摘要
本文主要研究内容是视觉目标的跟踪问题,其中涉及视频环境下运动目标的自
动分割、运动目标跟踪以及摄像机标定等方面的研究。视觉目标的跟踪问题是机器
视觉研究中的一个重要分支,是高级机器视觉研究的基础,有着广泛的应用,例
如:视频监视、虚拟现实、运动目标捕获、智能交通、军事制导等。
在运动目标自动分割研究中,介绍了现有的主要分割算法,针对运动对象容易
受到噪声影响的问题,提出了一种结合时域与空间域的改进瞬时差分算法,并给出
西安理工大学硕士学位论文
实验结果。研究了背景图像的统计特性,提出了一种可白适应更新的背景建模方
法,将其应用在本文中,取得了满意的效果,并对影响分割效果的噪声问题、阴影
问题进行了分析,给出了解决方法,实验证明了算法的可行性。
在运动目标的跟踪研究中,就跟踪问题的特点,分析了不同的跟踪模式与当前
主要的研究方向,结合现有算法,提出了一种具有鲁棒性的白适应卜尔曼跟踪模
型,可以较好地表征目标的机动运动,从而能够跟踪目标的运动。从算法的适用性
和可行性两方面考虑,选择既可靠义易于实现的颜色直方图匹配算法,在
刀加“配人“弓少口距离下进行了目标匹配。
在摄像机标定问题的研究中,介绍了经典的标定算法与土动视觉的白标定算
法。针对本课题的研究特点,利用一种基于本质矩阵的自标定算法,实现了2维目
标的3维映射,从而为下一步基于视觉的机器人目标捕获提供了基础。
关键词:运动目标检测,目标跟踪,摄像机标定,卡尔曼滤波
This thesis discusses visual tracking problem. It involves in the following several topics, moving objects detection, tracking the objects and camera calibration. Visual tracking is one of the most important branches in machine vision, and is the basis of some advanced machine vision. It has great applications such as video surveillance, virtual reality, moving object capture, intelligence transportation and military guidance.On the research of moving objects detection, primary algorithms of segmentation are introduced, and then an improved algorithm based on adjacent frame difference is proposed. Statistic characteristic of the background image is investigated. An adaptive-
refreshed background model is proposed. Noise problem and shadow problem of detecting objects are investigated. Experiments are given to show the validity of algorithm.On the research of the tracking objects, different tracking models and current research aspects are discussed. An adaptive kalman filter-tracking model is proposed to track the objects maneuverable motion. A matching algorithm based on color histogram is used in the objects matching under Bhattacharyya space.On the research of the camera calibration, classic calibration algorithms and self-calibration algorithms are introduced. By means of a self-calibration, mapping from object of 2D to 3D is realized. It is the base of further topic of object capture.
引文
[1] 贾云得.机器视觉.北京:科学出版社,2004年.
[2] 李智勇,沈振康,杨卫平等.动态图像分析.国防工业山版社,1999.
[3] C. Anderson, Peter Burt, and G. van der Wal. "Change detection and tracking Using pyramid transformation techniques".In Proceedings of SPIE-Intelligent Robots and Computer Vision, 1985, Vol.579, P72-78.
[4] I.Haritaoglu, Larry S. Davis, and D.Harwood. "W4: who? when? where? what? a real time system for detecting and tracking people",Japan: International conference on face and gesture recognition, 1998.
[5] C.Wren, A.Azarbayejani,T.Darrell et al. "Pfinder:Real-time tracking of the human body". IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7) : 780-785.
[6] J.Barron,D.Fleet,S.Beauchemin. "Performance of optical flow techniques". International Journal of Computer Vision, 12(1) ,1994 : 20-77.
[7] 付永会,张风超,张宪民.一种改进的基于颜色直方图的实时目标跟踪算 法.数据采集与处理,3(16) ,2001.
[8] D.Comaniciu,V.Ramesh,P.Meer. "Kernel-Based Object Tracking".IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003,5(25) : 654-577.
[9] D.P.HuttenIocker,G.A.Klanderman,W.J.Rucklidge."Comparing images using the Harsdorf distance". IEEE Trans PAMI, 1993,15(2) : 850-860.
