摘要
图像自动目标跟踪定位技术是世界各国精确视觉系统亟需解决的重要难题,是当前科技领域新兴的研究分支,也是计算机视觉领域的研究热点。尤其在某些场合,例如人无法参与或者工作量太大的情况下,研究智能化的无需人参与或仅需少量交互的系统是必然趋势。
本文深入研究了图像处理领域中高精度的角点检测、双目立体视觉摄像机标定、目标识别与跟踪算法、定位等立体视觉系统研制开发的各种关键技术,从理论和实践上深入地进行了讨论,提出并构建了一个完整的光电目标跟踪定位立体视觉系统方案。各章的具体内容安排如下：
图像特征点的提取是进行摄像机标定的前提,其提取的好坏直接影响着摄像机的标定精度,是顺利进行立体视觉和三维重建的基础。本文采用基于Harris角点检测原理的亚像素角点检测方法,利用角点邻域内图像灰度梯度变化与角点到邻域内任一点的矢量点乘为零的性质,采用迭代算法,获得了精度优于0.01个像素的亚像素角点坐标,解决了摄像机标定中高精度控制点坐标的获取问题。
针对摄像机标定过程中复杂的成像和畸变模型,提出了基于最小二乘支持向量机的摄像机标定方法。利用最小二乘支持向量机来直接学习图像信息与三维信息之间复杂的非线性映射关系,不需确定摄像机具体的内部参数和外部参数,只需要知道部分已知点(已知世界坐标的点)的图像坐标。在双目视觉的情况下,两摄像机的位置关系不需具体求出,而是隐含在网络中。由于核函数的参数以及惩罚因子是影响最小二乘支持向量机性能的关键因素,采用AGA算法自动选择确定LS-SVM参数,建立了基于AGA-LS-SVM的摄像机标定模型。仿真结果证明这一方法对于提高标定精度的有效性。
采用Haar特征作为目标识别的特征参数,解决目标自动识别与跟踪中存在的实时性、准确性的难题,将AdaBoost学习算法训练分类器,应用基于Haar特征的目标识别进行目标识别,试验结果证明该方法具有较好的实时性和较高的正确检测率。
将Kalman滤波预测方法融入到Mean Shift跟踪算法中,利用Kalman滤波预测目标位置,有效地解决了背景中大面积颜色干扰的问题,提高了跟踪方法的抗干扰能力和速度。并以仿射变换来描述目标尺寸的变化,利用连续两帧中匹配窗口的最大相关系数确定最优匹配窗口搜索目标。当目标被遮挡时,利用目标先前运动轨迹采用LS-SVM对目标运动趋势做预测,在目标被遮挡后重新出现时能够重新找到目标,进行跟踪。跟踪试验表明,算法在遮挡、背景与目标颜色相近和目标尺寸变化等复杂情况下都能对目标进行准确跟踪,具有良好的实时性和较强的抗干扰能力。
建立了目标自动识别与跟踪定位系统。进行了一系列目标自动识别与跟踪定位试验,试验结果表明：本文建立的目标自动识别与跟踪定位系统具有良好的实时性和较好的定位能力。
Automatic object recognition and tracking in image is the key technology of the preciselyguided weapons, which need to be solved urgently in the world, is the current tech area emerging research branch, it is also an active field in computer vision. Especially in some situation, for example the human is unable to participate in or in the work load too big situation, the research intellectualization does not need the human to participation or needs the few interactive systems is the inevitable trend.
In this paper deep research image processing domain high accuracy corner detection, camera calibration for stereo vision, object recognition tracking algorithm, location and so on stereoscopic vision system development each kind of key technologies, has carried on the discussion thoroughly from the theory and the practice. Proposed and has constructed a complete photoelectric object tracking location stereoscopic vision system plan. Each chapter of actual content arrangement is as follows:
Image characteristic point extraction is required to achieve camera calibration, extraction quality immediate influence following calibration precision, and carries on the stereo vision and the three dimensional reconstruction foundation smoothly. This paper uses sub-pixel corner detection method based on Harris corner detection principle, using iterative method and the corner property that any vector from the true corner to a pixel point in the comer neighborhood is always orthogonal to the gradient vector of the image at the point we obtained corners subpixel coordinates whose precision precedes 0.01 pixel. This solves the problem how to achieve the control points coordinates with subpixel accuracy on camera calibration.
