复杂背景条件下的运动目标检测与跟踪的研究
|
摘要
移动目标检测与跟踪是计算机视觉学科研究的一个重点课题。在视频监控、安防布控、武器装备等方面都有广泛的应用。经过多年来国内外研究者的共同努力,移动目标检测与跟踪技术已经得到长足的发展,取得了很多突破性的研究成果。但在实际复杂的现场环境中,光照变化、目标遮挡、阴影干扰、形变影响等的存在,给该技术提出了新的挑战。要很好的解决这些问题,并达到实际应用的要求,需要设计实时性和鲁棒性兼顾的新算法。本文深入学习若干核心算法,并在此基础上做了新的尝试,本文主要工作如下:
1.深入学习了国内外移动目标检测与跟踪的经典方法,并通过实验比较,了解各自优缺及适合的应用条件。在此基础上,提出了一种基于多特征目标建模的Mean-Shift及Particle Filter相结合的目标跟踪算法。目标建模融合了颜色、边缘、纹理等一般目标特征,另外还借鉴图像质量评价研究领域中的结构相似度(SSIM)概念,提取目标的结构信息作为第四个融合子特征。改进了多特征融合方法,得到鲁棒性较高的目标模型。在改进的MSPF(Mean-Shift & Particle Filter)跟踪框架下最终实现对移动目标的跟踪。通过实验验证该算法跟踪准确。
2.提出了一种基于行扫描的目标提取算法,该算法对图像进行逐行扫描,直接提取目标,不需要对全图进行链码跟踪。该算法在嵌入式DSP开发中结合DMA双缓冲技术,可以大大节省算法时间开销。
3.将多特征融合的MSPF目标跟踪算法移植到ADSP BF561开发平台上,解决移植中的图像格式转化等若干问题。结合基于行扫描的目标提取算法,优化目标跟踪算法在该平台上的实现。在移植基础上做C语言级和汇编级代码优化,进一步提升算法执行效率,最终满足目标跟踪应用的实时性要求。
Moving target detection and tracking is one of the most important subjects in computer vision. It has important and practical value together with wide developmental prosperity in video surveillance, security defense, and military hardware and so on. After years of joint efforts made by domestic and foreign researchers, this technology has been developed rapidly and achieved a lot of significant results. However, there are new challenges existing in practice complex environment, illumination changes, target occlusion, shadow interference, the impact of the presence of deformation and so on. To solve these problems and compensate the practical need of the requirements, it is necessary to design new algorithm of real-time performance and high robustness. This paper deeply studied many core algorithms and did new trial based on those. The main works in this paper are as follows:
1. By deeply investigating many classical methods of moving target detection and tracking, this paper points out their advantages, disadvantages and the appropriate application conditions of them. This paper proposes an algorithm based on multi-featured modeling, Mean Shift and Particle Filter combining. Object modeling combines the color, edge, texture and other general features. Using the concept of the structural similarity (SSIM) in the field of image quality evaluation for reference, this paper extracts the structural information of the target as the fourth sub-feature. Also,the paper improves the multi-feature fusion method to get a higher robustness target model. Finally this paper track objects in the improved MSPF (Mean Shift & Particle Filter) tracking framework and test the algorithm by numerous experiments.
2. The paper presents an object extraction algorithm based on line scanning. This algorithm scans the image line by line to extract object, other than searching object in whole area of images. In embedded DSP development, this algorithm is combined with DMA and ping-pong buffer, which could greatly improve the speed of the operation.
3. This paper transplants the multi-feature fusion MSPF tracking algorithm to ADSP BF561 development platform. Many problems in migration are Solve including image format conversion and so on. The line-scanning object extraction algorithm is used to optimize this tracking algorithm in the implementation on this platform. C-level and assembly-level code optimization are also included in to further improve the efficiency to meet the real-time requirement of the target tracking application.