[10] M.Isard and A. Blake, "Condesation-Conditional Density Propagation for Visual Tracking". Int'1 J. Computer Vision, 1998,1(29) .
[11] C.Gu,M.C.Lee. "Semi-automatic segmetation and tracking of semantic video objects". IEEE Transactions on Circuits and Systems for Video Technology. 1998,vol.8, 572-584.
[12] Y.Kameda,M.Minoh. "A human motion estimation method using 3-successive video frame". Proc. Of International Conference on Virtual Systems and Multimedia. 1996.
[13] 章硫晋编著.图像分割.北京:科学出版社,2001.
[14] 叶中付,李厚强等,一种基于高阶累积量的运动目标检测新方法.计算机工 程与应用,2002.
[15] T.Meier,K.N.Ngun. "Video Segmentation for Content-Based Coding". IEEE Trans. On Circuits and Systems for Video Technology, 1999,9(8) : 1190-1203.
[16] Stauffer C, Grimson W E L. "Adaptive Background Mixture Models for Real-Time Tracking". In:Proc IEEE Conf on Computer Vision and Pattern Recognition, Ft.Collins:IEEE Computer Society, 1999,246-252.
[17] Robert T. Collins, Alan J. Lipton, "Introduction to the Special Section on Video Surveillance," IEEE Transactions on pattern analysis and machine intelligence, Vol 22, No. 8, August 2000.
[18] MacKenna, Y. Raja, S. Gong, "Tracking Color Objects using Adaptive Mixture Models," Image and Vision Computing, 17:223-229,1999.
[19] MacKenna, Y. Raja, S. Gong, "Tracking Color Objects using Adaptive Mixture Models," Image and Vision Computing, 17:223-229,1999.
[20] T O lson, F Brill. "Moving Object Detection and Event Recognition Algorithms for Smart Cameras". P roc. DARPA Image Understanding Work shop, M ay 1997.
[21] Chris Stauffer,W.Eric and L.Grimson, "Learning Patterns of Activity Using Real-time Tracking". IEEE Trans. On Pattern Analysis and Machine Intelligence,vol. 22. no.8,Aug.2000.
[22] Robert T. Collins, Alan J. Lipton, "Introduction to the Special Section on Video Surveillance," IEEE Transactions on pattern analysis and machine intelligence, Vol 22, No. 8, August 2000.
[23] K.R.Castleman. Digital Image Processing.北京:清华大学出版社, 1998.
[24] P.Kaew TrakulPong , R. Bowden, "An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection",Proc. 2nd European Workshop on Advanced Video Based Surveillance Systems,AVBS01. Sept 2001.
[25] Mae Y, Shirai Y, M iura J, et al. " Object t racking in cluttered background based on optical flow and edges". 13th International Conference onPattern Recognition, 1996. 196-200.
[26] 徐立中.数字图像的智能信息处理.北京:国防工业出版社,2001.
[27] Serra and Soille. Mathematical Morphology and Its Applications to Image and Signal Processing. Boston: Kluwer Academic Publishers, 1996.
[28] Haralick R, Zhuang X. " Image analysis using mathematical morphology" IEEE Trans.on Pattern Analysis and Machine Intelligence, 1987, 9 (4) : 532-550.
[29] Stauder J, Mech R, Ostermann J. "Detection of moving cast shadows for object segmentation". IEEE Transaction on Multimedia, 1999 ,1(1) :65-76.
[30] Cucchiara R, Grana C, PiccardiM et al. "Improving shadow suppression in moving object detection with HSV co lo r information". In: Proceedings of IEEE Intelligent Transportation Systems Conference, Oak land, CA, U SA ,2001: 334-339.
[31] Takayuki Nakamura, Tsukasa Ogasawara. On2line visual learningmethod for color image segmentation and object tracking. Http :/ / robotics. aist-nara. ac. jp/ takayuki/ iros99cmr. PDF, 2003-07-08.
[32] P.Kaew TrakulPong , R. Bowden, "An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection ",Proc. 2nd European Workshop on Advanced Video Based Surveillance Systems,AVBS01. Sept 2001.
