摘要
运动图像分析是计算机视觉中的一项重要任务，其中的关键技术之一就是光流计算。光流不仅携带了被观察物体的运动信息，还携带有被观察物的三维结构，传感器参数，非刚性物体的局部弹性形变，甚至流体运动的矢量结构特征等丰富信息。通过光流我们可以了解物体许多重要的运动特性，在运动图像计算与分析中光流扮演着非常重要的角色。
本文针对目前光流场计算与分析中存在的问题和不足，深入系统地进行了研究并取得了一定的成果，其中包括：对传统光流方程进行了改进；提出了解决运动边界问题的新思路和新方法；研究了基于光流的流体运动图像计算和分析方法；为了提高运动矢量特征描述的精度和可靠性，提出了基于时间关联约束的Multivector图像滤波方法；研究了基于光流场的序列图像运动特征描述；本文的成果对改善光流计算的精度和可靠性，克服光流场计算中存在的问题具有重要意义。对运动图像计算、分析领域的研究具有较高理论价值和应用价值。
第一章论述了光流计算的研究意义，研究现状和存在问题，并介绍了本文的主要工作，以及论文内容安排。
第二章为了减少光流方程的模型误差和改进计算的鲁棒性，论文提出了一种新的基于图像局部结构不变模型(LSCM)的光流计算方法。由于模型LSCM较传统的亮度常数模型(BCM)对于图像的光照变化不敏感，因此本文方法可以显著提高光流计算的鲁棒性。在本文方法中使用图像局部二阶张量来描述图像的局部结构特征。同时为了进一步提高计算精度，减少由于Taylor级数一阶近似所带来的模型误差，本文给出了一种双向运动计算策略。新策略既具有二阶Taylor级数展开的精度逼近，同时又避免了非线性方程的计算。
第三章针对如何解决运动边界问题，本文提出了两种新的解决问题的思想。第一种思想采用概率选择策略来有效地解决不同运动区域的划分，同时结合局部更新计算来降低运动边界带来的干扰，以此提高运动边界处光流计算的精度。第二种思想从光流全局计算出发，直接通过非线性扩散反应方程来计算光流，这样避开了光流计算正则化方法中凸性和可微性的要求。同时本文分别设计了一致矢量增强扩散(CVED)和基于非线性滤波的扩散方式，来提高模型处理运动边界问题的能力。
第四章研究了基于光流方法的流体运动图像计算(PIV)，将第三章基于非线性滤波的光流方法进行推广，并应用于流体运动图像。此外，本章将信号分析中最小均方滤波的思想应用于矢量场滤波，提出一种基于时间关联约束的滤波策略，实现对原有运动矢量的滤波和增强。考虑到流体运动矢量的散度(div)和旋度(curl)也是重要的计算和分析对象。为此本文借助Clifford代数将运动矢量、散度(div)和旋度(curl)构建成一多矢量(Multivector)，作为流体运动矢量特征的综合描述。通过Multivector滤波计算得到更加可靠的流体运动特征描述结果。
第五章研究了基于光流场的序列图像运动特征描述。由于光流场的分辨率可以达到连续两帧的每一个像素，因此光流场为利用统计的方法进行图像运动特征描述提供了大量的冗余信息。文章在光流计算的基础上，研究了基于光流加速场统计信息的视频运动识别方法。给出了一种基于运动加速场的时空多分辨直方图(STMRH)，并利用STMRH进行动态纹理的运动特征辨识。为了提高算法的计算速度，论文还给出了一种简化的多网格快速光流计算方法。
第六章对论文的工作和成果进行了总结和评述，同时简要给出了进一步的研究内容和方向。
Motion image analysis is an important task of Computer Vision, and the optical flow computation is a key technique for motion image analysis. The optical flow is a convenient and useful image motion description, it contains rich 2D motion cues and is often used to recover 3D scene structure and 3D motion parameters of visual sensors. It also contains some important cues of elastic deformation of non-rigid bodies, and flow structure of fluid motion images. It can help us to know about many important motion characteristics of motion bodies by optical flow, It is undoubted that optical flow plays an important role in motion image computation and analysis.
