摘要
光流的概念最初来自于生物视觉研究,它描述了图像序列中可由视觉感知的运动,若由三维空间投影至二维图像平面,可近似表征为位移场。视觉感知研究发现,人类可通过运动直接识别周围环境,据此进行的自动导航试验也证明,以光流作为引导信息优于传统的导航方式。由于物体运动是视觉信息的主体,因此光流估计一直是计算机视觉及其相关研究领域的重要任务之一。光流的应用非常广泛,涉及了对象追踪、机器人学、人机交互、辅助驾驶、视频压缩、动态纹理分析、超分辨率等技术。
基于亮度常量假设的BCM模型是使用最为广泛的光流模型,然而该模型的求解存在孔径问题,且该模型仅对不变光照下的朗伯体表面有效,这限制了光流技术的应用。为了提高光流估计的准确性与稳定性,着眼于特定应用的改进模型陆续出现。
本文针对彩色视频的光流估计、光照改变时的光流计算、大位移运动的光流提取进行了研究,具体研究内容及创新成果如下:
1.为能利用色彩信息提高光流估计的稳定性,本文从彩色光流场与色度空间的关系开始,对彩色光流场的颜色模型、估计原理、典型方法进行了分析比较,针对光流场计算,提出了线性规范化的知觉颜色模型。该颜色模型利用人眼知觉特性,使颜色像素间的差值对光照变化具有稳定性,并使颜色差值向量的范数与知觉距离相匹配。同时,通过线性规范化使得颜色分量间的相关性大为降低,为后续的彩色光流场求解提供了较好的估计条件。为进一步获得对视觉方向、表面方向、高光、环境光照变化不敏感的颜色空间,本文提出了基于线性规范化的知觉颜色比值模型。
2.传统的光流估计是基于亮度或灰度等单色分量的,未充分利用彩色视频中丰富的颜色信息。光流是三维运动在二维平面上的投影,属于不适定问题,求解时需增加约束条件。若引入的辅助条件失效,则会引起大量光流误差。由于彩色图像中的某些颜色分量,在外界光照改变时,其稳定性优于亮度或灰度,因此可将颜色信息引入光流场计算,以提高估计质量。由此本文将构造的颜色空间与小区域平滑相结合,以色彩信息作为约束条件建立超定方程组,提出了扩展约束下的彩色光流方程法,实验结果表明,在实际摄录的视频中,本法获得的光流场质量优于同类方法。
3.受现有的数值求解技术所限,光流矢量存在奇异点,且易在运动物体边界处过度平滑。为此,本文提出采用改进的自动彩色细胞生长分割法,将运动区域与背景相分离以获得较为精确且连续一致的运动边缘,其后分区域滤波以消除奇异点,从而降低光流场误差。
4.基于图像亮度常量假设的模型其光流估计效果受光照影响较大,为克服此问题陆续出现了各种新模型,其中通用动态图像模型(GDIM)是影响较大、实用性较强的模型之一。本文通过对彩色图像序列的GDIM模型在克利福德代数域上的理论分析与推导,解释了GDIM模型中参数的物理意义,并根据推导结果对GDIM模型进行了修正。然后结合理论分析与实验数据,根据运动视觉产生的原理,提出了基于光照辐射的光流场模型,该模型将图像梯度场引入克利福德代数域,利用图像梯度场自身的方向特性及其对轮廓变化的敏感性,提高了光照改变时运动物体检测的准确度。
5.高速运动在视频中体现为大位移变化。常规的光流模型线性化求解仅适用于小位移,此类方法通常要求位移幅度不超过单个像素。为提高大位移估计质量,本文在采用总变分分级对偶估计技术初步获得大位移光流矢量后,以基于多维点集的Hausdorff距离作为彩色SIFT描述子的匹配距离,调整图像序列中对应物上的光流,以大位移光流场的分级彩色SIFT匹配法保持光流细节,减少了光流估计误差。
The concept of optical flow arises from studies of biological visual systems, which describes the apparent motion observed in a sequence of images. A displacement field can approximately characterise an optical flow field, which takes into account the projection from 3D to 2D image plane. Studies of visual perception reveal that human beings recognize their environment from motion information. The automatic navigation experiments also prove that the optical flow information as a guide is better than traditional navigation messages. Optical flow estimation has been one of important tasks in computer vision and related research areas, since objects motion is the main body of visual information. Optical flow has a wide range of applications such as object tracking, robotics, human–machine interaction, driver assistance systems, video compression, super-resolution, and dynamic texture analysis.
The most widespread approach to define and calculate optical flow field is based on brightness constancy assumption (BCM). However, BCM is only valid for Lambertian surfaces at constant illumination and there is an aperture problem, which limits applications of optical flow technology. Focusing on specific applications, improved optical flow models are presented in order to increase accuracy and stability of optical flow computation.
This dissertation involves optical flow estimation for color video, optical flow calculation in variable illumination and large displacement optical flow. The main research and contributions are listed as follows:
1. In order to improve the stability of optical flow vectors, a perception-based color space with linear normalization is proposed by using color information, which takes into account color perception properties of human eyes. The difference vectors between color pixels in this new color space are unchanged by reillumination, and the 2 norm of a difference vector matches the perceptual distance between two colors. The linear normalization greatly reduces the correlation between color components, and this normalized color space is suitable for optical flow estimation. The ratio color space based on linear normalization is presented to further enhance the robustness of color space to changes in viewing direction, object geometry, highlights and direction of the illumination.
2. Classic optical flow estimation only adopts brightness, gray or the other monochrome component without fully using rich color information. Optical flow field is the projection from 3D motion to 2D plane which belongs to ill-posed problem, so it needs other constraints to obtain a unique solution. It would cause a large number of optical flow errors if the auxiliary conditions are inappropriate. Because of some color components are more stable than brightness in illumination changes, this color information can be introduced into optical flow calculation for improving estimation quality. The color overdetermined equations of optical flow with extended constraints are proposed, which combine the reconstructed color space with small smooth region. Experiment results show that the proposed method is superior to the similar optical flow calculating methods in natural videos.
3. Optical flow vectors are tend to be over-smoothing on motion boundary that leads to more outliers because of the existing limitation of numerical technologies. For this reason, the improved automatic color segmentation based on cell growth is presented. With accurate and consistent motion boundary coming from segmentation, optical flow errors decrease and outliers reduce by filtering in different movement regions.
4. BCM is unstable in variable illumination, so there have been various improved optical flow models for mutative lights. General dynamic image model (GDIM) has large influence and wide applicability in these models. Based on GDIM, parameters of GDIM are explained and amended in Clifford algebra. And then, an optical flow model based on illumination radiation is proposed which bases on Clifford algebra and post-experiments data arising from principle of generating movement vision and illumination radiation theory. Following, a total variation algorithm is described. Last, experimental results show that the proposed model can achieve accurate and consistent optical flow fields in different illumination for general purpose.
5. Large displacement means high speed motions in videos. Traditional linearization in optical flow models is only valid for velocities of small magnitude which limits in one pixel. In the case of large motion vectors that arise in most real-world applications, total variation computation based on duality warping which integrates color SIFT matching is proposed. After obtaining preliminary large displacement, the optical flow vectors are adjusted with guiding in color SIFT matching based on Hausdorff distance in multi-dimensional point sets. The proposed method preserves details and enhances the quality of estimation for large displacement.