[33] Thomas Meier, KingN.Ngan. "Automatic Segmentation of Moving Objects for Video Object Plane Generation". IEEE Transactions on Circuits and Systems for Video Technology, 1998-09, 8(5) : 525-538.
[34] Gu Chuang, Lee Ming-chieh. "Semiautomatic Segmentation and Tracking of Semantic Video Objects". IEEE Transactions on Circuits and Systems for Video Technology, 1998-09, 8(5) : 572-584.
[35] Haritaoglu.I, Harwood, D,etc, "Active outdoor surveillance". Proceedings, International Conference on Image Analysis and Processing, 1999,1096-1099.
[36] Christopher Rasmussen, Gregory D.Hager. "Probabilistic data association method for tracking complex visual objects". IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000-06, 23(6) : 560-576.
[37] Fabrice Moscheni, et al. "Object tracking based on temporal and spatial information". ISO/IEC JTC1/SC29/WG11MPEG96/M0962.
[38] Patras, L.; Hendriks, E.A.; Lagendijk, R.L. "Video Segmentation by MAP Labeling of Watershed Segments". IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001-03, 23(3) : 326-332.
[3
[39] G.S. Young and R.Chellappa, "3D Motion Estimation Using a Sequence of Noise Stereo Images". IEEE Conference on Computer Vision and Pattern Recognition, June 1988:710-716.
[40] Kalman R E. "A New Approach to Linear filtering and Prediction Theory". ASME. Journal of Basic Eng, 1960,82D: 35-46.
[41] 付梦印,邓志红,张继伟. Kalman滤波理论及其在导航系统中的应用.北 京:科学出版社,2003.
[42] D.M. Gavrila,"The analysis of human motion and its application for visual surveillance," Proc. of the 2nd International Workshop on Visual Surveillance, Fort Collins, USA, 1999.
[43] 周宏仁,敬忠良.王培德.机动目标跟踪.北京:国防工业出版社.
[44] Zhong Y, Jain A K, Dubuisson2Jolly M. "Object Tracking Using Deformable Templates ". IEEE Trans. Pattern Analysis and Machine Intelligence, 2000, 22 (5) : 544-549.
[45] Smith,S.M. and Brady,J.M.(1995) . "Asset-2: Real-time motion segmentation and shape tracking", IEEE Trans. Pattern Analysis and Machine Intell.17 (8) : 814-820.
[46] D.Comaniciu,Vramesh,P.Meer "Kernel-Based Object Tracking".IEEE Transactions on Pattern Analysis and Machine Intelligence.2003, 5 (25) :564-577.
[47] 郑南宁.计算机视觉与模式识别.北京:国防工业出版社,1998.
[48] Abdel-Aziz Y.I., Karara H.M.. "Direct linear transformation from comparator coordinates into object Photogrammetry".Urbana:Univ. of Illlinois at Urbana Champaign,1971. 1-18.
[49] Tsai R.Y. "A versatile and calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV camera and lense". IEEE Journal of Automation, 1987,3(4) : 323-334.
[50] Maybank S J, Faugeras O D. "A theory of self-calibration of a moving camera. International Journal of Computer Vision", 1992 ,8 (2) : 123-151.
[51] 李华,吴福朝,胡占义.一种新的线性摄像机自标定方法.计算机学报, 2000,23(11) 1121-1129.
[5
[52] 刘涵,刘丁,杨延西.基于遗传算法模式匹配的机器人实时伺服.机器人, 2001,23(7) 732-736.
[53] Yan-Xi Yang, Ding Liu, Han Liu, Robot end-effector 2D visual positioning using neural networks, Proceedings of the Second IEEE Internation Conference on Machine Learning and Cybernetics, November 02-05,2003, Sheraton Hotel, Xi'an, China.
[54] Liu Han, Liu Ding, Li Qi, Real-time recognition of road traffic sign in moving scene image using genetic algorithm, Proceeding of the 4th IEEE World Congress on Intelligent Control and Automation, 2002, Shanghai, China, p1027-1030.