This thesis addresses some problems of optical flow computation and analysis including: increase the accuracy of optical flow computation, cope with the problems of motion boundary, propose a optical flow method for fluid motion image computation, give a vector filter based on temporal correlation constraints for the more accurate and reliable description of fluid motion characteristics, and analyze the motion patterns of video sequences by optical flow statistic. This research is significant for increasing the accuracy and reliability of optical flow computation, and it also has significant academic and practical value for motion images computation and analysis.
The first chapter systematically introduces the background , the significance and the state of the art of optical flow computation, and indicates the limitations of traditional methods. This chapter also gives the structure and the contributions of this dissertation.
In chapter 2, we propose a new optical flow method based on Local Structure Constancy Model (LSCM) instead of the traditional BCM for reducing the model error and increasing the robustness. Local image structure is less sensitive to illumination variation than intensity, which can increase the robustness of optical flow computation in real applications. Here we use two order structure tensors of an image to describe its local structure. A bi-directional computation scheme based on LSCM is also adopted for reducing the model error resulted from the linear Taylor's expansion, which allows two order Taylor's expansion of optical flow equation for a more accurate approximation and avoids nonlinear equation calculation.
Chapter 3 addresses the issue of motion boundary problems to which two ideas are introduced. First, a probability-control selecting scheme is adopted, which divides the local neighbor into different regions with consistent motion vector. By a local refining step, the new method can preserve motion boundaries efficiently; Second, we view optical flow computation as a nonlinear diffusion process instead of an energy minimization process. It avoids the restrictions of convexity and differentiability required by normal regularization methods. We use a Coherence Vector Enhancing Diffusion (CVED) scheme and a bilateral filtering diffusion scheme to improve the efficiency of preserving motion boundaries, respectively.
In chapter 4, an optical flow method based on nonlinear filtering scheme is proposed which is the extended version of the method based on bilateral filtering scheme proposed in chapter 3 and is applied to fluid motion images computation (PIV). In addition, a Least-squares (LS) vector-filtering scheme based on temporal correlation constraint is proposed for offline computation & analysis, which can help to suppress the computation noise and increase the reliability of fluid motion characteristics' description. In view of the div and curl fields as the main objects of computation & analysis, we extend the proposed vector-filtering scheme to multivector space, which takes into account div and curl along with motion vectors. With the help of Clifford algebra, we construct multivectors by vectors, div and curl to characterize fluid motion. By a multivector filtering computation, we obtain the reliable description of fluid motion characteristics.
The fifth chapter of the thesis is concerned with video motion analysis based on optical flow computation. From optical flow fields we can obtain the motion vector of each pixel per frame, which provides richly redundant information for statistic methods acting on optical flow fields. In this chapter we develop a statistics method for motion recognition based on motion accelerate fields. A spatio-temporal multiresolution histogram (STMRH) acting on motion accelerate fields as the motion character's description of dynamic texture videos is proposed. In order to reduce computational consumption, a simplified multigrid computation scheme for optical flow is adopted.
The final chapter gives the conclusion and the contributions of this dissertation, and indicates some related works that are yet remained and attractive for future research.
引文
[1] B. Horn and B. Schunck. "Determining optical flow, " Artificial Intelligence, 1981, 17: 185-203.
[2] B. Lucas and T. Kanade. "An iterative image registration technique with an application to stereo vision, " In Proc. Seventh International Joint Conference on Artificial Intelligence, Vancouver, Canada, Aug. 1981, 674-679.
[3] J. L. Barron, D. J. Fleet, and S. S. Beauchemin, "System and experiment performance of optical flow techniques, " International Journal of Computer Vision, 1994, 12(1): 43-77.
[4] A. Singh, "Optic Flow Computation: A unified Perspective, " IEEE Computer Society Press, California, 1991. 1-st Edition.
[5] B. Jahne, "Digital Image Processing-Concepts, Algorithms, and Scientific Applications, " Springer-Verlag, 1995. 3-st Edition.
[6] P. Anadan, "A computational framework and an algorithm for the measurement of visual motion", International Journal of Computer Vision, 1989, 2: 283-310.
[7] L. Alvarez, J. Weickert, and J. Sanchez. "Reliable estimation of dense optical flow fields with large displacements". International Journal of Computer Vision, Aug. 2000, 39(1): 41-56.