引文
[1]章毓晋.图像工程(下册):图像理解[M].第2版.北京:清华大学出版社,2007:9-12.
[2]龚卫国,桂祖宏,李正浩,辜小花.融合Adaboost和光流算法的视频人脸实时检测[J].仪器仪表学报, 2008, 29(7):1398-1402.
[3]孔健.基于MLBP-TOP与光流多特征的人脸表情融合识别研究[D].江苏镇江:江苏大学,2009.
[4]曹陶科.基于光流计算和DTW算法的动态手势识别研究与实现[D].天津:天津师范大学,2009.
[5]王安娜,薛嗣麟,俞跃,孙静.基于改进光流场模型的医学图像配准方法[J].中国图像图形学报, 2010,15(2): 328-333.
[6]江济良,屠大维,周许超,等.复杂光流场运动分析与特征提取[J].电子测量与仪器学报,2011,25(3):285-290.
[7] GUO Hongtao, ZHANG Ying.Application of optical flow method in inversion of ocean surface flow field[A].2010 Second IITA International Conference on Geoscience and Remote Sensing ,Volume 1 [C]. 2010:31-35.
[8]赵有婷,李熙莹,佘永业,等。基于视频全局光流场的交通拥堵检测[J].计算机应用研究,2010年11月,第27卷第11期:4355-4362.
[9]罗寰,王芳,陈中起,等.基于对称差分和光流估计的红外弱小目标检测[J].光学学报,2010年,第30卷06期: 1715-1720.
[10]覃天,陈万春,邢晓岚.基于光流信息的圆弧偏置比例导引规律[J].北京航空航天大学学报, 2011年第37卷第2期:189-192.
[11]沈兰荪,卓力.小波编码与网络视频传输[M].北京:科学出版社,2005年:155-156.
[12] Ryan David, Denman Simon, Fookes Clinton,et al.Textures of optical flow for real-time anomaly detection in crowds[A].Eighth IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2011)[C], IEEE, Klagenfurt University, Klagenfurt, Austria:1-7.
[13]郭宝龙,倪伟,闫允一.通信中的视频信号处理[M].北京:电子工业出版社,2007年:105-106.
[14] H.264, ITU-T and ISO/IEC. Draft ITU-T Recommendation and Final Draft International Standard of Joint Video Specification (ITU-T Rec. H.264 |ISO/IEC 14496-10 AVC)[S].日内瓦: ITU-T, 2005.
[15] H.263. Video coding for low bit rate communication[S].日内瓦: ITU-T, 1998.
[16] Belfiore S, Grangetto M, Magli E, et al. Concealment of whole-frame losses for wireless low bit-rate video based on multiframe optical flow estimation[J]. IEEE Transactions on Multimedia, April 2005, volume 7 ,issue 2: 316– 329.
[17]曹宁,胡建荣,马银松.基于光流估计的整帧恢复算法[J].通信学报,2007年第5期:137-140.
[18]庞林娟,郁梅,蒋刚毅,等.基于H.264的立体视频右图像整帧丢失错误隐藏算法[J].中国图象图形学报,2006年11月,第11卷第11期:1584-1587.
[19] A.MURAT TEKALP. Digital video processing[M]. Englewood Cliffs, NJ: Prentice-Hall, 1995:18-19.
[20]A.Verri,T.Poggio. Motion field and optical flow :qualitative properties[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, May 1989 Volume 11, Issue 5: 490-498.
[21]Gibson J.J. The perception of the visual world[M]. Cambridge: Riverside Press, 1950:78-90.
[22]Gibson J.J.The senses considered as perceptual systems[M].Boston,MA: Houghton-Mifflin,1966: 105-112.
[23] Gibson J.J. On the analysis of change in the optic array[J].Scandinavian J. Psychol.1977,18:161-163.
[24] Holte M.B., Moeslund T.B., Fihl P. View-invariant gesture recognition using 3D optical flow and harmonic motion context[J]. Computer Vision and Image Understanding, December 2010,Volume 114, Issue 12: 1353-1361.
[25] Jens Klappstein, Tobi Vaudrey, Clemens Rabe, et al. Moving Object Segmentation Using Optical Flow and Depth Information[M]. ADVANCES IN IMAGE AND VIDEO TECHNOLOGY, Lecture Notes in Computer Science, 2009, Volume 5414/2009: 611-623.
[26] Siddhartha Bhattacharyya, Ujjwal Maulik, Paramartha Dutta. High-speed target tracking by fuzzy hostility-induced segmentation of optical flow field[J]. Applied Soft Computing, January 2009, Volume 9, Issue 1:126-134.
[27] Jung Cheolkon, Jiao Licheng, Gong Maoguo. New Optical Flow Approach for Motion Segmentation Based on Gamma Distribution[J]. ADVANCES IN MULTIMEDIA MODELING, Lecture Notes in Computer Science, 2010, Volume 5916/2010: 444-453.
[28] Tal Nir, Alfred M. Bruckstein, Ron Kimmel. Over-Parameterized Variational Optical Flow[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2005, Volume 76, Number 2: 205-216.
[29] Wu Si, Yu Zhiwen, Wong Hau-San. A Shape Derivative Based Approach for Crowd Flow Segmentation[J]. COMPUTER VISION– ACCV 2009, Lecture Notes in Computer Science, 2010, Volume 5994/2010:93-10.
[30] Simon Denman, Clinton B. Fookes, Sridha Sridharan. Group Segmentation During Object Tracking Using Optical Flow Discontinuities[A]. 2010 Proceedings of the 4th Pacific-Rim Symposium on Image and Video Technology[C]. Wahingtong D.C., USA:IEEE Computer Society, 2010: 270-275.
[31] Lellmann J., Balzer J., Rieder A., et al. Shape from Specular Reflection and Optical Flow[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2008, Volume 80, Number 2: 226-241.
[32] Pickup David, Li Chuan, Darren Cosker, et al. Reconstructing Mass-Conserved Water Surfaces Using Shape from Shading and Optical Flow[J]. COMPUTER VISION– ACCV 2010, Lecture Notes in Computer Science, 2011, Volume 6495/2011:189-201.
[33] Tosun D., Prince J.L. A Geometry-Driven Optical Flow Warping for Spatial Normalization of Cortical Surfaces[J]. IEEE Transactions on Medical Imaging, Dec. 2008, Volume 27, Issue 12 : 1739 - 1753 .
[34] Horn B K P, Schunck B G. Determining optical flow[J]. Artificial Intelligence, 1981(17): 185–203.
[35] Xu Qianyi, Russell J. Hamilton, Robert A. Schowengerdt, et al. Lung tumor tracking in fluoroscopic video based on optical flow[J]. Medical Physics, 2008Dec, 35(12):5351-5359.
[36] Dario Figueira, Plinio Moreno, Alexandre Bernardino, et al. Optical Flow Based Detection in Mixed Human Robot Environments[J]. ADVANCES IN VISUAL COMPUTING, Lecture Notes in Computer Science, 2009, Volume 5875/2009: 223-232
[37] Idaku Ishii, Taku Taniguchi, Yamamoto Kenkichi . 1000-fps real-time optical flow detection system[A]. Edited by Fofi, David; Niel, Kurt S.Image Processing: Machine Vision Applications III. Proceedings of the SPIE[C]. Volume 7538, 2010: 75380M-1-11.