1.深入学习了国内外移动目标检测与跟踪的经典方法,并通过实验比较,了解各自优缺及适合的应用条件。在此基础上,提出了一种基于多特征目标建模的Mean-Shift及Particle Filter相结合的目标跟踪算法。目标建模融合了颜色、边缘、纹理等一般目标特征,另外还借鉴图像质量评价研究领域中的结构相似度(SSIM)概念,提取目标的结构信息作为第四个融合子特征。改进了多特征融合方法,得到鲁棒性较高的目标模型。在改进的MSPF(Mean-Shift & Particle Filter)跟踪框架下最终实现对移动目标的跟踪。通过实验验证该算法跟踪准确。
2.提出了一种基于行扫描的目标提取算法,该算法对图像进行逐行扫描,直接提取目标,不需要对全图进行链码跟踪。该算法在嵌入式DSP开发中结合DMA双缓冲技术,可以大大节省算法时间开销。
3.将多特征融合的MSPF目标跟踪算法移植到ADSP BF561开发平台上,解决移植中的图像格式转化等若干问题。结合基于行扫描的目标提取算法,优化目标跟踪算法在该平台上的实现。在移植基础上做C语言级和汇编级代码优化,进一步提升算法执行效率,最终满足目标跟踪应用的实时性要求。
Moving target detection and tracking is one of the most important subjects in computer vision. It has important and practical value together with wide developmental prosperity in video surveillance, security defense, and military hardware and so on. After years of joint efforts made by domestic and foreign researchers, this technology has been developed rapidly and achieved a lot of significant results. However, there are new challenges existing in practice complex environment, illumination changes, target occlusion, shadow interference, the impact of the presence of deformation and so on. To solve these problems and compensate the practical need of the requirements, it is necessary to design new algorithm of real-time performance and high robustness. This paper deeply studied many core algorithms and did new trial based on those. The main works in this paper are as follows:
1. By deeply investigating many classical methods of moving target detection and tracking, this paper points out their advantages, disadvantages and the appropriate application conditions of them. This paper proposes an algorithm based on multi-featured modeling, Mean Shift and Particle Filter combining. Object modeling combines the color, edge, texture and other general features. Using the concept of the structural similarity (SSIM) in the field of image quality evaluation for reference, this paper extracts the structural information of the target as the fourth sub-feature. Also,the paper improves the multi-feature fusion method to get a higher robustness target model. Finally this paper track objects in the improved MSPF (Mean Shift & Particle Filter) tracking framework and test the algorithm by numerous experiments.
2. The paper presents an object extraction algorithm based on line scanning. This algorithm scans the image line by line to extract object, other than searching object in whole area of images. In embedded DSP development, this algorithm is combined with DMA and ping-pong buffer, which could greatly improve the speed of the operation.
3. This paper transplants the multi-feature fusion MSPF tracking algorithm to ADSP BF561 development platform. Many problems in migration are Solve including image format conversion and so on. The line-scanning object extraction algorithm is used to optimize this tracking algorithm in the implementation on this platform. C-level and assembly-level code optimization are also included in to further improve the efficiency to meet the real-time requirement of the target tracking application.
引文
[1] R. Collins, et al. A System for Video Surveillance and Monitoring: VSAM Final Report. Carnegie Mellon University. Technical Report CMU-RI-TR-00-12.2000.[R].
[2] I. Haritao, D. Harwood, L. S. Davis. W4: Real-Time Surveillance of People and Their Activities[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence. Aug. 2000, 22(8): 809~830.
[3] C. Wren, A. Azarbayejan, T. Darrell, A. Pentland. Pfinder: Real-Time Tracking of the Human Body[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence. July. 1997, 19(7): 780~785.
[4] M Bogaert, N Chieq, P Cornez, et.al., The PASSWORDS project[J]. Proceedings of IEEE International Conference on Image Processing. Switzerland: Lansanne, 1996, 3:675~678.
[5] S. M. Smith. ASSET-2: Real-time Motion Segmentation and Object Tracking[J]. Real-Time Imaging, 1998, 4: 21~40.
[6] M. Saptharishi, C. S. Oliver, C. P. Diehl, K. S. Bhat, J. M. Dolan, A. Trebi-Ollennu, P. K. Khosla. Distributed Surveillance and Reconnaissance Using Multiple Autonomous ATVs: CyberScout[P]. IEEE Trans. on Robotics and Automation, Oct. 2002, 18(5): 826~836.
[7]孙涵.基于红外图像的道路识别与运动目标跟踪[D].[博士毕业论文].南京:南京理工大学,2005年.
[8]黄文清,汪亚明.基于自适应混合模型和区域特征的多目标跟踪与检测[J].计算机测量与控制,2003,11(9):648~650, 654.
[9] S. Chen, M. Shyu, S. Peeta and C. Zhang. Learning-Based Spatio-Temporal Vehicle Tracking and Indexing for Transportation Multimedia Database Systems[J]. IEEE Trans. on Intelligent Transportation Systems. Sept. 2003, 4(3): 154~167.
[10] S. Park, J. K. Aggarwal. Segmentation and Tracking of Interacting Human Body Parts under Occlusion and Shadowing[J]. Proceedings of the Workshop on Motion and Video Computing. Orlando,FL, December 2002,105~111.
[11] Suchendra M. Bhandarkar, Xingzhi Luo. Integrated detection and tracking of multiple faces using particle filtering and optical flow-based elastic matching[J]. Computer Vision and Image Understanding. 2009,113:708~715.
[12] J. Black, T. Ellis, P. Rosin. Multi View Image Surveillance and Tracking. Proceedings of the Workshop on Motion and Video Computing(MONTION’02) [C].Orlando, December2002,169~173.
[13] J Ren, J Orwell, GA Jones, M Xu. Tracking the soccer ball using multiple fixed cameras[J]. Computer Vision and Image Understanding,. 2009,113:633~642.
