基于图像的目标自动识别与跟踪技术研究
|
摘要
基于图像的目标自动识别与跟踪技术是世界各国精确打击武器系统急需解决的重要难题，也是计算机视觉领域的研究热点。本文作为国防科工委基础研究项目“基于图像的战场目标自动识别技术”成果的重要组成部分，对目标自动识别与跟踪技术的理论、计算和试验三方面进行了系统研究。包括：用两种语言编程实现了经典图像匹配方法中的模板匹配，对静态图片和运动目标进行了试验；将基于Haar特征的目标自动识别方法扩展到战场军事目标的自动识别，改进了AdaBoost算法，建立了基于改进AdaBoost算法的军事目标分类器训练方法，提高了分类器的训练精度；将Kalman滤波预测方法融入到CamShift算法中，提高了目标跟踪算法的速度和抗干扰能力；应用本文建立的目标自动识别与跟踪方法，建立了包括软件与硬件的快速目标自动识别与跟踪系统，进行了一系列目标自动识别与跟踪试验，分别实现了在简单背景、复杂背景、有干扰和遮挡等多种场景下的目标自动识别与跟踪，试验结果表明：本文建立的目标自动识别与跟踪算法速度快，目标自动识别与跟踪系统实时性和抗干扰能力强。该成果可应用于视频监控、战场目标识别跟踪、导航制导等多个领域，应用前景广阔。提出了将目标自动识别与跟踪算法移植到DSP上，以便用于弹上导引头的软件设计的思路和方法。为基于目标自动识别与跟踪技术的精确打击武器系统提供了重要的理论基础与技术支撑。
Automatic object detection and tracking in image is the key technology of the precisely guided weapons, which need to be solved urgently in the world. It is also an active field in computer vision. As an important component of the production of national defense basic project named "The automatic target recognition technology based on the images in the battlefield", the theory, algorithm, and experiment of automatic object detection and tracking are studied in this paper. The template-matching method is respectively realized with two different tools. By doing tests on static photos and motive video, the advantages and disadvantages of template-matching method are analyzed. The method based on Haar feature which could detect object automatically is introduced into millitary fields. The AdaBoost algorithm is developed. Based on the developed AdaBoost algorithm, the training method for military target classifier is established. The precision of classifier training is improved and has been verified by experiments. Speed and anti-jamming ability of automatic object tracking method is improved by merging Kalman filter into CamShift algorithm. Applying these methods built in this thesis, a system with hardware and software, which can detect and track object quickly and automatically, is built. The real-time and efficiency of this system is verified by some object detection and tracking experiments in different scenes such as simple background, complex background, jamming and obstruct. This system could be applied to many fields such as video surveillance, and navigation. In order to transfer the algorithm to DSP and apply to homing head on the missile at last, the design idea of software and the transfer process of algorithm from PC to DSP are proposed. Important theory and technical support are provided for the precisely guided weapons system based on automatic object detection and tracking.
Automatic object detection and tracking in image is the key technology of the precisely guided weapons, which need to be solved urgently in the world. It is also an active field in computer vision. As an important component of the production of national defense basic project named "The automatic target recognition technology based on the images in the battlefield", the theory, algorithm, and experiment of automatic object detection and tracking are studied in this paper. The template-matching method is respectively realized with two different tools. By doing tests on static photos and motive video, the advantages and disadvantages of template-matching method are analyzed. The method based on Haar feature which could detect object automatically is introduced into millitary fields. The AdaBoost algorithm is developed. Based on the developed AdaBoost algorithm, the training method for military target classifier is established. The precision of classifier training is improved and has been verified by experiments. Speed and anti-jamming ability of automatic object tracking method is improved by merging Kalman filter into CamShift algorithm. Applying these methods built in this thesis, a system with hardware and software, which can detect and track object quickly and automatically, is built. The real-time and efficiency of this system is verified by some object detection and tracking experiments in different scenes such as simple background, complex background, jamming and obstruct. This system could be applied to many fields such as video surveillance, and navigation. In order to transfer the algorithm to DSP and apply to homing head on the missile at last, the design idea of software and the transfer process of algorithm from PC to DSP are proposed. Important theory and technical support are provided for the precisely guided weapons system based on automatic object detection and tracking.