[38] Jayabalan E., A. Krishnan. Object Detection and Tracking in Videos Using Snake and Optical Flow Approach[J]. COMPUTER NETWORKS AND INFORMATION TECHNOLOGIES, Communications in Computer and Information Science, 2011, Volume 142, Part 2: 299-301.
[39] Barron J., Fleet D., Beauchemin S. Performance of optical flow techniques[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1994, Volume 12, Number 1: 43-77.
[40] Ali N. A., Ja’afar A. S., Abd Rahim R. Performance Analysis of Motion Estimation Algorithms on Digital Video Images[J]. Applied Mechanics and Materials (Volume 83), 2011: 174-178.
[41] Duthie G., Pyne D., Hooper S. The reliability of video based time motion analysis[J]. Journal of Human Movement Studies, 2003, 44: 259-271.
[42] Chen Zeqiang, Di Liping, Genong Yu, et al. Real-Time On-Demand Motion Video Change Detection in the Sensor Web Environment[J]. Computer Journal, July 2011: .
[43] Srinivasan M. V., Zhang S. W. Motion Cues in Insect Vision and Navigation[M]. In L. M. Chalupa and J. S. Werner (Ed.), The Visual Neurosciences, Cambridge, Mass.: MIT Press. 2004: 1193-1202.
[44] Ramesh Jain, Rangachar Kasturi, Brian G.Schunck. Machine Vision [M]. McGraw-Hill, 2001: 126-135.
[45] Snyder Wesley E., Qi Hairong. Machine vision[M]. Cambridge: Cambridge University Press, 2005: 76-83.
[46]A. Bruhn, J. Weickert, C. Schnorr. Lucas/Kanade meets Horn/Schunck: Combining local and global optical flow methods[J]. International Journal ofComputer Vision. 2005, 61(3):211-231.
[47]J.Weickert, C. Schnorr. A theoretical framework for convex regularizers in PDE-based computation of image motion[J]. International Journal of Computer vision. Dec 2001, 45(3):245-264.
[48] S.Uras, F. Girosi, A. Verri, et al. A computational approach to motion perception[J]. BIOLOGICAL CYBERNETICS,1987,Volume 60, Number 2: 79-87.
[49] Nagel H.H. Displacement vectors derived from second-order intensity variations in image sequences[J]. Computer Vision, Graphics, and Image Processing, January 1983, Vol. 21, No. 1.: 85-117.
[50] Nagel, H.H.On a constraint equation for the estimation of displacement rates in image sequences[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on , Jan 1989, Volume: 11 Issue:1 : 13 - 30 .
[51] Nagel Hans-Hellmut, Enkelmann, Wilfried. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on , Sept. 1986 ,Volume: PAMI-8 Issue:5 : 565 - 593 .
[52] E. H. Adelson , J. R. Bergen , Edward H. Adelson , et al.Spatiotemporal energy models for perception of motion[J]. Journal of the optical society of America.A, Optica and image science. 1985, Vol. 2, Issue 2: 284-299.
[53] Kearney Joseph K, Thompson William B, Boley, Daniel L. Optical flow estimation: an error anlaysis of gradient-based methods with local optimization[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, March 1987, Volume PAMI-9, Issue:2 : 229 - 244 .
[54]Lucas B.D. Generalize image matching by the method of differences[D].Ph.D. dissertation, Dept. of Computer Science, PA, USA: Carnegie-Mellon University,1984.
[55]B. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision[A]. Proceedings of the 1981 DARPA Image Understanding Workshop. Washington: IEEE press, April 1981: 121-130.
[56] Simoncelli E.P.Distributed re[resentation and analysis of visual motion[D].Ph.D. dissertation, Dept. of Electrical Engineering and Computer Science, Massachusetts, USA: MIT,1993.
[57] Singh Ajit .Optic flow computation: A unified perceptive[M]. California: IEEE Computer Society Press,1991.
[58] Anandan P. A computational frameword and an algorithm for the measurement of visual motion[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1989 Volume 2, Number 3:283-310
[59] Peter J. Burt , Edward H. Adelson. The laplacian pyramid as a compact image code[J].IEEE Trans. Communications,1983, 31:532-540.
[60] Burt P. J., Yen C., Xu X. Multiresolution flow-through motion analysis[A]. Computer Vision and Pattern Recognition– CVPR[C].Washington: IEEE press, 1983:246-252.
[61] Glazer Frank ,Reynolds George, Anandan P. Scene matching by hierarchical correlation[A]. Proceedings of the Conference on Computer Vision and Pattern Recognition Washington DC USA[C]. Washington: IEEE Press, Jun 1983: 432-441.
[62] Little J.J., Verri A. Analysis of differential and matching methods for optical[A]. Proc. IEEE 1st Work. Visual Motion[C]. Washington: IEEE Press, 1989:173-180.
[63] Little, J.J. Bulthoff, H.H. Poggio, T. Parallel optical flow using local voting[A]. Second International Conference on Computer Vision[C] . Washington: IEEE Press, Dec 1988 : 454 - 459 .
[64]黎洪松.数字视频处理[M].北京:北京邮电大学出版社,2006:70-71.
[65] Lee X, Y Wang .Motion-compensated prediction using Nodal-based deformable block matching[J]. Journal of Visual Communication and Image Representation, March 1995, Volume 6, Issue 1: 26-34.
[66] M. Dudon, O. Avaro, C. Roux. Triangular active mesh for motion estimation[J]. Signal Processing: Image Communication. July 1997, Volume 10, Issues 1-3: 21-41.
[67] Edward H. Adelson, James R. Bergen. The extraction of spatiotemporal energy in human and machine vision[A]. Proceedings of the Workshop on Motion:Representation and Analysis[C]. SC :Charleston, May 7-9,1986:151-155.
[68] Barman H., Haglund L., Knutsson, H. Estimation of velocity, acceleration and disparity in time sequences[A]. Proceedings of the IEEE Workshop on Visual Motion[C]. Washington: IEEE Press, 7-9 Oct. 1991 : 44 - 51 .
[69] Bigun J., Granlund G.H., Wiklund, J. Multidimensional orientation estimation with applications to texture analysis and optical flow[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Aug 1991 ,Volume 13 Issue 8 : 775– 790.
[70]Haglund L.Adaptive multidimensional filtering[D]. Ph. D. dissertation, Dept. Electrical Engineering, Univ. of Linkoping,1992.
[71] David J. Heeger. Optical flow using spatiotemporal filters[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1988, Volume 1, Number 4: 279-302.
[72] Bernd J?hne. Motion determination in space-time images[J]. COMPUTER VISION—ECCV 90 ,Lecture Notes in Computer Science.1990, Volume 427:161-173.
[73] Fleet D.J. Measurement of Image Velocity[M]. Norwell, MA: Kluwer Academic Publishers,1992:25-26.
[74]Santen J.P.H. van, Sperling G. Elaborated reichardi detectors[J]. J. Opt. Soc. Amer. A 2, 1985: 300-321.
[75]Watson A.B., Ahumada A.J. Model of human visual motion sensing[J]. J. Opt. Soc. Amer. A 2, 1985: 322-342.
[76]Fleet D.J., Jepson A.D. Computation of component image velocity from local phase information[J].Intern. J. Comput. 1990, Vis. 5:77-104.