[8] F. Lauze, P. Kornprobst and E. Memim, "A coarse to fine multiscale approach for linear least squares optical flow estimation, " Proceedings of the British Machine Vision Conference, Kingston University, U. K., Sep 2004, 767-776.
[9] M. J. Black and D. J. Fleet, "Probabilistic detection and tracking of motion boundaries, " International Journal of Computer Vision, 2000, 38(3): 231-245.
[10] A. Bab-Hadiashar and D. Suter, "Robust Optical Flow Estimation, " Int'l J. Computer Vision, 1998, 29(1): 59-77.
[11] E. Memin and P. Perez, "Dense estimation and object-based segmentation of the optical flow with robust techniques, " IEEE Trans. Image Processing, 1998, 7(5): 703-719.
[12] F. J. Hampson and J. C. Pesquet, "Motion estimation in the presence of illumination variations, " Signal Processing: Image Communication, 2000, 16: 373-381.
[13] S. H. Lai, "Adaptive motion estimation for image sequences under non-uniform illumination variations, " in Proceedings International Computer Symposium: Workshop on Image Processing and Pattern Recognition, (Chiayi, Taiwan), 2000, 223-230.
[14] S. H. Lai and M. Fang, "Robust and efficient image aliment with spatially varying illumination models, " in Proc. IEEE Conference on Computer Vision and Pattern Recognition, 1999, 2: 167-172.
[15] A. Nomura, "Spatio-temporal optimization method for determining motion vectors fields under non-stationary illuminations, " Image and Vision Computing, 2000, 18: 939-950.
[16] L. Zhang, T. Sakurai, and H. Miike, "Detection of motion fields under spatio-temporal non-uniform illuminations, " Image and Vision Computing, 1999, 17: 309-320.
[17] H. W. Haussecker and D. J. Fleet, "Computing optical flow with physical models of brightness variation, " IEEE Trans. Pattern Anal. Machine Intell, 2001, 23(6): 661-673.
[18] 裴继红，卢宗庆，谢维信，基于图像梯度场序列的双向GDIM光流计算方法，电子学报(已录用)。
[19] Zongqing Lu, Weixin Xie, Jihong Pei, "A Robust Optical Flow Estimation under Varying Illumination, " International Journal of Information Acquisition, 2005, 2(4): 1-11.
[20] S. Negahdaripour and C. H. Yu, "A generalized brightness change model for computing optical flow, " In Proceedings International Conference on Computer Vision, Germany, 1993, 2-11.
[21] K. P. Lim, A. Das and M. N. Chong, "Estimation of Occlusion and Dense Motion Fields in a Bidirectional Bayesian Framework, " IEEE Trans. Patter Anal. Machine Intell. 2002, 24(5): 712-718.
[22] Yosi Keller and Amir Averbuch, "Fast motion estimation using bidirectional gradient methods, " in Proc. IEEE Trans. Image Processing, Aug 2004, 13(8): 1042-105.
[23] D. J. Fleet and A. D. Jepson, "Computation of Component Image Velocity from Local Phase Information", International Journal of Computer Vision, 1990, 5(1): 77-104.
[24] M. Nicolescu and G. Medioni, "Layered 4D Representation and Voting for Grouping from Motion, " IEEE Transections On Pattern Analysis And Machine Intelligent, April 2003, 25(4): 492-501.
[25] M. Andersson and H. Knutsson, "Transformation of local spatio-temporal structure tensor fields, " IEEE ICASSP 2003, 285-288(Ⅱ).
[26] C. Pierpaoli, P. Jezzard, P. J. Basser, A. Barnett, G. Di Chiro. "Diffusion tensor MR imaging of the human brain, " Radiology, Dec. 1996, 201(3): 637-648.
[27] H. Liu, R. Chellappa, and A. Rosenfeld, "Accurate dense optical flow estimation using adaptive structure tensors and a parametric model, " in Proc. IEEE Trans. Image Processing, Oct 2003, 12(10): 1170-1179.
[28] D. Gibson and M. Spann, "Robust optical flow estimation based on a sparse motion trajectory set, " in Proc. IEEE Trans. Image Processing, April 2003, 12(4): 431-445.
[29] G. Farnebaick, "Fast and accurate motion estimation using orientation tensors and parametric motion models, " in Proc. Int. Conf. Pattern Recognition, 2000, 1: 135-139.