引文
1 郭修煌．精确制导技术．北京：国防工业出版社．1999．
2 魏伟波，芮筱亭．精确制导技术研究．火力与指挥控制，2006，31(2)：5～8，11．
3 魏伟波，芮筱亭．毫米波精确制导技术．火力与指挥控制，2005，30增刊：4～6，10．
4 魏伟波，芮筱亭，陈娅莎．毫米波雷达导引头技术．战术导弹技术，2006(录用)
5 杨富锋，芮筱亭，王国平，魏伟波．图像制导火箭弹成像环境分析．弹箭与制导学报，2006，26(1)：756～758，762
6 郁文贤，郭桂蓉．ATR的研究现状和发展趋势．系统工程与电子技术，1994(6)：25～29．
7 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
8 K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press, Boston, 1990.
9 Shoichi Arakil, Takashi Matsuoka, Haruo Takemura, and NaoKazu Yokoya, Real-time Tracking of Multiple Moving Objects in Moving Camera Image Sequences Using Robust Statistics. 1051-4651/98, 1998 IEEE.
10 R. J. Drazovich, S. Brooks and S. Foster. Knowledge-based ship classification. Naval Electr. Systems Command, 1979.
11 R. W. Mclaren and H. Y. Lin. A knowledge-based approach to ship identification. SPIE Vol. 635, 1986, pp. 257-267.
12 F. Sadjadi, et al. A model-based tech. for using MMW high range resolution radar for target recognition. Honeywell Interoffice Correspondance, Feb, 1985.
13 F. Sadjadi, et al. A model-based technique for recognizing targets by using millimeter wave radar signaure. Inter. Journal of Infrared and Millimeter Waves, Vol. 10, No. 3, 1987, pp. 337-342.
14 H. N. Nasr, et al. Knowledge-and model-based ATR algorithms adaptation. SPIE Institute Series, Vol. IS 7, 1990, pp. 122-129.
15 E. G. Zelnio. Importance of sensor models to model-based vision application. SPIE Institute Series Vol. IS 7, 1990, pp. 112-121.
16 W. F. Tatum. Model-based ATR systems for the military. SPIE Institute Series Vol. IS 7, pp. 130-139.
17 J. G. Verly, et al. A model-based system for automatic target recognition. SPIE Vol. 1471, 1991. pp. 266-282.
18 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．
19 B. P. McCune, et al. Radar with sight and knowledge. Defense Electronics, Vol. 2, 1983, pp. 257-267.
20 R. Johnson. Automatic target recognition fuse sensors and artificial intelligence. Defense Electronics, Vol. 1, 1984, pp. 106-115.
21 R. J. Drazovich, J. Robert, et al. An intelligence approach to radar target classification. Tri-service Workshop of Missile Ship Targeting, Naval Research Lab, 1982.
22 J. F. Gilmore, et al. TESS-the tactical expert system. Proc. Of SPIE, Vol. 635, 1986, pp. 143-150.
23 刘怡光，游志胜．一种用于图像目标识别的神经网络及其车型识别应用．计算机工程。2003，29(3)：30～32．
24 陈振羽，李德华，周焰．利用多种特征和Hopfieid神经网络的有遮挡的目标识别．中国图象图形学报，2000，5(12)：11～16．
25 Cedras Claudetle. Motion-based recognition. Image and Vision Computing, 2001, 13(2): 129～155
26 孙涵．基于红外图像的道路识别与运动目标跟踪．南京：南京理工大学，2005
27 张天序．成像自动目标识别．湖北：湖北科学技术出版社，2003
28 王栓，艾海舟，何克忠．基于差分图像的多运动目标的检测与跟踪．中国图象图形学报，1999，4(A)：470～475．
29 J L Barron, S S Beauchemin, D J Fleet. Performance of optical flow technigques. International Journal of Computer Vision, 1994, 12(1): 43-47
30 王新余，张桂林．基于光流的运动目标实时检测方法研究．计算机工程与应用，2004，1：43～46
31 胡明昊，任明武，杨静宇．一种快速实用的特征点匹配算法．计算机工程，2004，30(9)：31～33
32 Yu Zhong, Anil K. Jain, et al. Object Tracking using Deformable Templates. IEEE transactions on pattern analysis and machine intelligence, Vol. 22, No. 5, May 2000.
33 A. K. Jain, Y. Zhong, and S. Lakshmanan, Object Matching Using Deformable Templates. IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 18, no. 3, pp. 267-278, Mar. 1996.