[14] S. Guler, J. M. Griffith, I. A. Pushee. Tracking and Handoff Between Multiple Perspective Camera Views[J]. Proceedings of the 32nd Applied Imagery Pattern Recognition Workshop. 2003,275~281.
[15]万缨,韩毅,卢汉清.运动目标检测算法的探讨[J] [J].计算机仿真,2006,23(10):212~226.
[16] Lipton A, Fujiyoshi H and Patil R. Moving target classification and tracking from real-time video[J]. IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 1998, 8~14.
[17] Francois A. Mediiono G. G, Adaptive color background modeling for real-time segmentation of Video streams[J]. Proceedings of International Conference on Imaging Science, Systems and Technology, 1999,227~232.
[18] Zhou Y, Tao H, A Background Layer Model for Object Tracking through Occlusion[C]. Procedings of the 9th IEEE International Conference on Computer Vision, 2003, 2:1079~1085.
[19] Karmann K and Brandt A. Moving object recognition using an adaptive background memory[J]. Image Processing and Moving Object Recognition. Elsevier, Amsterdam, The Netherlands, 1990,47~52.
[20] Kilger M. A shadow handler in a video-based real-time traffic monitoring system[J]. Proc IEEE Workshop on Applications of Computer Vision, Palm Springs, CA, 1992, 1060~1066.
[21] Kato J. Watanabe T. ,et al. An HMM/MRF– based stochastic framework for robust vehicle tracking[J]. IEEE Transactions on Intelligent Transportation Systems, 2004,5(3):142 ~154.
[22] McKenna S et al, Tracking groups of people[J]. Computer Vision and Image Understanding, 2000, 80 (1): 42~56.
[23] C.Stuaffer , W. E. L. Grimson, Adaptive Background Mixture Models for Real-time Tracking[J]. CVPR99, June, 1999.107~113.
[24] C. Stuaffer , W. E. L. Grimson, Learning Pattern of Activity using Real-time Tracking[J]. IEEE Transacntions on Pattern Analysis and Machine Intelligence, 2000,22(8):747~757.
[25] Power P.W., Schoonees J.A. Understanding Background Mixture Models for Foreground Sefmentation[J]. Proceedings of Image and Vision Computing. New Zealand, 200, 267~271.
[26] Monnet A. , Mittal A. , et al. Background Modeling and Subtraction of Dynamic Scenes[C]. Processings of 9th IEEE International Conference on Computer Vision, 2003, 2:1305~1312.
[27]周宾,李晓强,苏士美.实用户外监控异常检测策略[J].计算机工程,2003,29(16):16~18.
[28] Elgammal A.Duraiswami R., et al. Background and Foreground Modeling Using Nonparametrics Kernel Density Estimation for Visual Surveillance[J]. Procedings of IEEE, 2002, vol.90(2):1151~1163.
[29] Barron J, Fleet D, Beauchemin S. Performance of optical flow techniques[J]. International Journal of Computer Vision, 1994, 12 (1): 42~77.
[30] Meyer D, Denzler J and Niemann H. Model based extraction of articulated objects in image sequences for gait analysis[C]. IEEE International Conference on Image Processing, Santa Barbara, California 1997, 78~81.
[31] Ying Li Tian , Arun Hampapur. Robust Salient Motion Detection with Complex Background For Rreal-time Video Surveillance[J]. Proceedings of IEEE Workshop on Motion and Video Computing.2005,2(02):30~35.
[32] Simon Denman ,Vinod Chandran, Sridha Sridharan. An adaptive optical ?ow technique for person tracking systems[J]. Elsevier Pattern Recognition Letters 28 (2007) 1232~1239.
[33] Stringa E. Morphological change detection algorithms for surveillance applications[C]. British Machine Vision Conference, Bristol, UK, 2000, 402~411.
[34] Jorge Badenas , Bober M , and Pla F.Motion and intensity-based segmentation and its application to traffic monitoring[C]. In Proceedings, International Conferece on Image Analysis and Processings ICIAP’97 , Florence, Italy,1997,520~529.
[35] Polana R and Nelson R. Low level recognition of human motion[J]. In: Proc IEEE Workshop on Motion of Non-Rigid and Articulated Objects, Austin, TX, 1994, 77~82.
[36] Fukunaga K, Hostetler L. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition[J]. IEEE Trans. on Inform. Theory, 1975, 21(1): 32.
[37] Cheng Y. Mean Shift, Mode Seeking, and Clustering[J]. IEEE Trans. on Pattern Anal. Machine Intell., 1995, 17(8): 790.
[38] Comaniciu D, Meer P. Mean Shift: A Robust Application Toward Feature Space Analysis[J]. IEEE Trans. on Pattern Anal. Machine Intell., 2002, 24(5): 603.
[39] Yang C , Duraiswami R , Davis L. Efficient Mean-shift Tracking via a New Similarity Measure[C]. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition. 2005,1(1):176~183.
[40]李乡儒,吴福朝,胡占义.均值漂移算法的收敛性[J].软件学报,2005,16(3): 365.