[77] Fleet D.J., Heeger D.J. Wagner H. Modeling binocular neurons in primary visual cortex[A]. Jenkin M., Harris L. (eds.), Computational and Biological Mechanisms of Visual Coding[C]. Cambridge University Press, 1996: 103-130.
[78] Fleet D.J., Jepson A.D. Stability of phase information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, December 1993, Volume 15 Issue 12:1253-1268.
[79] Gautama, T., Van Hulle, M.A. A phase-based approach to the estimation of the optical flow field using spatial filtering[J]. IEEE Transactions on NeuralNetworks, Sep 2002 , Volume 13 Issue 5: 1127 - 1136 .
[80]段先华,王元全,王平安,等.利用Gabor滤波的相位图像进行光流估计[J].计算机辅助设计与图形学学报, 2005, 17(10):2157-2167.
[81] Buxton Bf, Buxton H. Computation of optic flow from the motion of edge features in image sequences[J]. Image and Vision Computing , 1984,Volume 2, Issue 2: 59-75.
[82] Duncan J.H., Chou T.C. Temporal edges: The detection of motion and computation of optical flow[A].Proc. 2nd. Intern. Conf. Comput. Vis.[C]. DC, USA: IEEE Computer Society Washington, 1988.:374-382.
[83] Ellen C. Hildreth .The computation of the velocity field[C]. Proceedings of the Royal Society of London. Series B, Biological Sciences[C]. London :The Royal Society ,1984: 189-220.
[84] Waxmann A., Wu J., Bergholm F. Convected activation profiles and receptive fields for real time measurement of short range visual motion[A]. Proceedings of IEEE CVPR[C]. DC, USA: IEEE Computer Society Washington, 1998:717-723.
[85] N. Ohta. Optical flow detection by color images[A]. Proceedings of IEEE International Conference on Image Processing[C], Pan Pacific, Singapore. DC, USA: IEEE Computer Society Washington, 1989 :801-805.
[86] Jiansu Lai, John Gauch, J. Crisman. Using color to compute optical flow[J]. Intelligent Robot and computer vision XII, 1993, vol.2056:186-194.
[87] Jiansu Lai, John Gauch, J. Crisman. Computing optical flow in color image sequences[J]. Innovation and Technology in Biology and Medicine, 1994m 15(1):76-87.
[88]P. Golland, A. M. Bruckstein. Motion from color[J]. Computer Vision and Image Understanding, 1997, 68(3):346-362.
[89]Andrews R J, Lovell B C. Color optical flow[J].Workshop on Digital Image Computingm 2003, 1(1): 135-139.
[90]Madjidi H, Negahdaripour S. On robustness and localization accuracy of optical flow computation from color imagery[A]. Proceedings of the 3D Data Processing, Visualization and Transmission, 2nd International Symposium on(3DPVT’04)[C]. DC, USA: IEEE Computer Society Washington, 2004:317-324.
[91]Arshad Jamal, K. S. Venkatesh. A New Color Based Optical Flow Algorithm for Environment Mapping Using a Mobile Robot[A].22nd IEEE International Symposium on Intelligent Control Part of IEEE Multi-conference on Systems and Control Singapore[C]. DC, USA: IEEE Computer Society Washington, 1-3 October 2007: 567-572.
[92]Simon Denman, Clinton Fookes, Sridha Sridharan. Improved Simultaneous Computation of Motion Detection and Optical Flow for Object Tracking[A].2009 Digital Image Computing: Techniques and Applications[C], DC, USA: IEEE Computer Society Washington, 2009:175-182.
[93] G. Buchsbaum .A spatial processor model for object color perception[J]. Journal of the Franklin Institute, July 1980, Volume 310, Issue 1:1-26.
[94] B.Horn. Extra reproduction of colored images[J].Comput. Vision Graphics Image Process.1984, 26:135-167.
[95]H. Turssel. DSP solutions run the gamut for color systems[J]. IEEE Signal Process.April 1993:8-23.
[96] Liu Haiying, Chellappa Rama, Rosenfeld Azriel. Accurate dense optical flow estimation using adaptive structure tensors and a parametric model[J]. IEEE Transactions on Image Processing ,2003 Volume 12, Issue 10: 1170-1180.
[97] G. Farneback. Fast and accurate motion estimation using orientation tensors and parametric motion models[A]. Proceedings of 15th International Conference on Pattern Recognition [C]. Washington DC, USA: IEEE Computer Society Washington,Volume 1, September, 2000 :135-139.
[98]Jorgen Karlholm.Local signal models for image sequence analysis[D]. PhD Dissertation, Dept Electrical engineering, Linkoping, Sweden: Linkoping University:1998.
[99] Farneback, G. Very high accuracy velocity estimation using orientation tensors, parametric motion, and simultaneous segmentation of the motion field[A]. Eighth IEEE International Conference on Computer Vision, 2001. ICCV 2001. Proceedings[C]. Washington DC, USA: IEEE Computer Society Washington, 2001: 171– 177.
[100] Bernd J?hne, Horst W. Haussecker, Hanno Scharr. Study of dynamical processes with tensor-based spatiotemporal image processing techniques[A]. ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II [C].Springer-Verlag London, UK,1988: 322-336.
[101] Hagen Spies, Hanno Scharr. Accurate optical flow in noisy image sequences[A]. International Conference on Computer Vision - ICCV[C]. Washington DC, USA: IEEE Computer Society Washington, 2001 : 587-592.
[102]Farneback G. Spatial domain methods for orientation and velocity estimation[D].PhD Dissertation, Dept. Electrical Engineering, Linkoping, Sweden :Linkoping University,1999.
[103]卢宗庆.运动图像分析中的光流计算方法研究[D],博士学位论文.中国,西安:西安电子科技大学,2007.
[104]关键,李茂宽.几何代数域内的光流场改进算法[J].海军航空工程学院学报, 2008, 23(1):9-12.
[105]李茂宽,关键.基于几何代数的彩色光流场计算[J].光学学报, 2009, 29卷, 10期:2837-2841.
[106]裴继红,叶佩玲,谢维信.基于四元同质微分的彩色光流估计[J].电子与信息学报,2009, 31(11):2614-2619.
[107]Grossberg S., Mingollaa E. Neural dynamics of visual motion perception: local detection and global grouping[J].Neural networks for vision and image processing. Massachusetts: MIT Press,1992: 293-342.
[108]刘国锋,诸昌钤.光流的计算技术[J].西南交通大学学报,1997 ,32(6):656-662.
[109] Bruggeman H, Zosh W, Warren WH. Optic flow drives human visuo-locomotor adaptation[J]. Current Biology, 4 December 2007Volume 17, Issue 23:2035-2040.
[110] Zhou Y.T.,Chellappa R. Computation of optical flow using a neural network[A]. IEEE International Conference on Neural Networks vol.2[C]. Washington DC, USA: IEEE Computer Society Washington, 1988: 71– 78.
[111]李俊博,万明习.基于遗传算法的非刚性体光流场估计方法[J].电子学报, 2001, 29(1): 41-43.
[112]杨建伟,陈震,危水根,等.基于遗传算法的直线光流刚体运动重建[J].计算机工程, 2009, 35(8) :205-207.
[113]马东民.图像序列中的光流估计与运动分割[D].硕士学位论文.中国,北京:中科院研究生院,2010.
[114]张聪炫.基于蚁群算法由直线光流场重建三维结构的研究[D].硕士学位论文.中国,南昌:南昌航空工业大学,2010.