34 Shoichi Araki, Takashi Matsuoaka, Naokazu Yokoya, et al. Real-time tracking of multiple moving object contours in a moving camera image sequence. IEICE Trans Inf& Syst, 2000, E83-D(7).
35 Yun-Ting Lin and Yuh-Lin Chang, Tracking Deformable Objects with the Active Contour Model. O-8186-7819-4, 1997 IEEE.
36 M. Bertalmio, G. Sapiro, and G. Randall, Morphing Active Contours. Proc. Int'l Conf. Scale-Space Theories in Computer Vision, pp. 46-57, 1999.
37 Vieren C, Cabestaing F, Postaire J. Catching Moving Objects with Snakes for Motion Tracking. Pattern Recognition Letters, 1995, 16: 679～685.
38 W J Rucklidge. Efficiently Locating Objects Using Hausdorff Distance. International J of Computer Vision, 1997, 24(3): 251-270.
39 J. Shi and C. Tomasi. Good Feature to track. Proceedings oflEEE Conference on Computer Vision and pattern Recognition, pp 593-600. 1994.
40 Y. Cheng. Mean Shift, mode seeking, and clustering. IEEE Trans. Pattern Analysis and Machine Intelligence, 1995 Vol. 17, no. 8: 790-799.
41 D. Comaniciu and P. Meer. Mean Shift analysis and applications. Proc. lnt'l Conf. Computer Vision, 1999: 1197-1203.
42 A. Lipton, H. Fujiyoshi, and R. Patil, Moving Target Detection and Classification from Real-Time Video. Proc. IEEE Workshop Application of Computer Vision, 1998.
43 Collins R et al. A system for video surveillance and monitoring: VSAM final report. Carnegie Mellon University, Technical Report, 2002.
44 Margrit Betke, Esin Haritaoglu, Larry S. Davis. Real-time multiple vehicle detection and tracking from a moving vehicle. Machine Vision and Application, 2000, 12: 69-83.
45 Haritaoglu I, Harwood D and Davis L. W4: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (8):809-830.
46 Remagnino P, Tan T and Baker K. Multi-agent visual surveillance of dynamic scenes. Image and Vision Computing, 1998, 16(8):529-532.
47 徐瑞鑫．复杂背景下实时目标跟踪与识别研究．长春：中国科学院长春科学精密机械与物理研究所，2002．
48 唐仁圣．空中目标实时跟踪算法研究及系统设计．重庆：重庆大学，2004．
49 米长伟．电视制导炸弹目标图像实时处理技术研究．南京：南京理工大学，2005．
50 胡明昊．复杂背景下运动目标的实时跟踪．南京：南京理工大学，2002．
51 杨宜禾，周维真．成像跟踪技术导论．西安：西安电子科技出版社，1992．
52 徐之海，李奇．现代成像系统．北京：国防工业出版社，2001．
53 李象霖．三维运动分析[M]．合肥：中国科学技术大学出版社，1994．
54 石友学．图像匹配中若干问题的研究．大连：大连理工大学，2004．
55 王红梅，张科，李言俊．图像匹配研究进展．计算机工程与应用，2004，19：42～44，77．
56 魏伟波，芮筱亭．不变矩方法研究．火力与指挥控制，2005(录用)．
57 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: 511-518.
58 P. Viola, M. Jones. Rapid real-time object detection. Process of IEEE workshop on Statistical and Computational Theories of Vision. Vancouver, Canada, July 2001.
59 R. Lienhart and J. Maydt. An extended set ofhaar-like features for rapid object detection. IEEE ICIP 2002, Vol. 1, pp. 900-903, 2002.
60 Y. Freund and R. E. Schapire. A short introduction to boosting. Journal of Japanese Society for Artificial Intelligence, 14(5):771-780, September 1999. Appearing in Japanese, translation by Naoki Abe.
61 R. E. Schapire. A brief introduction to boosting. In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, 1999.
62 R. Meir and G. Ratsch. An introduction to boosting and leveraging. In S. Mendelson and A. Smola, editors, Advanced Lectures on Machine Learning, LNCS, pages 119-184. Springer, 2003. In press. Copyright by Springer Verlag.
63 Schapire R E, Freund Y, Bartlett P, et al. Boosting the margin: A new explanation for the effectiveness of voting methods. ICML 1997. Los Alamitos: IEEE Computer Society Press, 1997: 322-330.