[41] M Kass, A Witkin, D Terzopoulos. Snakes: Active contour models[J]. International Journal of Computer Vision, 1988,1(4):321~331.
[42] Menet S , Saint-Marc P , Medioni G. B-Snake: Implementation and application to stereo[J]. DARPA Image Understanding Workshop, 1990 ,720~726.
[43] Won Kim , Choon-Young Lee , Ju-Jang Lee. Tracking moving object using Snake’s jump based on image flow[J]. Mechatronics,2001,(11):119~216.
[44] Hong L. Multiresolutional Estimation Using Wavelet[J] Transform. IEEE Trans. On Aero Space and Electronic System,1993(29):1244 ~1251.
[45] M Isard , A Blake. Condensation-conditional density propagation for visual tracking[J]. Int. J. Comput. Vision, 1998,29(1):5 ~28.
[46] S Maskell, S Arulampalam, T Clapp. A tutorial on particle filters for on-line non-linear non-Gaussisn Bayesian tracking[J]. IEEE Tran. Signal Processing,2002,55(2): 174~188.
[47] C Chang, R Ansari. Kernel particle filter for visual tracking[J]. IEEE. Signal Processing, 2005,12(3):242~245.
[48] Zhaowen Wang , Xiaokang Yang , Yi Xu , Songyu Yu. CamShift Guided Particle Filter for Visual Tracking[J]. Elsevier Pattern Recognition Letters,2008,10:1016~1033.
[49] J Carmona Enrique, et.al., A new video segmentation method of moving objects based on blob-level knowledge[J]. Pattern Recognition letters, 2008(29):272~285.
[50]王欢.运动目标检测与跟踪技术研究[D]. [博士毕业论文].南京:南京理工大学,2009.3~4.
[51]刘亚,艾海舟,徐光佑.一种基于背景模型的运动目标检测与跟踪算法[J].信息与控制,2002,31(4):315-319,328.
[52] Kalman,R.E,Bucy,New results in linear filtering and prediction theory[J],Trans.ASME, Ser.D:J.Basic Eng 1961(83):95~108.
[53]王玉文,李智华.卡尔曼滤波在图象识别中的应用[J].哈尔滨师范大学自然科学学报,2005,21(3):3~6.
[54]刘振华.运动场景中目标检测与跟踪技术研究[D].[硕士学位论文] .南京:南京航空航天大学.2008.
[55] Comaniciu D.,P Meer, Mean Shift analysis and application[C],In Proceedings of theSeventh IEEE International Conference,Computer Vision,1999,2(2):1197~1203.
[56] Comaniciu D.,P Meer,Mean Shy. A Robust application toward feature space analysis[J],IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603~619.
[57] Comaniciu D.,P Meer,Robust Analysis of Feature Spaces:Color Image Segmentation[C], In Proc.1997 IEEE conf.,Computer Vision and Pattern Recognition,1997,750~755
[58]朱胜利.Mean Shift及相关算法在视频跟踪中的研究[D].[博士毕业论文].杭州:浙江大学.2006.
[59] Comaniciu D., Ramesh V,P Meer. Kernel-Based Object Tracking[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2003,25(5):564~577.
[60] Hammersley J M, Morton K W. Poorman’s Monte Carlo. J of the Royal Statistical Society B[M], 1954,16(1):23~38.
[61] Gordon N, Salmond D. Novel approach to non-liner and non-Gaussian Bayesian state estimation[J]. Proc of Institute Electric Engineering, 1993,140(2):107~113.
[62] Doucet A , Gordon N. Sequential Monte Carlo methods in practice[C].New York: Springer Verlag, 2001:133~134..
[63] Carlin,B.P.,N.G. Plson, and D.S. Stoffer, A Monte Carlo approach to nonnormal and nonlinear state-space modeling[J].Amer Statist Assoc,1992,87(418):493~500.
[64] Godsill S., A. Doucet, and M. West. Methodology for Monte Carlo smoothing with application to time-varying autoregressions[J]. In Proc. Int.Symp.Frontiers Time Series Modeling.2000.7~9.
[65] Crisan D. and A. Doucet. A Survery of convergence results on particle filtering merhods for practiotioners[J]. IEEE Trans. Speech and Audio Proc. 2002. 10(3):173~185.
[66] Satoh.Y. , T. Okatani, and K, Dguchi. A Color-base Tracking by Kalman Particle Filter[C]. in Proceedings of the 17th International Conference on Pattern Recognition. Yoshi, Japan 2004,3(3):502~505.
[67] Collins, R.T. Mean-Shift Blob Tracking through Scale Space[C]. in 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2003,2:234.
[68] Nummioar K. , E.Kolle-rMeier and L.Van Goo, Color Features for Tracking Non-rigid Objects[J], Chinese Jomual of Automatino, 2003.29(3):345~355.
[69] Curwen. Parallel implementation of Lagrangian aynamics for real-time snacks[C]. in Proc. British Machine Vision Conference, Spinger Verlag. New York.1991.23~25.