[115] Zhang Lei , Weng Yi-fang. Optical Flow Analysis Based on Cellular Neural Networks[A]. IPTC '10 Proceedings of the 2010 International Symposium on Intelligence Information Processing and Trusted Computing[C]. Washington, DC, USA : IEEE Computer Society ,2010: 454-457.
[116]李宝旺,徐颖,李兵,等.光流信息加工的神经基础[J].生理科学进展,2002年33卷04期:317-321.
[117] Robert J. Snowden, Alan B. Milne. The effects of adapting to complex motion: position invariance and tuning to spiral motions[J]. Journal of Cognitive Neuroscience , September 1996,Volume 8 Issue 5: 435-452.
[118] M. C. MORRONE, DAVID C. BURR, LUCIA M. VAINA. Two stages of visual processing for radial and circular motion[J]. Nature , 10 August 2002,376: 507 - 509 .
[119] Corpetti T., Méminé., Pérez P. Dense estimation of fluid flows[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2002, Volume 24 Issue 3 : 365-380.
[120]杨国亮,王志良,王国江,等.基于非刚体运动光流算法的面部表情识别[J].计算机科学,2007年第34卷第3期:213-215.
[121] Jahne B., Haussecker H., Geissler P. Handbook of computer vision and applications[M].Academic Press,1999,14(2):297-422.
[122] Black, M. J., Fleet, D. J. Probabilistic detection and tracking of motion discontinuities[J]. Proceedings of the Seventh IEEE International Conference on Computer Vision (ICCV'99)[C].1999 September 20-27,Kerkyra, Greece. Los Alamitos, CA: IEEE Computer Society,: 551-558.
[123] Christian B. U. Perwass, Gerald Sommer .An iterative Bayesian techniquefor dense image point matching[A].In Proceedings of Dynamic Perception[C]. Washington, DC, USA : IEEE Computer Society ,2002:283-288.
[124] Kevin K?ser, Christian Perwass, Gerald Sommer. Dense optic flow with a Bayesian occlusion model[A]. In Proceedings of SCVMA'2004[C].2004:127-139.
[125]Simoncelli E.P., Adelson E.H., Heeger D.J. Probability distributions of optical flow[A]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91[C]. Washington, DC, USA : IEEE Computer Society , 1991: 310 - 315 .
[126] Krishnamurthy R., Moulin, P., Woods J. Optical flow techniques applied to video coding[A]. International Conference on Image Processing vol.1, 1995 [C]. Washington, DC, USA : IEEE Computer Society , Oct 1995 : 570– 573.
[127] Alvareza L. D. , Rafael Molinaa B , Aggelos K. Katsaggelos. Motion estimation in high resolution image reconstruction from compressed videl sequences[A]. 2004 International Conference on Image Processing, 2004. ICIP '04. Vol. 3 [C]. Washington, DC, USA : IEEE Computer Society ,2004: 1795– 1798.
[128] Coimbra M.T., Davies, M. Approximating optical flow with the MPEG-2 compressed domain[J]. IEEE Transactions on Circuits and Systems for Video Technology , 2005, 15(1): 103-107.
[129] Rapantzikos, K. Zervakis, M. Robust optical flow estimation in MPEG sequences[A]. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. Proceedings (ICASSP '05) [C]. March 2005 ,Volume 2:893-896.
[130]尤隽永,刘贵忠,李宏亮.一种快速、鲁棒的压缩视频光流场估计算法[J].电子与信息学报,2007年9月,第29卷第9期:2154-2157.
[131] HAUSSECKER H. W., FLEET D. J. Computing optical with phusical models of brightness variation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2001, 23(06):661-673. [132 ] Negahdaripour S., Yu, C.-H. A generalized brightness chang model for computing optical flow[A]. Fourth International Conference on Computer Vision 1993[C]. Washington, DC, USA : IEEE Computer Society , May 1993 : 2 -11 .
[133]S.H.Lai. Computation of optical flow under non-uniform brightness variations[J]. Pattern Recognition Letters, 2004, 25: 885-892.
[134] Daniilidis K., Kruger V. Optical flow computation in Log-Polar plane[A]. Proceedings of the 6th International conference on computer analysis of images and patterns[C]. Washington, DC, USA : IEEE Computer Society, 1995:65-72.
[135]Yeasin M. Optical flow in Log-Mapped image plane-a new approach[J]. Trans on PAMI, 2002, 24(1):125-131.
[136]Bertero M., Poggio T.A., Torre V. Ill-posed problems in early vision[A]. Proc. IEEE 1988[C]. Washington, DC, USA : IEEE Computer Society,August 1988, vol.76:869-889.
[137] Gennert Michael A., Negahdaripour Shahriar. Relaxing the brightness constancy assumption in computing optical flow[R]. Massachusetts: Massachusetts Institute of Technology Cambridge, MA, USA ,June,1987.
[138] Lebedev, L.P. and Cloud, M.J. The Calculus of Variations and Functional Analysis with Optimal Control and Applications in Mechanics[M]. Series on Stability, Vibration and Control of Systems, Series A - Vol. 12. CALIFORNIA, USA: World Scientific, 2003:1-98.
[139]Bernard Dacorogna .Introduction to the Calculus of Variations[M]. London, UK :Imperial College Press, 2004:39-40.
[140] Antonin Chambolle. An algorithm for total variation minimization and applications[J]. Journal of Mathematical Imaging and Vision, 2004, Volume: 20, Issue: 1/2, Publisher: Springer,: 89-97.
[141] Luigi Bagnato, Pascal Frossard, Pierre Vandergheynst Optical flow and depth from motion for omnidirectional images using a TV-L1 variational framework on graphs[A]. 2009 International Conference on Image Processing - ICIP[C]. Washington, DC, USA : IEEE Computer Society, 2009 :1469-1472.
[142] Li Yingying, Osher Stanley. A new median formula with applications to PDE based denoising[J]. Commun. Math. Sci., 2009, Volume 7, Number 3:741-753.
[143]张永平,郑南宁,赵荣椿.基于变分的图像分割算法[J].中国科学E辑,2002, 32(1):133-144.
[144] Kline, M. Mathematical Thought from Ancient to Modern Times ,Vol 2 [M]. Oxford: Oxford University Press, 1990:35-37.
[145] Shapiro S., Pagnucco M., Lesperance Y.,et al.Iterated belief change in the situation calculus[J]. Artificial Intelligence, 2011, 175(1):165–192.
[146] Guo Qiaoyun, Xu Xuemei, Li An. Computation of Real-Time Optical Flow Based on Corner Features[A]. 2010 International Symposium on Intelligence Information Processing and Trusted Computing (IPTC)[C]. Washington, DC, USA : IEEE Computer Society,Oct. 2010 : 345– 348.
[147] Brox Thomas, Bregler C. Large displacement optical flow[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, Volume: 33, Issue: 3, Publisher: IEEE: 41-48.
[148] Brox Thomas, A. Bruhn, N. Papenberg, et al. High accuracy optical flow estimation based on a theory for warping[A]. Proc. ECCV, Springer LNCS 3024[C]. Berlin,Germany:Springer, 2004: 25–36.
[149] Thomas Brox, Andr′es Bruhn, Nils Papenberg, et al.High Accuracy Optical Flow Estimation Based on a Theory for Warping[J]. COMPUTER VISION - ECCV 2004 Lecture Notes in Computer Science, Volume 3024/2004:25-36.