64 沈学华，周志华，吴建鑫等．Boosting和Bagging综述．计算机工程与应用．2000，12：31～32，40．
65 L. Breiman. Bagging Predictors. Machine learning, 1996, 24(2):123-140
66 Y. Freund and R. E. Schapire. Experiments with a new boosting algorithm. 1996.
67 武勃，黄畅，艾海舟等．基于连续AdaBoost算法的多视角人脸检测．计算机研究与发展．2005，42(9)：1612～1621．
68 R. Lienhart and V. Pisarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection. MRL Technical Report, Intel Labs, 2002.
69 H. A. Rowley, S. Baluja and T. Kanade. Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, No. 1, pp. 23-38, 1998.
70 Jose Barreto, Paulo Menezes and Jorge Dias. Human-robot interaction based on Haar-like features and eigenfaces. In: International Conference on Robotics and Automation, 2004.
71 郑峰，杨新．基于AdaBoost算法的人脸检测．计算机仿真，2005，22(9)：167-169，253．
72 赵江，徐鲁安．基于AdaBoost算法的目标检测．计算机工程，2004，30(4)：125-126，172
73 孔凡芝，张兴周，谢耀菊．基于AdaBoost算法的人脸检测技术．应用科技，2005，32(6)：7-9．
74 Papageorgiou C, Oren M. and Poggio T. A general framework for object detection. International Conference on Computer Vision, 1998.
75 K. Fukunaga and L. D. Hostetler. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Information Theory, 1975, Vol. 21: 32-40.
76 耿振伟，蒋咏梅，粟毅．一种巨幅遥感影像中机场ROI检测算法．电子与信息学报，2005，27(11)：1770-1773
77 D. Comaniciu, P. Meer. Mean Shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Machine Intell, May 2002(24): 603-619.
78 Papageorgiou C, Oren M. and Poggio T. A general framework for object detection. In: International Conference on Computer Vision, 1998
79 G. R. Bradski. Computer vision face tracking for use in a perceptual user interface. Intel Technology Journal, 1998, 2nd Quarter.
80 D. Comaniciu, V. Ramesh, P. Meer. The variable bandwidth Mean Shift and data-driven scale selection. 8th International Conference on Computer Vision, Vancouver, Canada, July 2001, Vol. I: 438-445.
81 D. Comaniciu, V. Ramesh, P. Meer: Kernel-based object tracking. IEEE Trans. Pattern Anal. Machine Intell. 2003(25): 564-577.
82 D. Comaniciu, P. Meer: Mean Shift analysis and applications. 7th International Conference on Computer Vision, Kerkyra, Greece, September 1999: 1197-1203.
83 P. Meer, C.V. Stewart, D.E. Tyler. Robust computer vision: An interdisciplinary challenge. Computer Vision and Image Understanding, 2000, Vol.78: 1-7.
84 B. Georgescu, I. Shimshoni, P. Meer. Mean Shift based clustering in high dimensions: A texture classification example. 9th International Conference on Computer Vision, Nice, France, 2003. 8: 456-463.
85 B. Georgescu, P. Meer. Point Matching Under Large Image Deformations and Illumination Changes. IEEE Trans. Pattern Anal. Machine Intell. 2004, Vol. 26: 674-689.
86 Dorin comaniciu, Visvanathan Ramesh, Peter Meer. Real-Time Tracking of Non-Rigid Objects using Mean Shift. IEEE CVPR 2000.
87 Alper Yilmaz, Khurram Hassan-Shafique, Mubarak Shah, Niels da Vitoria Lobo. Target-Tracking in FLIR Imagery Using Mean-Shift and Global Motion Compensation. Workshop on Computer Vision Beyond the Visible Spectrum, with CVPR 2001, Kauai, Hawaii, 2001.
88 Sohaib Khan, Mubarak Shah. Object Based Segmentation of Video Using Color, Motion and Spatial Information. IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2001, Kauai, Hawaii, 2001.
89 Omar Javed and Mubarak Shah. Tracking And Object Classification For Automated Surveillance. The seventh European Conference on Computer Vision, Denmark, 2002.
90 C. Yang, R. Duraiswami, D. DeMenthon and L. Davis. Mean-Shift Analysis Using Quasi-Newton Methods. In IEEE International Conference on Image Processing, 2003, Vol.3: 447 - 450.
91 C. Yang, R. Duraiswami, A. Elgammal and L. Davis. On-Line Kernel-Based Tracking in Joint Feature-Spatial Spaces. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004.