[30] A. Bruhn, J. Weickert, and C. Schn6rr. "Lucas/Kanade meets Horn/Schunck: Combining local and global optical flow methods, " International Journal of Computer Vision vol, 2005, 61 (3): 211-231.
[31] D. M. Young. Iterative Solution of Large Linear Systems. Academic Press, New York, 1971.
[32] C. Feddern, J. Weickert and B. Burgeth, "Level-Set Methods for Tensor-Valued Images". In Proc. Second IEEE Workshop on Variational, Geometric and Level Set. Methods in Computer Vision, Nice, France, 2003, 65-2.
[33] 伍鸿熙，沈纯理，虞言林著，黎曼几何初步，北京大学出版社，1989。
[34] Jorgen Karlholm, Local Signal Models for Image Sequence Analysis, PhD Dissertation, Dept. Electrical Engineering, Linkoping University, ISBN 91-7219-220-8, ISSN 0345-7524, Linkoping, Sweden, 1998.
[35] S. H. Lai, "Computation of optical flow under non-uniform brightness variations, " Pattern Recognition Letters, 2004, 25: 885-892.
[36] T. Corpetti, E. Memin, and P. Perez. "Dense Estimation of Fluid Flows, " In PAMI, 2002, 24(3): 365-380.
[37] K. Daniilidis and V. Kruger, "Optical flow computation in Log-Polar plane, " Proceedings of the 6th International Conference on Computer Analysis of Images and Patterns, 1995, 65-72.
[38] M. Yeasin, "Optical flow in Log-Mapped image plane-a new approach, " IEEE. Trans on PAMI, 2002, 24(1): 125-131.
[39] 马颂德，张正友，计算机视觉，科学出版社，2001。
[40] David Tschumperle, PDE's Based Regularization of Multivalued Images and Applications, PhD, Odyssee Lab/INRIA/ENPC/ENS-13, France, Dec 2002.
[41]J. Weickert, Anisotropic Diffusion in Image Processing, PhD, Teubner-Verlag,Stuttgart, 1996.
[42] B. M. ter Haar Romeny (Ed.), Geometry-driven diffusion in computer vision,Kluwer, Dordrecht, 1994.
[43] A. R. Rao, B. G. Schunck, "Computing oriented texture fields," CVGIP: Graphical Models and Image Processing, 1991, 53:157-185.
[44] C. Ballester Nicolau, An affine invariant model for image segmentation:Mathematical analysis and applications, Ph.D. thesis, University of Illes Baleares,Palma de Mallorca, Spain, 1995.
[45] M. Nitzberg, D. Mumford, T. Shiota, Filtering, segmentation and depth, Lecture Notes in Computer. Science, vol. 662, Springer, Berlin, 1993.
[46] M. Nitzberg, T. Shiota, "Nonlinear image filtering with edge and corner enhancement," IEEE Trans. Pattern Anal. Mach. Intell, 1992, 14(8):826-833.
[47] D. Barash, D. Comaniciu, "A common framework for nonlinear diffusion, adaptive smoothing, bilateral filtering and mean shift," Image and Video Computing, 2003,22(1):73-81.
[48] T. Brox, A. Bruhn, N. Papenberg, and J. Weickert, "High accuracy optic flow estimation based on a theory for warping," In T. pajdla and J. matas, editors,Computer Vision-ECCV 2004, Prague, Lecture Notes in Computer Science, 2004,3024:25-36.
[49] C. Schnorr, "On functionals with greyvalue-controlled smoothness terms for determining optical flow," IEEE Trans. Pattern Anal. Mach. Intell, Oct 1993,15:1074-1079.
[50] J. Weickert and C. Schnorr. "A theoretical framework for convex regularizes in PDE-based computation of image motion," International Journal of Computer Vision, Dec 2001,45(3):245-264.
[51] A. Bruhn and J. Weickert, "Towards ultimate motion estimation: Combining highest accuracy with real-time performance," Proc. International Conference on Computer Vision, Beijing, China, 2005, 794-755.
[52] Zongqing Lu, Weixin Xie and JiHongPei."Dense Optical Flow Computation Based on Bayesian Selecting Scheme," Chinese Journal of Electronics, 2007, 16(1):107-110.