In view of camera calibration process in complex imaging and distortion model, proposed based on LS-SVM camera calibration method. Least Squares Support Vector Machines are used to learn the relationships between the image information and the 3D information. It neither requires an accurate mathematical model nor needs any prior knowledge about the parameters. Only needs to know the image coordinate of partial known points(known world coordinate points). In binocular vision, the relationship between the location of the two cameras obtained without specific, but implicit in the map relations. The nuclear function parameter and penalty parameter is a pivotal factor which decides performance of LS-SVM, Uses the AGA algorithm automatic selection to determine the LS-SVM parameter, Has established the camera calibration model based on AGA-LS-SVM. Simulation results showed the validity to improving the calibration ccuracy.
Uses the Haar characteristic to take the object identification the characteristic parameter, in the solution automatic object recognition and the track exists real time, accurate difficult problem. Using AdaBoost learning algorithm training classifier, apply the Haar characteristic carries on object identification, the experiment result show that the method has the good real-time performance and the high correct detection rate.
Integrates the Kalman filter forecast technique to the Mean Shift tracking algorithm, using Kalman filter prediction objective position, has solved in effectively the background the big area color disturbance question, improves the tracking method anti-interference ability and speed. And describes the object size change by the affine transformation, matches the window using continuous two frame in the maximum correlation coefficient determination the optimal matching window search object. When the object is occlusion, using the object previous track forecast moving tendency with the LS-SVM, when the object is covered reappears could find object anew, carries on the tracking. The tracking experiment indicated that the algorithm in the occlusion, the background and the object color are close and the size change and so on the complex situation can carry on the accurate tracking to the object, has the good real time performance and anti-interference ability.
Established the automatic object recognition tracking and location system. Has carried on a series of automatic object recognition tracking and location experiment. The experiment results shows that this papaer established the automatic object recognition tracking and location system has the good real time nature and location ability.
引文
[1]J. Ferryman, A. Worrall. A generic deformable model for vehicle recogonition. Proceedings of British Machine Vision Conference.1995, 127-136P
[2]Z. Sun, G. Bebis, R. Miller. Evolutionary Gabor filter optimization with application to vehicle detection.IEEE International Conference on Data Mining,2003, Nov,307-314P
[3]Haiyuan Wu, Yukio Yoshida, Tadayoshi Shioyama. Optimal Gabor Filters for High Speed Face Identification.ICPR 2002,(1):107-110P
[4]Magee D. Tracking multiple vehicles using foreground, background and motion models. Image and Vision Computing,2004,22:143-155P
[5]Zhu Z, Xu G, Yang B, Shi D, Lin X. VISATRAM:A real-time vision system for automatic traffic monitoring. Image and Vision Computing, 2000,18(10):781-794P
[6]Chia Jung Pai, Hsiao Rong Tyan, Yu Ming Liang, et al. Pedestrian detection and tracking at crossroads. Pattern Recognition,2004,37(5):1025-1034P
[7]田启川,刘正光,李临生.基于序列图像的虹膜特征提取与分类.天津大学学报,2007,40(12)：1441-1446页
[8]Fischer S, Cristobal G Minimum entropy transform using gabor wavelets for image compression. International Conference on Image Analysis and Processing, Palermo,Italy,2001, Sept,428-433P
[9]Jianguo Zhang, Tieniu Tan, Li Ma. Rotation invariant texture segmentation via circular gabor filter. IEEE International Conference on Pattern Recognition,2002
[10]P. Viola, M. Jones. Rapid real-time object detection. Process of IEEE workshop on Statistical and Computational Theories of Vision. Vancouver, Canada,2001, July.