[70] Koller and J. Weber. Towards Robust Automatic Traffic Scene Analysis in Real-time[J]. In Peoceedings of Int’L Conf. Patern Recognition.1994,4(4):126~131.
[71] Birchfield S, Elliptical Head Tracking Using Intensity Gradients and Color Histograms[C]. In: Proceedings of the international conference on Computer Vision and Pattern Recognition, 1998, 232~237.
[72] Serby D, Koller-Meier E, Van-Gool L, Probabilistic object tracking using multiple features. Pattern Recognition[J], 2004, 2:184~187.
[73] Maggio E. and A. Cavallaro. Hybrid Particle Filter and Mean Shift tracker with adaptivetranstion modelC]. in Acoustics, Speech, and Signal Processing 2005.Proceedings. (ICASSP’05), 2005,2:221~224.
[74] Zhu W, Levinson S.E. Edge orientation-based multiview object recognition[C]. ICPR00, IEEE CS Press,2000:1936~1939.
[75] Porikli F. Integral histogram:A fast way to extract histograms in Cartesian spaces[J]. CVPR05, Pages I San Diego:IEEE CS Press, 2005:829~836.
[76] Milan Sonka, Vaclav Hlavac, Roger Boyle.图像处理、分析与机器视觉(艾海舟武勃等) [M] .人民邮电出版社.2003.
[77] J. Serra and G. Verchery. Machematical morphology applied to fibre composite materials[M]. Film Science Technology, 1973 6:141~158.
[78] J. M. Coggins and A.K. Jain. A spatial filtering approach to texture analysis[J]. Pattern Recognition Letters,1985, 3:195~203.
[79] M.Unser and M. Eden. Multiresolution feature extraction and selection for texture segmentation[J]. IEEE Transcation on Pattern Analysis and Machine Intelligence, 1989. 11(7):717~728.
[80] Rafael C. Gonzalez, Richard E. Woods.数字图像处理(第二版)(阮秋琦阮宇智等) [M].电子工业出版社.2003,540~543.
[81] Wang Zhou, Bovik A C, Sheikh H R. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13 (4) : 600~612.
[82] Serby D, Koller-Meier E, Van-Gool L, Probabilistic object tracking using multiple features[J]. Pattern Recognition, 2004, 2:184~187.
[83] Brasnett P, Mihayhova L, Bull D, Sequential Monte Carlo tracking by fusing multiple cues in video sequences[J]. Image Vision Computing. 2007, 25(8):1217~1227.
[84] Shan, C.S., Y.C. Wei,and T. Tam. Real time tracking by combing particle filter and Mean Shift[C]. in Proceeding of Sixth IEEE International Conference on Automatic Face and Gesture Recognition,2004,669~671.
[85]朱胜利,朱善安.基于卡尔曼滤波器组的Mean Shift模板更新算法[J].中国图像图形学报,2007,12(3).
[86] Freeman H. Computer Processing of Line Drawing Images[M]. Computing Surveys.1974.6(1) : 57~97.
[87]章毓晋.图像处理和分析[M].北京:清华大学出版社,l999.03.
[88]陈峰.Blackfin系列DSP原理与系统设计[M].北京:电子工业出版社.2003.
[89] RenMingwu YangJingyu SunHan. Tracing Boundary Contours in a Binary lmage[J]. Image and Vision Computing,2002,20(2) :125~131.
[90]杨万扣,任明武,杨静宇.数字图像中基于链码的目标面积计算方法[J].计算机工程2008.34(1):30~33.
[91] Tang G Y. A Discrete Version of Green’s Theorem[J]. IEEE Trans On Pattern Anal 1985 4(3):242~249.
[92] ADSP-BF561 Blackfin Processor Hardware Reference. Norwood[R], MA, USA: Analog Devices,Inc, 2005.
[93]罗志强,王耀南.Blackfin533的DMA技术及其在图像处理中的应用[J].国外电子元器件,2005,2:32~35.
[94]周鹏.JPEG2000编码器在Blackfin561上的实现与优化[D].[硕士学位论文] .西安:西安电子科技大学.2009.14~15.
[95] ADSP-BF561 Blackfin Data sheet[R]. Analog Devices, Inc.2006.
[96] ADSP-BF561 EZ-KIT Lite Board Design Database (Revision 2.1) [R]. Analog Devices, Inc.2006.
[97] Thorsten Lorenzen.Blackfin Processor SCCB Software Interface for Configuring I2CSlave Devices.Engineer to Engineer Note ANALOG DEVICES.March[R],2003.EE-204.
[98] David J. Katz Rick. Gentile Embedded Media Processing(陈喆等译) [M].北京:电子工业出版社.2007:80~82.
[2] I. Haritao, D. Harwood, L. S. Davis. W4: Real-Time Surveillance of People and Their Activities[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence. Aug. 2000, 22(8): 809~830.