[53] Zongqing Lu, Weixin Xie and JiHongPei."An Optical Flow Computation Based On Nonlinear Diffusing," Chinese Journal of Electronics, 2007,2(16):267-270.
[54] C. Tomasi and R. Manduchi, "Bilateral Filtering for Gray and Color Images,"Proceedings of the IEEE International Conference on Computer Vision, Bombay,India, 1998,839-846.
[55] JiHong Pei, Zongqing Lu and Weixinxie."A Method For IR Point Target Detection Based On Spatial-temporal Bilateral Filter," International Conference on Pattern Recognition (ICPR 2006), HongKong, 2006.
[56] T. Corpetti, D. Heitz, G Arroyo, E. Memin and A. Santa-Cruz, "Fluid experimental flow estimation based on an optical-flow scheme," Experiments in Fluids, 2005.
[57] M. Raffel, C. willert, and J. kompenhans, Particle Image Velocimetry. Springer,2nd edition, 2001.
[58] L. Gui, S. T. Wereley. "A correlation-based continuous window-shift technique to reduce the peak-locking effect in digital PIV image evaluation", Experiments in Fluids, Springer-Verlag, 2002, 32:506-517.
[59] Lourenco L, Krothapalli. "A True resolution piv: a mesh-free second-order accurate algoritm", In the 1 Oth International symposium on applications of laser techniques in fluid mechanics, Lisbon, Portugal, July 2000.
[60] Mark P. Wernet, "Fuzzy Logic Particle Tracking Velocimetry," SPIE Conference on Optical Diagnostics in Fluid and Thermal Flow, San Diego, 1993, (NASA TM 106194).
[61] G M. Quenot, J. Pakleza, T. A. Kowalewski, "Particle image velocimetry with optical flow," Experiments in Fluids, 1998,25:177-189.
[62] R. Okuda, Y. Sugii and K. Okamoto, "Velocity Measurement of Blood Flow in a Microtube Using Micro PIV System," Proceedings of PSFVIP-4, Chamonix, France, June, 2003,4:3-5.
[63] P. Ruhnau, C. Guetter, T. Putze and C. Schnorr, "A variational approach for particle tracking velocimetry," Meas. Sci. Technol, 2005. 16:1449-1458.
[64] T. Kohlberger, E. Memin, C. Schnorr, "Variational dense motion estimation using the Helmholtz decomposition," In: Scale Space Methods in Computer Vision.Berlin: Springer, 2003, S. 432-448.
[65] S. H. Lim, J. G Apostolopoulos and A. E. Gamal, "Optical flow estimation using temporally oversampled video," IEEE Transactions on Image Processing, August,2005, 14(8): 1074-1087.
[66] S. H. Lim, "Video processing applications of high speed CMOS image sensors,"Ph.D. Dissertation, Dept. Elect. Eng. Comp. Sci., Stanford Univ., Stanford, CA, Mar, 2003.
[67] A. M. Moya, V. V. Fernandez and W. A. Rodrigues Jr, "Multi Functions of a Real Variable", Advances in Applied Clifford Algebras 11(S3), pp. 69-77, 2001.
[68] J. Ebling and G. Scheuermann, "Clifford Fourier Transform on Vector Fields, " IEEE Transactions on Visualization and Computer Graphics, July/August, 2005, 11(4): 469-479.
[69] M. Felsberg and G. Sommer. "Structure multivector for local analysis of images". Technical Report Number 2001, Christian-Albrechts-University at zu Kiel, Institutfur Informatik und Praktische Mathematik, February 2000.
[70] D. Hestenes, etc. Geometric computing with Clifford algebras: theoretical foundations and applications in computer vision and robotics. Publisher: Springer-Verlag, London, UK, 2001. ISBN: 3-540-41198-4.
[71] A. Lasenby, Chris Doran and Stephen Gull, "A Multivector Derivative Approach to Lagrangian Field Theory, " Found. Phys, 1993. 23(10): 1329-1356.
[72] T. Billow, "Hypercomplex Spectral Signal Representations for the Processing and Analysis of Images, " Ph. D. Dissertation, Institute For Information And Practical Mathematics. Christian-Albrechts Univ., Kiel, Germany, Aug, 1993.
[73] F. Brackx, R. Delanghe, and F. Sommen, Clifford Analysis, Vol. 76 of Research Notes in Mathematics, Pitman Advanced Publishing Program, 1982.