[11]孙隆和.机载光电探测、跟踪、瞄准系统技术分析和发展研究.电光与控制.1995(1)：1-10页
[12]周启煌,单东升.坦克火力控制系统.国防工业出版社,1997：1-30页
[13]David A, Forsyth J P.计算机视觉一种现代方法.北京：电了工业出版社,2004.6
[14]付京逊,R.L.冈萨雷斯,c.s.G李.机器人学.北京：中国电子科学技术出版社,1989
[15]Abdel-Aziz Y I. Karara H M. Direct linear transformation into object space coordinates in close-range photogrammetry. In:Proc. Symp. Close-Range Photogrammetry.1971:1-18P
[16]Brown D C. Decentering Distortion of Lenses. Photogrammetric Eng. Remote Sensing.1966:444-462P
[17]Wong KW. Mathematical foundation and digital analysis in close-range photogrammetry. In:Proc.13th Congress of the Int Society for Photogrammetry.1976:1355-373P
[18]B. Hallert. Notes on calibration of cameras and photographs in photogrammetry. Photogrametria,1968, (23):163-178P
[19]W. Faig. Calibration of close-range photogrammetry systems: Mathematical formulation. Photogrammetric Eng. Remote Sensing,1975, 41(12):1479-1486P
[20]R.Y Tsai. An Efficent and Accurate Camera Calibration Technique for 3D Machine Vision. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami Beach, FL, USA,1986:364-374P
[21]R.Y Tsai. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE Journal of Robotics and Automation,1987,3(4):323-344P
[22]J. Weng, P. Cohen and M. Herniou. Calibration of Stereo Cameras Using a Non-Linear Distortion Model. In Proceedings of International Conference on Pattern Recognition,1990:246-253P
[23]J. Weng, P. Cohen, M. Herniou. Camera calibration with distortion models and accuracy evaluation. IEEE Trans. on Pattern Analysis and Machine Intelligence,1992, October,14(10):965-980P
[24]Reg G. Wilson. Modeling and Calibration of Automated Zoom Lenses. PhD
thesis, Department of Electrical and Computer Engineering, Carnegie Melton University, Pittsburgh, Pennsylvania, USA,1994:69-73P
[25]D. C. Brown. A strategy for mufti-camera on-the-ob self-calibration. Institute Fur Photogrammetrrie Stuttgart, Festschrift, Friedrich Ackermann, zum 60. Geburtstag.1989:13P
[26]贾云得.机器视觉.北京：科学出版社.2000
[27]D. G Lowe. Three-dimensional object recognition from single two-dimensional images. AI.1987,37:355-395P
[28]J Aloimonos, I Weiss, A Bandopadhay. Active vision, IJCV.1988,76(8): 899-916P
[29]余静,游志胜.自动目标识别与跟踪技术研究综述.计算机应用研究,2005,1：12-15页
[30]魏伟波.基于图像的目标自动识别与跟踪.南京理工大学硕士学位论文,2006
[31]M Sameh Yamanu, A Aly Farag, ShinYi Hsu. A Fuzzy Hyperspectral Classifier for Automatic Target Recognition (ATR) Systems. Pattern Recognition Letters,1999,20:1431-1438P
[32]A Kenneth Augustyn. A New Approach to Automatic Target Recognition. IEEE Trans. on Aerospace and Electronic Systems,1992,28 (1):105-114P
[33]A. James, R. Atches, C. P. Walters, GRudolf Buser. Aided and Automatic Target Recognition Based upon Sensory Inputs from Image Forming Systems. IEEE Trans. on PAMI,1997,19 (9):1004-1019P
[34]K. Fukunaga. Introduction to Statistical Pattern Recognition, Academic Press, Boston,1990.
[35]Shoichi Arakil, Takashi Matsuoka, Haruo Takemura, et al. Real-time Tracking ofMultiple Moving Objects in Moving Camera Image Sequences Using Robust Statistics.1998,1051-4651P
[36]R.J.Drazovic, S. Brooks, S. Foster. Knowledge-based ship classification. Naval Electr. Systems Command,1979.
[37]R. W. Mclaren, H. Y. Lin. A knowledge-based approach to ship
identification.1986,635:257-267P
[38]F.Sadjadi. A model-based tech. for using MMW high range resolution radar for target recognition. Honeywell Interoffice Correspondance, Feb,1985.
[39]F.Sadjadi. A model-based technique for recognizing targets by using millimeter wave radar signaure. Inter. Journal of Infrared and Millimeter Waves,1987,10(3):337-342P
[40]H.N.Nasr. Knowledge and model-based ATR algorithms adaptation. SPIE Institute Series,1990, (7),122-129P
[41]E.GZelnio. Importance of sensor models to model-based vision application. SPIE Institute Series,1990, (7),112-121P
[42]W. F. Tatum. Model-based ATR systems for the military. SPIE Institute Series VoI.IS 7,130-139P
[43]J.G.Verly. A model-based system for automatic target recognition. SPIE 1991,1471:266-282P
[44]余小游,卢焕章,常青.多传感器目标识别系统中的数据融合方法与系统结构的研究.国防科技参考,1998,19(1)：1034-1038页
[45]B.P.McCune, et al. Radar with sight and knowledge. Defense Electronics, 1983,2:257-267P
[46]R.Johnson. Automatic target recognition fuse sensors and artificial intelligence. Defense Electronics,1984,1:106-115P
[47]R.J.Drazovich, J.Robert. An intelligence approach to radar classification. Tri-service Workshop of Missile Ship Targeting, Naval Research Lab, 1982.