[150] Serdar Ince. Occlusion-Aware Intermediate View Reconstruction[D].Boston, USA: Boston University, College of Engineering,2008.
[151] Proesmans M., Gool L. Van, Pauwels E.,et al.Determination of optical flow and its discontinuities using non-linear diffusion[J]. COMPUTER VISION—ECCV 94 ,Lecture Notes in Computer Science, 1994, Volume 801/1994;294-304.
[152]L. Alvarez, R. Deriche, T. Papadopoulo, et al .Symmetrical dense optical flow estimation with occlusions detection[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2002, Volume 75, Number 3: 371-385.
[153] Sun J., Li Y., Kang S. B., et al. Symmetric stereo matching for occlusion handling[A]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition vol. 2- CVPR 2005[C]. Washington, DC, USA : IEEE Computer Society , June 2005 :399– 406.
[154] Kim H., Sohn K..3D reconstruction from stereo images for interactions between real and virtual objects[J]. Signal Processing: Image Communication, January 2005, Volume 20, Issue 1: 61-75.
[155] Ince S., Konrad J. Occlusion-Aware Optical Flow Estimation[J]. IEEE Transactions on Image Processing, AUGUST 2008, VOL. 17, NO. 8: 1443– 1451.
[156] Xiao Jiangjian, Cheng Hui, Sawhney Harpreet, et al. Bilateral Filtering-based optical flow estimation with occlusion detection[J]——ECCV 2006, Part I, LNCS 3951: 211-224.
[157] Horn B.K.P. Robot Vision[M]. New York: McGraw-Hill,1986: 98-120.
[158] Bertozzi M., Broggiand A., Fasciol A. Vision-based intelligent vehicles: state of the art and perspectives[J]. Robotics and Autonomous Systems, 2000, 32(1): 1–16.
[159] Kastrinaki V., Zervakis M., Kalaitzakis K. A survey of video processing techniques for traffic applications[J]. Image and Vision Computing , 2003, 21(4): 359–381.
[160] Mileva Y., Bruhn A., Weickert J. Illumination-robust variational optical flow with photometric invariants[J].Lecture Notes in Computer Science, 2007,vol. 4713, Springer: 152–162.
[161]Golland P., Bruckstein A.M. Motion from color[J]. Computer Vision and Image Understanding, 1997, 68(3):346–362.
[162] Weijer van de, Gevers J.T. Robust optical flow from photometric invariants[A]. In: Proc. 2004 IEEE International Conference on Image Processing[C]. Washington, DC, USA: IEEE Computer Society, October 2004, vol. 3:1835–1838.
[163]Hau?ecker H., Fleet D. Estimating optical flow with physical models of brightness variation[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence, 2001, 23(6):661–673.
[164]Negahdaripour, S. Revised definition of optical flow: integration of radiometric and geometric clues for dynamic scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(9):961–979.
[165]Uras S., Girosi F., Verri A., et al. A computational approach to motion perception[J]. Biological Cybernetics, 1988, 60:79–87.
[166]Shafer S.A. Using color to seperate reflection components[J]. Color Research and Applications, 1985, 10(4):210–218.
[167]József Molnár, Dmitry Chetverikov , Sándor Fazekas. Illumination-robust variational optical flow using cross-correlation[J]. Computer Vision and Image Understanding,2010, 114: 1104–1114.
[168] McCane B., Novins K., Crannitch D., et al. On Benchmarking Optical Flow[J]. Computer Vision and Image Understanding, 2001, 84(1), 126-143.
[169] Baker Simon, Scharstein Daniel, Lewis J.P. A database and evaluation methodology for optical flow [A]. In Proc. Eleventh IEEE international conference on computer vision (iccv 2007)[C]. Washington, DC, USA: IEEE Computer Society, 2007:1-8.
[170] Otte M., Nagel H.H. Estimation of optical flow based on higher-order spatiotemporal derivatives in interlaced and non-interlaced image sequences[J]. Artif. Intell., 1995, 78: 5–43.
[171] Adelson E., Bergen J. Spatiotemporal energy models for the perception of motion[A].in Proc. IEEEWorkshop on Visual Motion[C]. Washington, DC, USA: IEEE Computer Society, 1986: 151–156.
[172] Baker Simon, Scharstein Daniel, Lewis J.P. A Database and Evaluation Methodology for Optical Flow[J]. Int J comput. Vis.,2011, 92:1-31.
[173] Brox T., Malik J. Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2011, Volume 33, Issue 3: 500 - 513.
[174] Steinbrücker F., Pock Thomas, Cremers D. Large Displacement Optical Flow Computation without Warping[A]. ICCV 2009[C]. Washington, DC, USA: IEEE Computer Society, 2009:1609-1614.
[175] Kearney J., Thompson W., Boley D. Optical flow estimation: an error analysis ofgradient-hased mehtods with local optimization[J]. IEEE Transactions on Pattern Analysis and Machine Inielhgence, March 1987, 9(2):229—244.
[176] Lucas B. D. Generalized Image Matching by the Method of Differences[D]. PhD thesis, Pittsburgh, PA: Dept. of Computer Science, Carnegie-Mellon University, 1984.
[177] Aggarwal J., Nandhakumar N. On the computation of motion from sequence of images—a review[A]. Proc. of the IEEE, August 1988 [C]. Washington, DC, USA: IEEE Computer Society, 1988, 76(8):917—935.
[178] Fleet D.J., Black M.J., Nestares O. Bayesian inference of visual motion boundaries[M]. Lakemeyer G., B. Nebel (eds.). Exploring Artificial Intelligence in the New Millennium[C],CA, USA: Morgan Kaufmann Press, 2003:139-173.
[179]F. Girosi, A. Verri, and V. Torre. Constraints for the computation of optical flow[A]. In Proc. IEEE Workshop on Visual Motion[C]. Washington, DC, USA: IEEE Computer Society, 1989: 116—124.
[180]James D.Floey,Andries van Dam, Steven K. Feiner, et al. Introduction to Computer Graphics[M]. Boston, USA: Addison-Wesley Professional,1994: 253-260.
[181]Stone, M., Cowan W., Beatty J., Color Gamut Mapping and Printing of Digital Color Images[J]. ACM TOG, October 1988, 7(3): 249-292.
[182]Pritchard D.H. U.S. Color Television Fundamentals ----A Review[J]. IEEE Transactions on Consumer Electronics, November 1977,CE-23(4): 467-478.
[183] CIE, Commission Internationale de l'Eclairage Proceedings[S]. Cambridge: Cambridge University Press, 1931.
[185]Smith A.R. Color Gamut Transform Paris[A]. SIGGRAPH'78 Proceedings of the 5th annual conference on Computer graphics and interactive techniques[C]. ACM, NY, USA, 1978: 12-19.
[186] Xiang Xuezhi, Zhao Chunhui, Lei Zhang. A method of color optical flow computation with local and global model combined[A]. 7th World Congress on Intelligent Control and Automation, 2008. WCICA 2008[C]. Washington, DC, USA: IEEE Computer Society, 2008: 8492– 8496.
[187] Kelson R. T. ,Andre M. ,Adelardo A. D. Optical flow using color information: preliminary results[A]. Proceedings of the 2008 ACM symposium on Applied computing- SAC '08[C]. ACM, NY, USA, 2008: 1607-1611.