92 C. Yang, R. Duraiswami, A. Elgammal and L. Davis. Real-Time Kernel-Based Tracking in Joint Feature-Spatial Spaces. Technical Report CS-TR-4567, Dept. of Computer Science, University of Maryland, College Park, 2004.
93 (美)Linda G．Shapiro，George C．Stockman著，赵清杰，钱芳，蔡利栋译．Computer Vision．北京：机械工业出版社，2005．
94 吴晓娟，翟海亭，王磊等．一种改进的CamShift手势跟踪算法．山东大学学报(工学版)，2004，34(6)：120～124
95 杨洪丰．视频序列中运动目标的实时分割与跟踪．西安：西安理工大学，2003
96 陆文广．快速目标自动识别与跟踪方法及实现研究．南京：南京理工大学，2005．
97 王宾．视频序列中运动目标检测与跟踪有关问题的研究．西安：西北大学电子系．2004
98 郑海滨．视频监视方法研究．西安：西北工业大学．2002
99 John G. Allen, Richard Y. D. Xu, Jesse S. Jin. Object Tracking Using CamShift Algorithm and Multiple Quantized Feature Spaces. Australian Cmputer Society, Inc. 2004
100 Andre Senior and Sabri Tosunoglu. Hybrid Machine Vision Control. Florida Conference on Recent Advances in Robotics. Gainesville, Florida, 5-6 May 2005.
101 Grewal, Mohinder S. and Angus P. Andrews. Kalman Filtering Theory and Practice. Upper Saddle River, NJ USA, Prentice Hall. 1993.
102 Welch and Bishop. An introduction to the Kalman Filter. UNC-Chapel Hill, TR 95-041, April5, 2004.
103 陈峰．Blackfin系列DSP原理与系统设计．北京：电子工业出版社，2004
104 魏伟波，芮筱亭．图像边缘检测方法研究．计算机工程与应用，2006(录用)
105 魏伟波，芮筱亭，刘军等．基于OpenGL的火炮膛内压力变化的动画仿真．系统仿真学报，2006，18(3)：666～668．
106 杨富锋，芮筱亭，魏伟波．用小波方法估计密度函数．兵工学报，2005(录用)
2 魏伟波，芮筱亭．精确制导技术研究．火力与指挥控制，2006，31(2)：5～8，11．
3 魏伟波，芮筱亭．毫米波精确制导技术．火力与指挥控制，2005，30增刊：4～6，10．
4 魏伟波，芮筱亭，陈娅莎．毫米波雷达导引头技术．战术导弹技术，2006(录用)
5 杨富锋，芮筱亭，王国平，魏伟波．图像制导火箭弹成像环境分析．弹箭与制导学报，2006，26(1)：756～758，762
6 郁文贤，郭桂蓉．ATR的研究现状和发展趋势．系统工程与电子技术，1994(6)：25～29．
7 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
8 K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press, Boston, 1990.
9 Shoichi Arakil, Takashi Matsuoka, Haruo Takemura, and NaoKazu Yokoya, Real-time Tracking of Multiple Moving Objects in Moving Camera Image Sequences Using Robust Statistics. 1051-4651/98, 1998 IEEE.
10 R. J. Drazovich, S. Brooks and S. Foster. Knowledge-based ship classification. Naval Electr. Systems Command, 1979.
11 R. W. Mclaren and H. Y. Lin. A knowledge-based approach to ship identification. SPIE Vol. 635, 1986, pp. 257-267.
12 F. Sadjadi, et al. A model-based tech. for using MMW high range resolution radar for target recognition. Honeywell Interoffice Correspondance, Feb, 1985.
13 F. Sadjadi, et al. A model-based technique for recognizing targets by using millimeter wave radar signaure. Inter. Journal of Infrared and Millimeter Waves, Vol. 10, No. 3, 1987, pp. 337-342.
14 H. N. Nasr, et al. Knowledge-and model-based ATR algorithms adaptation. SPIE Institute Series, Vol. IS 7, 1990, pp. 122-129.
15 E. G. Zelnio. Importance of sensor models to model-based vision application. SPIE Institute Series Vol. IS 7, 1990, pp. 112-121.
16 W. F. Tatum. Model-based ATR systems for the military. SPIE Institute Series Vol. IS 7, pp. 130-139.
17 J. G. Verly, et al. A model-based system for automatic target recognition. SPIE Vol. 1471, 1991. pp. 266-282.
18 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．
19 B. P. McCune, et al. Radar with sight and knowledge. Defense Electronics, Vol. 2, 1983, pp. 257-267.
20 R. Johnson. Automatic target recognition fuse sensors and artificial intelligence. Defense Electronics, Vol. 1, 1984, pp. 106-115.