[48]肖敬若.复杂背景下的实时目标跟踪.西北工业大学硕士学位论文.2006,14-18页
[49]J. L. Baryon, S. S. Beauchemin, D. J. Fleet. Performance of optical flow technigques. International Journal of Computer Vision,1994,12(1):43-47P
[50]Yu Huang, Thomas S. Huang, Heinrich Niemann. A Region-Based Method for Model-Free Object Tracking. International Conference on Pattern Recognition,2002:592-595P
[51]Gregory D. Hager, Peter N. Belhumeur. Efficient Region Tracking With Parametric Models of Geometry and Illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence.1998,20(10):1025-1039P
[52]M. Isard, A. Blake. CONDENSATION-Conditional Density Propagation for Visual Tracking. International Journal of Computer Vision,1998,29(1): 5-28P
[53]N. Paragios and R. Deriche. Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects. IEEE Trans. Pattern Analysis and Machine Intelligence,2000, Mar,22(3):266-280P
[54]A. R. Mansouri. Region Tracking Via Level Set PDEs Without Motion Computation. IEEE Trans. Pattern Analysis and Machine Intelligence,2002, July,24(7):947-961P
[55]A. Yilmaz, Xin Li, M. Shah. Contour-Based Object Tracking with Occlusion Handling in Video Acquired Using Mobile Cameras. IEEE Trans. Pattern Analysis and Machine Intelligence,2004, Nov,26(11):1531-1536P
[56]Tao Zhang, D. Freedman. Improving Performance of Distribution Tracking through Background Mismatch. IEEE Trans. Pattern Analysis and Machine Intelligence,2005,27(2):282-287P
[57]Collins R. T, Yanxi Liu, Leordeanu M. Online selection of discriminative tracking features. IEEE Transactions on Pattern Analysis and Machine Intelligence.2005,27(10):1631-1643P
[58]Yi-Sheng Yao, Chellappa R. Tracking a dynamic set of feature points. IEEE Transactions on Image Processing.1995,4(10):1382-1395P
[59]J.Shi, C.Tomasi. Good Feature to track. Proceedings of IEEE Conference on Computer Vision and pattern Recognition,1994,593-600P
[60]Y. Cheng. Mean Shift, mode seeking, and clustering. IEEE Trans. Pattern Analysis and Machine Intelligence,1995,17(8):790-799P
[61]D. Comaniciu, P Meer. Mean Shift analysis and applications. Int'l Conf. Computer Vision,1999:1197-1203P
[62]Zhang Zhengyou. A flexible new technique for camera calibration. IEEE
Transactions on Pattern Analysis and Machine Intelligence,2000,22(11): 1330-1334P
[63]Copper J, Svetha and Kitchen L. Early jump-out comer detectors. IEEE Traps on PAMI,1993,15:823-828P
[64]T. Hsin, W. C. Hu. A rotationally invariant two phase scheme for comer detection. Pattern Recognition,1996,128:819-828P
[65]Nobel A. Finding corners. Image and Vision Computing,1998,6(2): 121-128P
[66]Lin RS, Chu C.H, Hsueh Y C. A modified morphological detector. Pattern Recognition Letters,1998,29:279-286P
[67]Gennery D.B. Object detection and measurement using stereo vision. In: Proc. ARPA image understanding workshop, College Park, MD, Apr,1980: 161-167P
[68]H. Nagel. Displacement Vectors from the Second Order Variations in Image Sequences. Computer Vision, Graphics and Image Processing,1983: 85-117P
[69]L. Kitchen, A. Rosenfeld. Gray-Level Corner Detection. Pattern Letters, 1982,1(2):95-102P
[70]O.A. Zuniga, R. Haralick. Corner Detection Using the Facet Model. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Washington DC, USA,1983:30-37P
[71]Moravec H.P. Towaxds automatic visual obstacle avoidance. In 5th International Joint Conference on Artificial Intelligence,1977:584P
[72]Harris C, Stephens. A combined corner and edge detector. Proc.4th Alvey Vision Conf,1988:147-151P
[73]M. Trajkovic, M. Hedley. Fast corner detection. Image and Vision Computing,1998,18:75-87P
[74]Smith S. M, Brady J. M. SUSAN. A new approach to low level image processing. International Journal of Computer Vision,1997,23(1):45-78P
[75]S. Tabbone. Corner Detection Using Laplacian of Gaussian Operator.