[188] Yang Jian, Liu Chengjun, Zhang Lei. Color Space Normalization:Enhancing the discriminating power of color space for space[J]. Pattern Recognition, 2010, 43: 1454–1466.
[189]Bedford R., Wyszecki B. Wavelength Discrimination for Point Source[J]. Journal of the optical society of America, 1958, 48: 129-130.
[190]Wright W. D. The rays are not coloured: essays on the science and vision and colour[J]. Science, October 1968, Vol. 162 no. 3850: 249-250.
[191] Xue Jingteng, Chen Chang Wen. A new perceptual quality metric for video transrating for mobile devices[A]. MCMC '10 Proceedings of the 2010 ACM multimedia workshop on Mobile cloud media computing[C]. ACM, NY, USA,2010: 35-40.
[192]Hamilton Y. Chong, Steven J. Gortler,Todd Zickler. A Perception-based Color Space for Illumination-invariant Image Processing[J]. 35th annual conference on computer graphics and interactive techniques (SIGGRAPH 2008)[C]. August 11-15, Los Angeles, Calif. ACM Transactions on Graphics, 2008, 27(3): 1-7.
[193]Walter Rudin. Principles of Mathematical Analysis[M]. Thire Edition, NY, USA: McGraw-Hill, 1976: 123-136.
[194]卓里奇B.A.数学分析(第二卷)[M].第4版,译者:蒋铎,钱珮玲,周美珂,邝荣雨.北京:高等教育出版社, 2006年12月:81-90.
[195]Theo Gevers, Arnold W.M Smeulders. Color-based object recognition[J]. Pattern Recognition, 1999, 32: 453-464.
[196] Schunck E.G. The motion constraint equation for optical flow[A]. International Conference on Pattern Recognition - ICPR 1984[C]. Washington, DC, USA: IEEE Computer Society, 1984: 20-22.
[197] DelBimbo A., Nesi P., Sanz J.L.C. Analysis of optical flow constraints[J]. IEEE Trans.on Image Processing, Apr.1995, vol. 4: 460-469.
[198]Alberto Del Bimbo, Paolo Nesi, Jorge L. C. Sanz, Optical Flow Computation Using Extended Constraints[J].IEEE TRANSACTIONS ON IMAGE PROCESSING, MAY 1996, VOL. 5, NO. 5: 720-739.
[199]李俊山,李旭辉.数字图像处理[M].北京:清华大学出版社,2007年4月:167-168.
[200] Deshmukh K.S. Color image segmentation-a review[A]. Edited by Jusoff, Kamaruzaman; Xie, Yi. Second International Conference on Digital Image Processing[C]. Proceedings of the SPIE, Volume 7546, 2010: 24-26.
[201]Meier Thomas. Segmentation for video object plane extraction and reduction of coding artifacts[D]. Australia: Dept.Of Electrical and Electronic Engineering, the University of Western Australia,1998.
[202]雷震,吴玲达,李东.基于局部微分光流的运动对象分割[J].计算机科学,2009年6月: 276-278.
[203] Vezhnevets V, Konushin V.“GrowCut”- interactive multi-label N-D image segmentation by cellular automata[A]. Proceedings of the Graphicon'2005- Proc. Graphicon[C].2005: 150–156.
[204] Luo J., Crandall D. Color object detection using spatial-color joint probability functions[J]. IEEE Transactions on Image Processing, 2006, 15(6): 1443–1453.
[205] Diplaros A., Gevers T., Patras I. Combining color and shape information for illumination-viewpoint invariant object recognition[J]. IEEE Transactions on Image Processing,2006, 15(1):1–11.
[206] Stokman H., Gevers T. Selection and fusion of color models for image feature detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(3): 371–381.
[207] Kuska Jens-peer, Scheibe Patrick, Braumann Ulf-Dietrich. Fluid extensions for optical flow and diffusion-based image registration[A]. Bildverarbeitung für die Medizin 2008[C]. Berlin Germany: Springer, 2008: 92-96.
[208] Lu Zongqing, Xie Weixin, Pei Jihong. A PDE-based method for optical flow estimation[A]. The 18th International Conference on Pattern Recognition (ICPR'06), Volume 02[C]. Washington, DC, USA: IEEE Computer Society, 2006: 78-81.
[209]白小晶,陈允杰,孙怀江,等.基于改进光流场模型的大脑图像配准[J].计算机辅助设计与图形学学报,2008,20(3):349-355.
[210]Negahdaripour S.,Yu C. H.A generalized brightness change model for computing optical flow[A]. Proceedings International Conference on Computer Vision[C].Berlin Germany: Springer, May 1993: 2-l1.
[211] Ajit Singh. Optical flow computation :A unified perspective[M]. Los Alamitos,Califonia: IEEE Computer Society Press,1991:182-190.
[212]B.K.P.Horn. Robot Vision[M]. Cabridge, US: MIT Press, 1986.
[213] Lee H.C., Breneman E.J., Schutte C.P.Modeling light reflection for computer color vision[J]. IEEE Trans. On Pattern Anal.Mach.Inter., vol.PAMI-12, Apr.1990: 402-409,
[214] Pentland A. Photometric motion[J]. IEEE Trans. On Patt. Anal Mach Intel, vol. PAMI-13,Sep, 1991: 879-890.
[215] Shafer S.A. Using color to separate reflection components[J]. COLOR Res. Appl. 1985,10(4): 210-218.
[216] Siddhartha Bhattacharyya, Ujjwal Maulik, Paramartha Dutta. High-speed target tracking by fuzzy hostility-induced segmentation of optical flow field[J]. Applied Soft Computing, January 2009,Volume 9, Issue 1: 126-134.
[217] Negahdaripour S. Revised Representation of Optical Flow for Dynamic Scene Analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Sep 1998, Volume 20, Issue 9: 961– 979.
[218] Negahdaripour S., Shokrollahi A., Gennert M. Relaxing the Brightness Constancy Assumption in Computing Optical Flow[R]. MA: Massachusetts Institute of Technology Cambridge, MA, USA, 1987.
[219] Negahdaripour S., Jin L. Direct Recovery of Motion and Range From Images of Scenes With Time-Varying Illumination[A]. ISCV '95 Proceedings of the International Symposium on Computer Vision[C]. Washington, DC, USA: IEEE Computer Society, 1995: 467-472.
[220] Barron J.L., Klette R. Quantitative colour optical flow[A]. 16th International Conference on Pattern Recognition[C]. Washington, DC, USA: IEEE Computer Society, August 2002, vol. 4: 251–255.
[221]Selig J M. Geometric fundamentals of robotics[M]. Berlin: Springer, 2005:197-210.
[222]Alan Macdonald. A survey of geometric algebra and geometric calculus[EB/OL]. http://faculty.luther.edu/~macdonal/GAGC/GAGC.html. [2010-07-12].
[223]Hestenes D, Sobczyk G. Clifford algebra to geometric calculus: a unified language for mathematics and physics[M]. Berlin: Springer, 1984: 47-62.
[224]Mangesh Nijasure, Sumanta Pattanaik, Vineet Goel. Interactive global illumination in dynamic environments using commodity graphics hardware[A].The 11th Pacific Conference on Computer Graphics and Applications (PG’03)[C]. Washington, DC, USA: IEEE Computer Society, 2003: 450-454.