[74] 王兴国，刘济林，顾伟康，“流场可视化中的运动矢量估计方法”，电子学报，1999，27(2)：99-102。
[75] T. Corpetti, E. Memin, and P. Perez. "Estimating Fluid Optical Flow, " In Proc. International Conf. on Pattern Recognition, 2000, 3: 1045-1048.
[76] M. Oishi, M. Oshima and T. Kobayashi, "High-speed PIV Measurement of Blood Flow in the Modeled Artery, " Proceedings of PSFVIP-4, Chamonix, France, June, 2003, 4: 3-5.
[77] C. D. Meinhart, S. T. Wereley, J. G. Santiago, "PIV measurements of a microchannel flow, " Experiments in Fluids, Springer-Verlag, 1999, 27: 414-419.
[78] L. Hesselink, "Digital image processing in flow visualization, " Ann Rev Fluid Mech vol, 1998, 20: 421-485.
[79] C. E. Willert, M. Gharib, "Digital particle image velocimetry, " Exp Fluids vol, 1991, 10: 181-193.
[80] J. Westerweel, Digital particle image velocimetry-theory and application, Delft: Delft University Press, 1993.
[81] P. T. Tokumaru, P. E. Dimotakis, "Image correlation velocimetry, " Exp Fluids vol, 1995, 19: 1-15.
[82] H. T. Huang, H. E. Fiedler, J. J. Wang, "Limitation and improvement of PIV. Part Ⅰ: Limitation of conventional techniques due to deformation of particle image patterns, " Exp Fluids, 1993, 15: 168-174.
[83] B. Ferguson, X. C. Zhang, "Materials for terahertz science and technology. " Nature Materials, 2002, 9(1): 26-33.
[84] D. Chetverikov, M. Nagy, and J. Verestoy. "Comparison of Tracking Techniques Applied to Digital PIV, " In Proc. International Conf. on Pattern Recognition, 2000, 4: 233-242.
[85] D. Chetverikov and J. Verestoy. "Feature Point Tracking for Incomplete Trajectories, " Computing, 2000, 62: 233-242.
[86] J. Shi and C. Tomasi. "Good features to track, " In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'94), Seattle, June 1994, 593-600.
[87] J. B. Talcott, P. C. Hansen, E. L. Assoku and J. F. Stein. "Visual motion sensitivity in dyslexia: evidence for temporal and energy integration deficits, " Neuropsychologia, 2000, 38: 395-943.
[88] C. Chubb and G. Sperling, "Second-order motion perception: space-time separable mechanisms, " in Proceedings: Workshop on Visual Motion (IEEE Computer Society Press, Washington, D. C. ), 1989, 126-138.
[89] A. Brandt. "Multi-level adaptive solutions to boundary-value problems". Mathematics of Computation, Apr. 1977, 31 (138): 333-390.
[90] W. L. Briggs, V. E. Henson, and S. F. McCormick. "A Multigrid Tutorial". SIAM, Philadelphia, second edition, 2000.
[91] W. Hackbusch. Multigrid Methods and Applications. Springer, New York, 1985.
[92] U. Trottenberg, C. Oosterlee, and A. Schuller. Multigrid. Academic Press, San Diego, 2001.
[93] P. Wesseling. An Introduction to Multigrid Methods. Wiley, Chichester, 1992.
[94] R. T. Collins et al., "A system for video Surveillance and Monitoring, " CMU-RI-TR-00-12, http://www.cs.cmu.edu.
[95] 尹晓华，智能视频监控中多目标检测跟踪技术研究，西安电子科技大学硕士学位论文，2006年。
[96] S. E. Palmer, Vision science: Photons to phenomenology. Cambrige, MA: MIT Press, 2000。
[97] 李智勇等著，动态图像分析，国防工业出版社，1999。
[98] A．Murat等著，数字视频处理，电子工业出版社，1995。
[99] S. Uras, F. Girosi, A. Verri and V. Torre, "A computational approach to motion perception," 1987, 171-180.
[100] H. Barman, L. Haglund, H. Knutsson and G Granlund, "Estimation of velocity,acceleration and disparity in time sequences," Proc. IEEE Workshop on Visual Workshop, Princeton, 1991, 44-51.