Proceedings of the 4th Scandinavian Conference on Image Analysis, Tromso, Norway,1993:1055-1059P
[76]Tissainayagam, Suter D. Assessing the performance of corner detectors for point feature tracking applications. Image and Vision Computing,2004,22 (8):663-679P
[77]梁志敏,高洪明,王志江等.摄像机标定中亚像素级角点检测算法.焊接学报,2006,27(3)：102-104页
[78]潭晓波.摄像机标定及相关技术研究.国防科学技术大学硕士学位论文.2004,11：9-20页
[79]J. Alison Noble. Descriptions of Image Surfaces. PhD thesis, Department of Engineering Science, Oxford University,1989:45P
[80]张广军.机器视觉.科学出版社.2004.8：52-53页
[81]G C Barney, S M Dos. Elevator traffic analysis, design and control. London:IEE, Peter Peregrinus,1985.
[82]DAINISA, JUBETS M. Accurate remote measurement of robot trajectory motion. Conference on Robotics and Automation,1985:92-99P
[83]MARTINS H A, BIRK J R, KELLEY R B. Camera models based on data from two calibration planes. Computer Graphics Image Processing,1981, 17(2):173-180P
[84]MALIKM, MUDARS, FLORENT C. Automatic camera calibration based on robot calibration. IEEE Instrumentation and Measurement Technology Conference,1999,2:1278-1282P
[85]赵清杰,孙增圻,兰丽.摄像机神经网络标定技术.控制与决,2002,17(3)：336-342页
[86]Jun J, Kim C. Robust Camera Calibration Using Neural Network. Proceeding IEEE Region 10 Conference. TENCON,1999:694-697P
[87]刘宏建,罗毅,刘允才.可变精度的神经网络摄像机标定法.光学精密工程,2004,12(4)：443-448页
[88]Ahmed M T, Hemaved E. A Neural Approach for Single-and Multi-Image Camera Calibration. IEEE International Conference on Image Processing,
Kobe,1999:925-929P
[89]崔彦平,林玉池,张晓玲.基于神经网络的双目视觉摄像机标定方法的研究.光电子·激光,2005,16(9)：1097-1100页
[90]马颂德,张正友.计算机视觉——计算理论与算法基础.北京：科学出版社.1998
[91]崔万照,朱长纯,保文纯等.最小二乘小波支持向量机在非线性系统辨识中的应用.西安交通大学学报,2004,38(6)：562-586页
[92]孙德山.支持向量机分类与回归方法研究.中南大学博士学位论文.2004,4：63-88页
[93]Suykens J A K, Van Gestel T, DeBrabanter J, et al. Least Squares Support Vector Machines. River Edge, NJ:World Scientific,2002.
[94]杜京义,侯媛彬.基于遗传算法的支持向量回归机参数选取.系统工程与电子技术,2006,28(9)：1430-1434页
[95]VAPNIK V. The Nature Of Statistical Learning Theory. NY:Springer, 1995.
[96]Cristianini N, Shawe Taylor J. An Introduction to Support Vector Machines and Other Lernel-Based Learning Methods. Cambridge University Press, 2000.
[97]Joachims T, Learning to Classift Text using Support Vector Machines: Methods, Theory, and Algorithms, Ph.D. Dissertation, Department of Computer Science, University of Dortmund,2000.
[98]Chapelle O, Vapnik V. Model Selection for Support Vector Machines, Advances in Neural Information Processing Systems, S A Solla, T K Leen and K R Muller, Eds. Cambridge, MA:MIT Press,2000:230-236P
[99]Cherkassky V, Ma Y Q. Practical Selection of SVM Parameters and noise estimation fot SVM regression, Neural Networks,2004,17(1):113-126P
[100]焦刘缑,刘陈,李水,等.智能数据挖掘与知识发现.西安电子科技大学出版社.2006：247页
[101]Lee J H, Lin C J. Automatic Model Selection for Support Vector Machines. Technical Report, Dept. of Computer Science and Information Engineering,
National Taiwan University, Taipei.2000, (11).
