[123] Sturm P, Triggs B. A Factorization Based Algorithm for Multi-image ProjectiveStructure and Motion[C]. Proceedings of the4th European Conference onComputer Vision. Cambridge, England,1996:709-720.
[124] Poelman C, Kanade T. A Paraperspective Factorization Method for Shape andMotion Recovery[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1997,19(3):580-593.
[125] Liu S, Zhao L, Li J, etc.. The Research of3D Reconstruction from UncalibratedImage Sequences Combined with3D Models[C]. Proceedings of2008Internationalconference on computer science and software engineering.2008:1117-1119.
[126] Micusik B, Kosecka J. Piecewise Planar City Modeling from Street ViewPanoramic Sequences[C]. In CVPR,2009:2906-2912.
[127] Pollefeys M et al. Detailed Real-time Urban3d Reconstruction from Video[J].IJCV,2008,78(2-3):143-167.