21 R. J. Drazovich, J. Robert, et al. An intelligence approach to radar target classification. Tri-service Workshop of Missile Ship Targeting, Naval Research Lab, 1982.
22 J. F. Gilmore, et al. TESS-the tactical expert system. Proc. Of SPIE, Vol. 635, 1986, pp. 143-150.
23 刘怡光，游志胜．一种用于图像目标识别的神经网络及其车型识别应用．计算机工程。2003，29(3)：30～32．
24 陈振羽，李德华，周焰．利用多种特征和Hopfieid神经网络的有遮挡的目标识别．中国图象图形学报，2000，5(12)：11～16．
25 Cedras Claudetle. Motion-based recognition. Image and Vision Computing, 2001, 13(2): 129～155
26 孙涵．基于红外图像的道路识别与运动目标跟踪．南京：南京理工大学，2005
27 张天序．成像自动目标识别．湖北：湖北科学技术出版社，2003
28 王栓，艾海舟，何克忠．基于差分图像的多运动目标的检测与跟踪．中国图象图形学报，1999，4(A)：470～475．
29 J L Barron, S S Beauchemin, D J Fleet. Performance of optical flow technigques. International Journal of Computer Vision, 1994, 12(1): 43-47
30 王新余，张桂林．基于光流的运动目标实时检测方法研究．计算机工程与应用，2004，1：43～46
31 胡明昊，任明武，杨静宇．一种快速实用的特征点匹配算法．计算机工程，2004，30(9)：31～33
32 Yu Zhong, Anil K. Jain, et al. Object Tracking using Deformable Templates. IEEE transactions on pattern analysis and machine intelligence, Vol. 22, No. 5, May 2000.
33 A. K. Jain, Y. Zhong, and S. Lakshmanan, Object Matching Using Deformable Templates. IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 18, no. 3, pp. 267-278, Mar. 1996.
34 Shoichi Araki, Takashi Matsuoaka, Naokazu Yokoya, et al. Real-time tracking of multiple moving object contours in a moving camera image sequence. IEICE Trans Inf& Syst, 2000, E83-D(7).
35 Yun-Ting Lin and Yuh-Lin Chang, Tracking Deformable Objects with the Active Contour Model. O-8186-7819-4, 1997 IEEE.
36 M. Bertalmio, G. Sapiro, and G. Randall, Morphing Active Contours. Proc. Int'l Conf. Scale-Space Theories in Computer Vision, pp. 46-57, 1999.
37 Vieren C, Cabestaing F, Postaire J. Catching Moving Objects with Snakes for Motion Tracking. Pattern Recognition Letters, 1995, 16: 679～685.
38 W J Rucklidge. Efficiently Locating Objects Using Hausdorff Distance. International J of Computer Vision, 1997, 24(3): 251-270.
39 J. Shi and C. Tomasi. Good Feature to track. Proceedings oflEEE Conference on Computer Vision and pattern Recognition, pp 593-600. 1994.
40 Y. Cheng. Mean Shift, mode seeking, and clustering. IEEE Trans. Pattern Analysis and Machine Intelligence, 1995 Vol. 17, no. 8: 790-799.
41 D. Comaniciu and P. Meer. Mean Shift analysis and applications. Proc. lnt'l Conf. Computer Vision, 1999: 1197-1203.
42 A. Lipton, H. Fujiyoshi, and R. Patil, Moving Target Detection and Classification from Real-Time Video. Proc. IEEE Workshop Application of Computer Vision, 1998.
43 Collins R et al. A system for video surveillance and monitoring: VSAM final report. Carnegie Mellon University, Technical Report, 2002.
44 Margrit Betke, Esin Haritaoglu, Larry S. Davis. Real-time multiple vehicle detection and tracking from a moving vehicle. Machine Vision and Application, 2000, 12: 69-83.
45 Haritaoglu I, Harwood D and Davis L. W4: real-time surveillance of people and their activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (8):809-830.
46 Remagnino P, Tan T and Baker K. Multi-agent visual surveillance of dynamic scenes. Image and Vision Computing, 1998, 16(8):529-532.