[102]Cherkassky V, Shao X H, Mulier F M, et al. Model Complexity Control for Regression using VC Generalization Bounds, IEEE Trans. Neural Networks,1999,10(5):1075-1089P
[103]Santamaria I, Pantaleon C, Vielva L, et al. Blink Equalization of Constant Modulus Signals using Support Vector Machines, IEEE Trans. Signal Processing,2004,52(6):1773-1782P
[104]Chapelle O, Vapnik V, Bousquet O, et al. Choosing Multiple Parameters for Support Vector Machines. Machine Learning,2002,46(1-3):131-159P
[105]Gold C, Sollich P. Model Selection for Support Vector Machine Classification Neurocomputing,2003,55(1-2):221-249P
[106]Bengio Y. Gradient-Based optimization of Hyperparameters. Neural Computation,2000,12(8):1889-1900P
[107]Keerthi S S. Efficient Tuning of SVM Hyperparameters using Radius/Margin Bound and Iterative Algorithms. IEEE Trans. Neural Networks,2002, (13):1225-1229P
[108]Ito K, Nakano R. Optimizing Support Vector Regression Hyperparameters base on cross-Validation, Proc. Int. Joint Conf. Neural Networks, Portland, Oregon,2003, (3):2077-2082P
[109]M. SRINIVAS, L M. PATNAIK. Adaptive probabilities of crossover and mutation in genetic algorithm. IEEE Transactions on SMC,1994,24(4): 656-667P
[110]Kai-Min Chung, Wei-Chun Kao, et al. Decomposition methods for linear support vector machines. IEEE International Conference on Acoustics, Speech and Signal Processing.2003(4):868-871P
[111]Faig W. Calibration of close-range photogrammetric system:mathematical formulation. Photommetric Eng Remote Sensing,1975,41(12):1479-1486P
[112]Sobel I. On calibration computer controlled cameras for perceiving 3D scenes. Artificial Intelligence,1974,5(2):185-198P
[113]Gennery D B. Stereo-camera calibration. Proc Image Understanding
Workshop,1979,4:101-108P
[114]Lowe D G. Solving for the parameters of object models from image description. Proc Image Understanding Workshop,1980,4:121-127P
[115]Hakan B, Mohamed S K. A three-step camera calibration method. IEEE Trans, on Instrumentation and Measurement,1997,46(5):1165-1172P
[116]Janne Heikkila, Olli Silven. A four-step camera calibration procedure with implicit image correction. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Puerto Rico,1997:1106-1112P
[117]Shih S W, Hung Y P, Lin W S. When should consider lens distortion in camera calibration. Pattern Recognition,1995,28(3):447-461P
[118]Rainer Lienhart and Jochen Maydt. An Extended Set of Haar like Features for Rapid Object Detection. IEEE ICIP,2002, Sep,1:900-903P
[119]Kearns M. Vallant L G Learning Boolean Formulae or Factoring: [Technical Report TR-1488]. Cambridge. MA:Havard University Aiken Computation Laboratory,1988
[120]Kearns M. Vallant L G. Crytographic Limitation on Learning Boolean Formulae and Finite Automata. In:Proc of the 21st annual ACM Symposium on Theory of Computing. New York NY:ACM press.1989, 433-444P
[121]Vallant L G. A theory of the learnable. Communications of the ACM. 1984,27(11):1134-1142P
[122]Kearns M J, Vazirani L G. Learning Boolean formulae or finite automata is as hard as factoring:[Technical Report TR-14-88] Harvard University Aiken Computation Laboratory, Aug.1988
[123]Kearns M J, Vazirani L G Cryptographic limitations on learning Boolean formulae and finite automata. Journal of the Association for Computing Machinery,1994,41(1):67-95P
[124]Schapire R E. The strength of weak learnability. Machine Learning.1990. 5(2):197-227P
[125]Freund Y, Schapire R.E. A decision-theoretic generalization of online
learning and an application to boosting. In Proc. Second European Conference on Computational Learning Theory,1994.
[126]Freund Y. Boosting a weak learning algorithm by majority. Information and Computation,1995 (121).