[3] C. Wren, A. Azarbayejan, T. Darrell, A. Pentland. Pfinder: Real-Time Tracking of the Human Body[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence. July. 1997, 19(7): 780~785.
[4] M Bogaert, N Chieq, P Cornez, et.al., The PASSWORDS project[J]. Proceedings of IEEE International Conference on Image Processing. Switzerland: Lansanne, 1996, 3:675~678.
[5] S. M. Smith. ASSET-2: Real-time Motion Segmentation and Object Tracking[J]. Real-Time Imaging, 1998, 4: 21~40.
[6] M. Saptharishi, C. S. Oliver, C. P. Diehl, K. S. Bhat, J. M. Dolan, A. Trebi-Ollennu, P. K. Khosla. Distributed Surveillance and Reconnaissance Using Multiple Autonomous ATVs: CyberScout[P]. IEEE Trans. on Robotics and Automation, Oct. 2002, 18(5): 826~836.
[7]孙涵.基于红外图像的道路识别与运动目标跟踪[D].[博士毕业论文].南京:南京理工大学,2005年.
[8]黄文清,汪亚明.基于自适应混合模型和区域特征的多目标跟踪与检测[J].计算机测量与控制,2003,11(9):648~650, 654.
[9] S. Chen, M. Shyu, S. Peeta and C. Zhang. Learning-Based Spatio-Temporal Vehicle Tracking and Indexing for Transportation Multimedia Database Systems[J]. IEEE Trans. on Intelligent Transportation Systems. Sept. 2003, 4(3): 154~167.
[10] S. Park, J. K. Aggarwal. Segmentation and Tracking of Interacting Human Body Parts under Occlusion and Shadowing[J]. Proceedings of the Workshop on Motion and Video Computing. Orlando,FL, December 2002,105~111.
[11] Suchendra M. Bhandarkar, Xingzhi Luo. Integrated detection and tracking of multiple faces using particle filtering and optical flow-based elastic matching[J]. Computer Vision and Image Understanding. 2009,113:708~715.
[12] J. Black, T. Ellis, P. Rosin. Multi View Image Surveillance and Tracking. Proceedings of the Workshop on Motion and Video Computing(MONTION’02) [C].Orlando, December2002,169~173.
[13] J Ren, J Orwell, GA Jones, M Xu. Tracking the soccer ball using multiple fixed cameras[J]. Computer Vision and Image Understanding,. 2009,113:633~642.
[14] S. Guler, J. M. Griffith, I. A. Pushee. Tracking and Handoff Between Multiple Perspective Camera Views[J]. Proceedings of the 32nd Applied Imagery Pattern Recognition Workshop. 2003,275~281.
[15]万缨,韩毅,卢汉清.运动目标检测算法的探讨[J] [J].计算机仿真,2006,23(10):212~226.
[16] Lipton A, Fujiyoshi H and Patil R. Moving target classification and tracking from real-time video[J]. IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 1998, 8~14.
[17] Francois A. Mediiono G. G, Adaptive color background modeling for real-time segmentation of Video streams[J]. Proceedings of International Conference on Imaging Science, Systems and Technology, 1999,227~232.
[18] Zhou Y, Tao H, A Background Layer Model for Object Tracking through Occlusion[C]. Procedings of the 9th IEEE International Conference on Computer Vision, 2003, 2:1079~1085.
[19] Karmann K and Brandt A. Moving object recognition using an adaptive background memory[J]. Image Processing and Moving Object Recognition. Elsevier, Amsterdam, The Netherlands, 1990,47~52.
[20] Kilger M. A shadow handler in a video-based real-time traffic monitoring system[J]. Proc IEEE Workshop on Applications of Computer Vision, Palm Springs, CA, 1992, 1060~1066.
[21] Kato J. Watanabe T. ,et al. An HMM/MRF– based stochastic framework for robust vehicle tracking[J]. IEEE Transactions on Intelligent Transportation Systems, 2004,5(3):142 ~154.
[22] McKenna S et al, Tracking groups of people[J]. Computer Vision and Image Understanding, 2000, 80 (1): 42~56.
[23] C.Stuaffer , W. E. L. Grimson, Adaptive Background Mixture Models for Real-time Tracking[J]. CVPR99, June, 1999.107~113.
[24] C. Stuaffer , W. E. L. Grimson, Learning Pattern of Activity using Real-time Tracking[J]. IEEE Transacntions on Pattern Analysis and Machine Intelligence, 2000,22(8):747~757.
[25] Power P.W., Schoonees J.A. Understanding Background Mixture Models for Foreground Sefmentation[J]. Proceedings of Image and Vision Computing. New Zealand, 200, 267~271.
[26] Monnet A. , Mittal A. , et al. Background Modeling and Subtraction of Dynamic Scenes[C]. Processings of 9th IEEE International Conference on Computer Vision, 2003, 2:1305~1312.