[101] J. Bigun, G Granlund and J. Wiklund, "Multidimensional orientation estimation with applications to texture analysis and optical flow," IEEE Trans.PAMI, 1991,13(8):775-790.
[102] L. Haglund, Adaptive Multidimensional Filtering. PhD Dissertation, Dept.Electrical Engineering, Univ. of Linkoping (ISSN 0345-7524), 1992.
[103] D. J. Fleet, Measurement of Image Velocity. Kluwer Academic Publisher,Norwell, 1992.
[104] A. D. Jepson and D. J. Fleet, "Phase singularities in scale-space," Image and Vision Computation, 1991, 9:338-343.
[105] Temujin Gautama and Marc M. Van Hulle, "A Phase-based Approach to the Estimation of the Optical Flow Field Using Spatial Filtering," IEEE Trans. Neural Networls, Sep 2002, 13(5): 1127-1136.
[106]G. Farneback, "Very high accuracy velocity estimation using orientation tensors, parametric motion, and simultaneous segmentation of the motion field," in Proc.Int. Conf. Computer Vision, 2001, 1:77-80.
[107]B. Jahne, H. Haussecker, H. Spies, D. Schmundt, and U. Schurr, "Study of dynamical processes with tensor-based spatiotemporal image processing techniques," in Proc. ECCV, 1998, 2:322-336.
[108]H. Spies and H. Scharr, "Accurate optical flow in noisy image sequences," Proc.Int. Conf. Computer Vision, 2001,1:587-592.
[109]G. Farneback, Spatial Domain Methods for Orientation and Velocity Estimation,PhD Dissertation, Dept. Electrical Engineering, Linkoping University, ISBN 91-7219-441-3, ISSN 0280-7971, Linkoping, Sweden, 1999.
[110]B. Jahne, H. Haussecker, and P. Geissler, Handbook of Computer Vision and Applications, Academic Press, Spring 1999, 14(2):297-422.
[111]Black, M. J. and D. J. Fleet, Probabilistic detection and tracking of motion discontinuities. international Journal of Computer Vision, 2000, 38(3):229-243.
[112]C. Perwass, G Sommer, An iterative bayesian technique for dense image point matching. In Proceedings of Dynamic Perception, 2002, 283-288.
[113]K. Koeser, C. Perwass and G Sommer, "Dense Optic Flow with a Bayesian Occlusion Model, " In Spatial Coherence for Visual Motion Analysis: First International Workshop, SCVMA, Prague, 2004, 127-139.
[114] E. Barth, I. Stuke, T. Aach and C. Mota, "Spatio-temporal motion estimation for transparency and occlusions, " In Proceedings of IEEE International conference on image processing (ICIP'03), Barcelona, Spain, September, 2003, 3: 69-72.
[115] M. Pingault, E. Bruno and D. Pellerin, "A robust multiscale B-Spline function decomposition for estimating motion transparency, " IEEE Trans on Image Processing, Nov 2003, 12(11): 1416-1426.
[116] T. Poggio and W. Reichardt, "Visual control orientation behavior in the fly: Part 2 towards underlying neural interactions, " Quarterly Reviews in Biophysics, 1976, 9: 377-438.
[117] J. Hoey and J. J. Little, "Bayesian Clustering of Optical Flow Fields, " Proceedings of the ninth IEEE International Conference on Computer Vision (ICCV'03), Oct 2003, 2: 1086-1093.
[118] 周兵，运动目标检测及在视频监控中的应用，北京航空航天大学博士论文，2003。
[119] http://klimt.iwr.uni-heidelberg.de/～hspies/publications. html,http://www.csd.uwo.ca/faculty/barron.
[120] H. Spies, H. Hauβecker, B. Jahne and J. L. Barron: Differential Range Flow Estimation. 21. Symposium fur Mustererkennung DAGM. Bonn, 1999, 309-316.
[121] J. L. Barron and H. Spies. "Quantitative regularized range flow". In Vision Interface, Montreal, Canada, May 2000, 203-210.
[122] H. H. Nagel, "Displacement vectors derived from second-order intensity variations in image sequences", 1983 CGIP, 21: 85-117.
[123] H. H. Nagel, "On a constraint equation for the estimation of displacement rates in image sequences, " IEEE Trans. PAMI, 1989, 11(1): 13-30.