[225]Chambolle A. An algorithm for total variation minimization and applications[J]. Mathematical imaging and vision, 2004, 20(1/2): 89-97.
[226]Pock T, Urschler M, Zach C, et al. A duality based algorithm for TV-L1-optical-flow image registration[A]. Proc.of the 10th international conference on medical image computing and computer assisted intervention. Washington, DC, USA: IEEE Computer Society, 2007:124-129.
[227] Black M. J., Anandan P. The robust estimation of multiple motions: parametric and piecewise smooth flow fields[J]. Computer Vision and Image Understanding, Jan. 1996, 63(1):75–104.
[228] Cohen I. Nonlinear variational method for optical flow omputation[A]. Eighth Scandinavian Conference on Image Analysis(1993),volume 1, Issue: 1 [C]. USA, Publisher: Citeseer, May 1993: 523–530.
[229] Memin E., Perez P. Dense estimation and object-based segmentation of the optical flow with robust techniques[J]. IEEE Transactions on Image Processing, May 1998, 7(5): 703–719.
[230] Papenberg N., Bruhn A., Brox T.,et al. Highly accurate optic flow computation with theoretically justified warping[J].International Journal of Computer Vision, 2006,67:141–158.
[231] Zimmer H., Bruhn A., Weickert J., et al. Complementary optic flow[A]. EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition[C].Springer-Verlag Berlin, Heidelberg, 2009: 207–220.
[232] Alvarez L., Weickert J., Sanchez J. Reliable estimation of dense optical flow fields with large displacements[J]. International Journal of Computer Vision, Aug. 2000, 39(1):41–56.
[233] Wedel A., Cremers D., Pock T. Structure- and motion-adaptive regularization for high accuracy optic flow[A]. 2009 IEEE 12th International Conference on Computer Vision[C]., Washington, DC, USA: IEEE Computer Society, 2009: 1663 - 1668 .
[234] Brox T., Bruhn A., Papenberg N., et al. High accuracy optical flow estimation based on a theory for warping[A]. editors; T. Pajdla and J. Matas. Proc. 8th European Conference on Computer Vision[C]. volume 3024 of LNCS , Springer, May 2004: 25–36.
[235] Memin E., Perez P. A multigrid approach for hierarchical motion estimation[A]. In Proc. Sixth International Conference on Computer Vision[C]. Bombay, India: Narosa Publishing House, Jan. 1998: 933–938.
[236]宣本金.变分法--理论与应用[M].合肥:中国科学技术大学出版社,2006年8月: 96-100.
[237] Steinbrücker F., Pock Thomas, Cremers D.,Large Optical Flow Computation without Warping[A].2009 IEEE 12th International Conference on Computer Vision (ICCV2009)[C]. Washington, DC, USA: IEEE Computer Society, 2009: 1609-1614.
[238] Chambolle A. An algorithm for total variation minimization and applications[J]. J. Math. Im. Vis., 2004, 20(1-2):89–97.
[239] Aujol J.F., Gilboa G., Chan T., et al. Structure texture image decomposition - modeling, algorithms, and parameter selection[J]. Int. J. of Computer Vision, 2006, 67(1):111–136.
[240] Zach C., Pock T., Bischof H. A duality based approach for realtime TV-L1 optical flow[A]. In Pattern Recognition (Proc. DAGM 2007)[C]. Heidelberg, Germany: Springer. 2007:214–223,
[241] Andreas Wedel, Thomas Pock, Christopher Zach, et al. An improved algorithm for TV-L1 optical flow[M]. Statistical and Geometrical Approaches to VisualMotion Analysis, LNCS 5604, Springer-Verlag Berlin, Heidelberg. 2009:23–45.
[242]于晶晶,潘振宽,魏伟波.小位移光流计算的对偶方法[J].计算机工程,2010年4月,第36卷,第7期:260-262.
[243] Li Yingying , Osher S. A new median formula with applications to PDE based denoising[J]. Commun. Math. Sci., 2009,7(3):741-753.
[244] Sun Deqing, Roth Stefan, Black Michael J. Secrets of optical flow estimation and their principles[A]. In Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2010)[C]. Washington, DC, USA: IEEE Computer Society, June 2010: 2432– 2439.
[245] Weber J., Malik J. Robust computation of optical flow in a multiscale differential framework[J]. International Journal of Computer Vision, 1995, 14:67–81.
[246] Liu C., Yuen J., Torralba A., et al. SIFT flow: dense correspondence across different scenes[A]. In Proc. European Conference on Computer Vision[C], volume 5304 of LNCS, Springer-Verlag Berlin, Heidelberg, 2008: 28–42.
[247] Shekhovtsov A., Kovtun I., Hlavac V. V. Efficient MRF deformation model for non-rigid image matching[A]. Conference on Computer Vision and Pattern Recognition, 2007. CVPR '07[C]. IEEE Washington, DC, USA: IEEE Computer Society, June 2007: 1 - 6.
[248] Brox Thomas, Malik Jitendra. Large Displacement optical flow: descriptor matching in variational motion estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,. 2011, Volume 33, Issue 3: 500 - 513.
[249] Lowe D. G. Object recognition from local scale invariant features[J]. Computer Vision, 1999, vol. 2:1150–1157.
[250] Lowe D. G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91–110.
[251] Mikolajczyk K., C. Schmid. A performance evaluation of local descriptors[J]. IEEE Transactions on PAMI, Oct. 2005, vol. 27, no. 10: 1615–1630.
[252]Yan Ke1, Rahul Sukthankar. PCA-SIFT: A More Distinctive presentation forLocal Image Descriptors[A]. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04), Volume 2 [C]. IEEE Washington, DC, USA: IEEE Computer Society, 2004: 506-513.
[253] Rubner Y., Tomasi C., Guibas L.J. The earth mover’s distance as a metric for image retrieval[J]. International Journal of Computer Vision ,2000,40(2): 99–121.
[254] Koen E. A. van de Sande, Theo Gevers, Cees G. M. Snoek. Evaluating Color Descriptors for Object and Scene Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, Volume 32 , Issue 9 : 1582– 1596.
[255] Bosch A., Zisserman A., X. Muoz. Scene classification using a hybrid generative/discriminative approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, vol. 30, no. 04: 712–727.
[256] Abdel-Hakim A. E. ,Farag A. A. CSIFT: A SIFT descriptor with color invariant characteristics[A]. IEEE Conference on Computer Vision and Pattern Recognition[C]. Washington, DC, USA: IEEE Computer Society, 2006: 1978–1983.
[257] Burghouts G. J., Geusebroek J. M. Performance evaluation of local color invariants[J]. Computer Vision and Image Understanding, 2009, vol. 113: 48–62.
[258] Yan Cui , Alain Pagani, Didier Stricker. SIFT IN Perception-based color space[A]. 2010 IEEE 17th International Conference on Image Processing[C]. Washington, DC, USA: IEEE Computer Society, 2010:3909-3912.
[259] Hamidreza Dastmalchi, Javad Jafaryahya, Reza Najafi, et al. Averaged Segmental Partial Hausdorff Distance for Robust Face Recognition[A]. 2011 Second International Conference on Intelligent Systems, Modelling and Simulation[C]. Washington, DC, USA: IEEE Computer Society, 2011:35-39.
[260]何力.一种基于Huasdorff距离的运动目标跟踪算法[D].合肥:中国科技大学,2010.