[27]周宾,李晓强,苏士美.实用户外监控异常检测策略[J].计算机工程,2003,29(16):16~18.
[28] Elgammal A.Duraiswami R., et al. Background and Foreground Modeling Using Nonparametrics Kernel Density Estimation for Visual Surveillance[J]. Procedings of IEEE, 2002, vol.90(2):1151~1163.
[29] Barron J, Fleet D, Beauchemin S. Performance of optical flow techniques[J]. International Journal of Computer Vision, 1994, 12 (1): 42~77.
[30] Meyer D, Denzler J and Niemann H. Model based extraction of articulated objects in image sequences for gait analysis[C]. IEEE International Conference on Image Processing, Santa Barbara, California 1997, 78~81.
[31] Ying Li Tian , Arun Hampapur. Robust Salient Motion Detection with Complex Background For Rreal-time Video Surveillance[J]. Proceedings of IEEE Workshop on Motion and Video Computing.2005,2(02):30~35.
[32] Simon Denman ,Vinod Chandran, Sridha Sridharan. An adaptive optical ?ow technique for person tracking systems[J]. Elsevier Pattern Recognition Letters 28 (2007) 1232~1239.
[33] Stringa E. Morphological change detection algorithms for surveillance applications[C]. British Machine Vision Conference, Bristol, UK, 2000, 402~411.
[34] Jorge Badenas , Bober M , and Pla F.Motion and intensity-based segmentation and its application to traffic monitoring[C]. In Proceedings, International Conferece on Image Analysis and Processings ICIAP’97 , Florence, Italy,1997,520~529.
[35] Polana R and Nelson R. Low level recognition of human motion[J]. In: Proc IEEE Workshop on Motion of Non-Rigid and Articulated Objects, Austin, TX, 1994, 77~82.
[36] Fukunaga K, Hostetler L. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition[J]. IEEE Trans. on Inform. Theory, 1975, 21(1): 32.
[37] Cheng Y. Mean Shift, Mode Seeking, and Clustering[J]. IEEE Trans. on Pattern Anal. Machine Intell., 1995, 17(8): 790.
[38] Comaniciu D, Meer P. Mean Shift: A Robust Application Toward Feature Space Analysis[J]. IEEE Trans. on Pattern Anal. Machine Intell., 2002, 24(5): 603.
[39] Yang C , Duraiswami R , Davis L. Efficient Mean-shift Tracking via a New Similarity Measure[C]. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition. 2005,1(1):176~183.
[40]李乡儒,吴福朝,胡占义.均值漂移算法的收敛性[J].软件学报,2005,16(3): 365.
[41] M Kass, A Witkin, D Terzopoulos. Snakes: Active contour models[J]. International Journal of Computer Vision, 1988,1(4):321~331.
[42] Menet S , Saint-Marc P , Medioni G. B-Snake: Implementation and application to stereo[J]. DARPA Image Understanding Workshop, 1990 ,720~726.
[43] Won Kim , Choon-Young Lee , Ju-Jang Lee. Tracking moving object using Snake’s jump based on image flow[J]. Mechatronics,2001,(11):119~216.
[44] Hong L. Multiresolutional Estimation Using Wavelet[J] Transform. IEEE Trans. On Aero Space and Electronic System,1993(29):1244 ~1251.
[45] M Isard , A Blake. Condensation-conditional density propagation for visual tracking[J]. Int. J. Comput. Vision, 1998,29(1):5 ~28.
[46] S Maskell, S Arulampalam, T Clapp. A tutorial on particle filters for on-line non-linear non-Gaussisn Bayesian tracking[J]. IEEE Tran. Signal Processing,2002,55(2): 174~188.
[47] C Chang, R Ansari. Kernel particle filter for visual tracking[J]. IEEE. Signal Processing, 2005,12(3):242~245.
[48] Zhaowen Wang , Xiaokang Yang , Yi Xu , Songyu Yu. CamShift Guided Particle Filter for Visual Tracking[J]. Elsevier Pattern Recognition Letters,2008,10:1016~1033.
[49] J Carmona Enrique, et.al., A new video segmentation method of moving objects based on blob-level knowledge[J]. Pattern Recognition letters, 2008(29):272~285.
[50]王欢.运动目标检测与跟踪技术研究[D]. [博士毕业论文].南京:南京理工大学,2009.3~4.
[51]刘亚,艾海舟,徐光佑.一种基于背景模型的运动目标检测与跟踪算法[J].信息与控制,2002,31(4):315-319,328.
[52] Kalman,R.E,Bucy,New results in linear filtering and prediction theory[J],Trans.ASME, Ser.D:J.Basic Eng 1961(83):95~108.
[53]王玉文,李智华.卡尔曼滤波在图象识别中的应用[J].哈尔滨师范大学自然科学学报,2005,21(3):3~6.
[54]刘振华.运动场景中目标检测与跟踪技术研究[D].[硕士学位论文] .南京:南京航空航天大学.2008.