47 徐瑞鑫．复杂背景下实时目标跟踪与识别研究．长春：中国科学院长春科学精密机械与物理研究所，2002．
48 唐仁圣．空中目标实时跟踪算法研究及系统设计．重庆：重庆大学，2004．
49 米长伟．电视制导炸弹目标图像实时处理技术研究．南京：南京理工大学，2005．
50 胡明昊．复杂背景下运动目标的实时跟踪．南京：南京理工大学，2002．
51 杨宜禾，周维真．成像跟踪技术导论．西安：西安电子科技出版社，1992．
52 徐之海，李奇．现代成像系统．北京：国防工业出版社，2001．
53 李象霖．三维运动分析[M]．合肥：中国科学技术大学出版社，1994．
54 石友学．图像匹配中若干问题的研究．大连：大连理工大学，2004．
55 王红梅，张科，李言俊．图像匹配研究进展．计算机工程与应用，2004，19：42～44，77．
56 魏伟波，芮筱亭．不变矩方法研究．火力与指挥控制，2005(录用)．
57 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: 511-518.
58 P. Viola, M. Jones. Rapid real-time object detection. Process of IEEE workshop on Statistical and Computational Theories of Vision. Vancouver, Canada, July 2001.
59 R. Lienhart and J. Maydt. An extended set ofhaar-like features for rapid object detection. IEEE ICIP 2002, Vol. 1, pp. 900-903, 2002.
60 Y. Freund and R. E. Schapire. A short introduction to boosting. Journal of Japanese Society for Artificial Intelligence, 14(5):771-780, September 1999. Appearing in Japanese, translation by Naoki Abe.
61 R. E. Schapire. A brief introduction to boosting. In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, 1999.
62 R. Meir and G. Ratsch. An introduction to boosting and leveraging. In S. Mendelson and A. Smola, editors, Advanced Lectures on Machine Learning, LNCS, pages 119-184. Springer, 2003. In press. Copyright by Springer Verlag.
63 Schapire R E, Freund Y, Bartlett P, et al. Boosting the margin: A new explanation for the effectiveness of voting methods. ICML 1997. Los Alamitos: IEEE Computer Society Press, 1997: 322-330.
64 沈学华，周志华，吴建鑫等．Boosting和Bagging综述．计算机工程与应用．2000，12：31～32，40．
65 L. Breiman. Bagging Predictors. Machine learning, 1996, 24(2):123-140
66 Y. Freund and R. E. Schapire. Experiments with a new boosting algorithm. 1996.
67 武勃，黄畅，艾海舟等．基于连续AdaBoost算法的多视角人脸检测．计算机研究与发展．2005，42(9)：1612～1621．
68 R. Lienhart and V. Pisarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection. MRL Technical Report, Intel Labs, 2002.
69 H. A. Rowley, S. Baluja and T. Kanade. Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, No. 1, pp. 23-38, 1998.
70 Jose Barreto, Paulo Menezes and Jorge Dias. Human-robot interaction based on Haar-like features and eigenfaces. In: International Conference on Robotics and Automation, 2004.
71 郑峰，杨新．基于AdaBoost算法的人脸检测．计算机仿真，2005，22(9)：167-169，253．
72 赵江，徐鲁安．基于AdaBoost算法的目标检测．计算机工程，2004，30(4)：125-126，172
73 孔凡芝，张兴周，谢耀菊．基于AdaBoost算法的人脸检测技术．应用科技，2005，32(6)：7-9．
74 Papageorgiou C, Oren M. and Poggio T. A general framework for object detection. International Conference on Computer Vision, 1998.
75 K. Fukunaga and L. D. Hostetler. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Information Theory, 1975, Vol. 21: 32-40.
76 耿振伟，蒋咏梅，粟毅．一种巨幅遥感影像中机场ROI检测算法．电子与信息学报，2005，27(11)：1770-1773
77 D. Comaniciu, P. Meer. Mean Shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Machine Intell, May 2002(24): 603-619.
78 Papageorgiou C, Oren M. and Poggio T. A general framework for object detection. In: International Conference on Computer Vision, 1998
79 G. R. Bradski. Computer vision face tracking for use in a perceptual user interface. Intel Technology Journal, 1998, 2nd Quarter.
80 D. Comaniciu, V. Ramesh, P. Meer. The variable bandwidth Mean Shift and data-driven scale selection. 8th International Conference on Computer Vision, Vancouver, Canada, July 2001, Vol. I: 438-445.