[124] H. H. Nagel and W. Enkelmann, "An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences, " IEEE Trans. PAMI, 1986, 8(5): 565-593.
[125] E. H. Adelson and D. J. Heeger, "Probability distributions of optical flow, " IEEE Proc. Of CVPR, Maui, 1991, 310-315.
[126] E. P. Simoncelli, Distributed Representation and Analysis of Visual Motion, PhD Dissertation, Dept. of Electrical Engineering and Computer Science, MIT, 1993.
[127] Nelson, R. C. and Polana, R., "Qualitative recognition of motion using temporal texture, " CVGIP: Image Understand, 1992, 56(1): 78-89.
[128]Zongqing Lu, Weixin Xie, Jihong Pei, "A Robust Optical Flow Estimation under Varying Illumination," International Journal of Information Acquisition, 2005,2(4):1-11.
[129] P. Bouthemy and R. Fablet, "Motion characterization from temporal cooccurences of local motion-based measures for video indexing," in Proc. Conf. Pattern Recognition, Brisbane, Australia, Aug. 1998, 905-908.
[130]G. Doretto, Dynamic Texture Modeling, Ms. D. dissertation, Department of Computer Science, University of California, 2002.
[131]E. Hadjidemetriou, M. D. Grossberg, and S. K. Nayar, "Multiresolution Histograms and their Use for Recognition". IEEE Trans, on Pattern Analysis and Machine Intelligence, July 2004,26(7):831-847.
[132]S. McKenna et al, "Tracking groups of people," Computer Vision and Image Understanding, 2000, 80(1):42-56.
[133]K. Karmann and A. Brandt, "Moving object recognition using an adaptive background memory," In: V Cappellini, Time-varying Image Processing and Moving Object Recognition. 2. Elsevier, Amsterdam, The Netherlands, 1990.
[134]M. A. Kilger, "Shadow handler in a video-based real-time traffic monitoring system," In: Proc IEEE Workshop on Applications of Computer Vision, Palm Springs, CA, 1992, 1060-1066.
[135]C. Stauffer and W. Grimson, "Adaptive background mixture models for real-time tracking," In: Proc IEEE Conference on Computer Vision and Pattern Recognition,Fort Collins, Colorado, 1999,2,246-252.
[136] A. Lipton, H. Fujiyoshi and R. Patil, "Moving target classification and tracking from real-time video," In: Proc IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 1998, 8-14.
[137]R. Wildes and L. Wixson, "Detecting Salient Motion Using Spatiotemporal Filters and Optical Flow," Proc. DARPA Image Understanding Workshop, 1999.
[138]黎洪松,数字视频处理,北京邮电大学出版社, 2006。
[139]O. Lee, Y. Wang. "Motion-compensated prediction using Nodal-based deformable block matching". Journal of Visual Communacation and Image Representation,1995, 6(1):26-34.
[140]M. Dudon, O. Avaro and C. Roux, "Triangular active mesh for motion estimation." Signal Processing: Image Communication, 1997, 10(4):21-41.
[141]Weixin Xie, Zongqing Lu and JiHongPei."An Optical Flow Method For Micro Blood Motion Image Computation," Chinese Journal of Electronics, 2006, 15(4A): 797-802.
[142] Nesi, P., Del Bimbo, A., and Ben-Tzvi, D., "A Robust Algorithm for Optical Flow Estimation", Computer Vision and Image Understanding, July 1995, 62(1): 59-68.
[143] Heitz, F. and Bouthemy, P., "Multimodal Estimation of Discontinuous Optical Flow Using Markov Random Fields", IEEE Transactions on Pattern Analysis and Machine Intelligence, Dec. 1993, 15(12): 1217-1232.
[144] A. Bruhn, J. Weickert and C. Schnorr, "Lucas/Kanaade Meets Horn/Schunck: Combining Local and Global Optic Flow Methods", International Journal of Computer Vision, 2005, 61(3): 211-231.
[145] H. Liu, T. Hong, M. Herman, and R. Chellappa, "A general motion model and spatiotemoral filters for computing optical flow, " International Journal of Computer Vision, 1997, 22: 141-172.
[146] David Tschumperle, PDE's Based Regularization of Multivalued Images and Applications, PhD, Universite de Nice-Sophia Antipolis, 2002.