[127]P. Viola, M. Jones. Rapid object detection using a boosted cascade of simple features. Process of IEEE Conference on Computer Vision and Pattern Recognition 2001.Los Alamitos:IEEE Computer Society Press, 2001:511-518P
[128]Y. Freund and R. E. A Short introduction to Boosting. Journal of Japanese Society for Artificial Intelligence,1999,14(5):771-780P
[129]袁野,仲崇权,余松煜,等.基于神经网络的图像颜色测温方法.红外与激光工程.2003,32(5)：527-530页
[130]Ohta Y, Kanade T, Sakai T. Color information for region segmentation. Computer Graphics and Image Processing.1980,13(3):222-241P
[131]Theo Gevers, Arnold W M Smeulders. Color-based object recognition. Pattern Recognition.1999,32(3):453-464P
[132]David A, Forsyth, Jean Ponce著,王宏等译.计算机视觉.北京：电子工业出版社,2004
[133]K. Fukunaga, L. D. Hostetler. The estimation of the gradient of a density function with application in pattern recognition. IEEE Trans. Information Theory,1975,21(1):32-40P
[134]Y. CHENG Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799P
[135]D. COMANICIU, P. MEER. Robust analysis of feature spaces:color image segmentation.1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Juan:IEEE Computer Society,1997:750-755P
[136]D. COMANICIU, P. MEER. Mean shift:A Robust application toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619P
[137]A. Bhattacharyya. On a measure of divergence between two statistical populations defined by their probability distributions. Bull. Calcutta Math,1943,35:99-109P
[138]康文静,丁雪梅,刘功亮等.带宽自适应Mean Shift跟踪算法.光电子·激光,2008,19(1)：135-138页
[139]刘胜.最优估计.哈尔滨工程大学出版社,1995.
[140]Grewal, Mohinder S, Angus P. Andrews. Kalman Filtering Theory and Practice. Upper Saddle River, NJ USA, Prentice Hall.1993.
[141]Welch, Bishop. An introduction to the Kalman Filter. UNC-Chapel Hill, TR 95-041, Apri15,2004.
[142]Comaniciu D, Ramesh V, Meer P. Real-Time tracking of non-rigid objects using mean shift. Werner B. IEEE Int'l Proc of the Computer Vision and Pattern Recognition, Stoughton:Printing House,2000,2:142-149P
[143]Yilmaz A, Shafique K, Shah M. Target tracking in airborne forward looking infrared imagery. Journal of Image and VisionComputing,2003, 21(7):623-635P
[144]Bradski GR. Computer vision face tracking for use in a perceptual user interface In:Regina Spencer Sipple, ed. IEEE Workshop on Applications of Computer Vision. Stoughton:Printing House.1998,214-219P
[145]Collins R T. Mean shift blob tracking through scale space[A]. IEEE International Conference On Computer Vision and Pattern Recognition. 2003,2:234-240P
[146]彭宁嵩,杨杰,刘志,等.Mean-Shift跟踪算法中核函数窗宽的自动选取.软件学报,2005,16(9):1542-1550页
[147]Comaniciu D. Ramesh V. Meer P. The variable bandwidth mesh shift and data-driven scale selectice.8th Intl Conf On computer Vision,2001,1: 438-445P
[148]Changjiang YANG, Ramani DURAISWAMI, Larry DAVIS. Eighteenth Annual Conference on Neural Information Processing Systems. Eighteenth Annual Conference on Neural Information Processing Systems. Victoria British Columbia, Callada:NIPS,2004.
[149]K. NUMMIARO, E. KOLLER-MEIER, L. Van GOOL. Color Features for Tracking Non-Rigid Objects. Special Issue on Visual Surveillance. Chinese Journal of Automation.2003,29(3):345-355P
[150]Comaniciu D, Ramesh V. Meer P. Kernel-based object tracking. IEEE Trans On Patern Analysis and Machine Intelligence.2003,25(5):564-575P
[151]孙中森,孙俊喜,宋建中,等.一种抗遮挡的运动目标跟踪算法.光学精密工程,2007,15(2)：267-271页
[152]胡朝晖,汪凯,车奇,李东文.机载光电跟踪系统作用距离建模与仿真.探测与控制学报,2005,274：50-56页
[153]赵妙娟,车宏.军用光电系统作用距离分析.红外与激光工程,2008,37：501-503页
[154]曹辉.船舶监控中的视频稳像与目标跟踪的研究.大连海事大学博士学位论文.132页