81 D. Comaniciu, V. Ramesh, P. Meer: Kernel-based object tracking. IEEE Trans. Pattern Anal. Machine Intell. 2003(25): 564-577.
82 D. Comaniciu, P. Meer: Mean Shift analysis and applications. 7th International Conference on Computer Vision, Kerkyra, Greece, September 1999: 1197-1203.
83 P. Meer, C.V. Stewart, D.E. Tyler. Robust computer vision: An interdisciplinary challenge. Computer Vision and Image Understanding, 2000, Vol.78: 1-7.
84 B. Georgescu, I. Shimshoni, P. Meer. Mean Shift based clustering in high dimensions: A texture classification example. 9th International Conference on Computer Vision, Nice, France, 2003. 8: 456-463.
85 B. Georgescu, P. Meer. Point Matching Under Large Image Deformations and Illumination Changes. IEEE Trans. Pattern Anal. Machine Intell. 2004, Vol. 26: 674-689.
86 Dorin comaniciu, Visvanathan Ramesh, Peter Meer. Real-Time Tracking of Non-Rigid Objects using Mean Shift. IEEE CVPR 2000.
87 Alper Yilmaz, Khurram Hassan-Shafique, Mubarak Shah, Niels da Vitoria Lobo. Target-Tracking in FLIR Imagery Using Mean-Shift and Global Motion Compensation. Workshop on Computer Vision Beyond the Visible Spectrum, with CVPR 2001, Kauai, Hawaii, 2001.
88 Sohaib Khan, Mubarak Shah. Object Based Segmentation of Video Using Color, Motion and Spatial Information. IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2001, Kauai, Hawaii, 2001.
89 Omar Javed and Mubarak Shah. Tracking And Object Classification For Automated Surveillance. The seventh European Conference on Computer Vision, Denmark, 2002.
90 C. Yang, R. Duraiswami, D. DeMenthon and L. Davis. Mean-Shift Analysis Using Quasi-Newton Methods. In IEEE International Conference on Image Processing, 2003, Vol.3: 447 - 450.
91 C. Yang, R. Duraiswami, A. Elgammal and L. Davis. On-Line Kernel-Based Tracking in Joint Feature-Spatial Spaces. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004.
92 C. Yang, R. Duraiswami, A. Elgammal and L. Davis. Real-Time Kernel-Based Tracking in Joint Feature-Spatial Spaces. Technical Report CS-TR-4567, Dept. of Computer Science, University of Maryland, College Park, 2004.
93 (美)Linda G．Shapiro，George C．Stockman著，赵清杰，钱芳，蔡利栋译．Computer Vision．北京：机械工业出版社，2005．
94 吴晓娟，翟海亭，王磊等．一种改进的CamShift手势跟踪算法．山东大学学报(工学版)，2004，34(6)：120～124
95 杨洪丰．视频序列中运动目标的实时分割与跟踪．西安：西安理工大学，2003
96 陆文广．快速目标自动识别与跟踪方法及实现研究．南京：南京理工大学，2005．
97 王宾．视频序列中运动目标检测与跟踪有关问题的研究．西安：西北大学电子系．2004
98 郑海滨．视频监视方法研究．西安：西北工业大学．2002
99 John G. Allen, Richard Y. D. Xu, Jesse S. Jin. Object Tracking Using CamShift Algorithm and Multiple Quantized Feature Spaces. Australian Cmputer Society, Inc. 2004
100 Andre Senior and Sabri Tosunoglu. Hybrid Machine Vision Control. Florida Conference on Recent Advances in Robotics. Gainesville, Florida, 5-6 May 2005.
101 Grewal, Mohinder S. and Angus P. Andrews. Kalman Filtering Theory and Practice. Upper Saddle River, NJ USA, Prentice Hall. 1993.
102 Welch and Bishop. An introduction to the Kalman Filter. UNC-Chapel Hill, TR 95-041, April5, 2004.
103 陈峰．Blackfin系列DSP原理与系统设计．北京：电子工业出版社，2004
104 魏伟波，芮筱亭．图像边缘检测方法研究．计算机工程与应用，2006(录用)
105 魏伟波，芮筱亭，刘军等．基于OpenGL的火炮膛内压力变化的动画仿真．系统仿真学报，2006，18(3)：666～668．
106 杨富锋，芮筱亭，魏伟波．用小波方法估计密度函数．兵工学报，2005(录用)