[55] Comaniciu D.,P Meer, Mean Shift analysis and application[C],In Proceedings of theSeventh IEEE International Conference,Computer Vision,1999,2(2):1197~1203.
[56] Comaniciu D.,P Meer,Mean Shy. A Robust application toward feature space analysis[J],IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603~619.
[57] Comaniciu D.,P Meer,Robust Analysis of Feature Spaces:Color Image Segmentation[C], In Proc.1997 IEEE conf.,Computer Vision and Pattern Recognition,1997,750~755
[58]朱胜利.Mean Shift及相关算法在视频跟踪中的研究[D].[博士毕业论文].杭州:浙江大学.2006.
[59] Comaniciu D., Ramesh V,P Meer. Kernel-Based Object Tracking[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2003,25(5):564~577.
[60] Hammersley J M, Morton K W. Poorman’s Monte Carlo. J of the Royal Statistical Society B[M], 1954,16(1):23~38.
[61] Gordon N, Salmond D. Novel approach to non-liner and non-Gaussian Bayesian state estimation[J]. Proc of Institute Electric Engineering, 1993,140(2):107~113.
[62] Doucet A , Gordon N. Sequential Monte Carlo methods in practice[C].New York: Springer Verlag, 2001:133~134..
[63] Carlin,B.P.,N.G. Plson, and D.S. Stoffer, A Monte Carlo approach to nonnormal and nonlinear state-space modeling[J].Amer Statist Assoc,1992,87(418):493~500.
[64] Godsill S., A. Doucet, and M. West. Methodology for Monte Carlo smoothing with application to time-varying autoregressions[J]. In Proc. Int.Symp.Frontiers Time Series Modeling.2000.7~9.
[65] Crisan D. and A. Doucet. A Survery of convergence results on particle filtering merhods for practiotioners[J]. IEEE Trans. Speech and Audio Proc. 2002. 10(3):173~185.
[66] Satoh.Y. , T. Okatani, and K, Dguchi. A Color-base Tracking by Kalman Particle Filter[C]. in Proceedings of the 17th International Conference on Pattern Recognition. Yoshi, Japan 2004,3(3):502~505.
[67] Collins, R.T. Mean-Shift Blob Tracking through Scale Space[C]. in 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2003,2:234.
[68] Nummioar K. , E.Kolle-rMeier and L.Van Goo, Color Features for Tracking Non-rigid Objects[J], Chinese Jomual of Automatino, 2003.29(3):345~355.
[69] Curwen. Parallel implementation of Lagrangian aynamics for real-time snacks[C]. in Proc. British Machine Vision Conference, Spinger Verlag. New York.1991.23~25.
[70] Koller and J. Weber. Towards Robust Automatic Traffic Scene Analysis in Real-time[J]. In Peoceedings of Int’L Conf. Patern Recognition.1994,4(4):126~131.
[71] Birchfield S, Elliptical Head Tracking Using Intensity Gradients and Color Histograms[C]. In: Proceedings of the international conference on Computer Vision and Pattern Recognition, 1998, 232~237.
[72] Serby D, Koller-Meier E, Van-Gool L, Probabilistic object tracking using multiple features. Pattern Recognition[J], 2004, 2:184~187.
[73] Maggio E. and A. Cavallaro. Hybrid Particle Filter and Mean Shift tracker with adaptivetranstion modelC]. in Acoustics, Speech, and Signal Processing 2005.Proceedings. (ICASSP’05), 2005,2:221~224.
[74] Zhu W, Levinson S.E. Edge orientation-based multiview object recognition[C]. ICPR00, IEEE CS Press,2000:1936~1939.
[75] Porikli F. Integral histogram:A fast way to extract histograms in Cartesian spaces[J]. CVPR05, Pages I San Diego:IEEE CS Press, 2005:829~836.
[76] Milan Sonka, Vaclav Hlavac, Roger Boyle.图像处理、分析与机器视觉(艾海舟武勃等) [M] .人民邮电出版社.2003.
[77] J. Serra and G. Verchery. Machematical morphology applied to fibre composite materials[M]. Film Science Technology, 1973 6:141~158.
[78] J. M. Coggins and A.K. Jain. A spatial filtering approach to texture analysis[J]. Pattern Recognition Letters,1985, 3:195~203.
[79] M.Unser and M. Eden. Multiresolution feature extraction and selection for texture segmentation[J]. IEEE Transcation on Pattern Analysis and Machine Intelligence, 1989. 11(7):717~728.
[80] Rafael C. Gonzalez, Richard E. Woods.数字图像处理(第二版)(阮秋琦阮宇智等) [M].电子工业出版社.2003,540~543.
[81] Wang Zhou, Bovik A C, Sheikh H R. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13 (4) : 600~612.
[82] Serby D, Koller-Meier E, Van-Gool L, Probabilistic object tracking using multiple features[J]. Pattern Recognition, 2004, 2:184~187.
[83] Brasnett P, Mihayhova L, Bull D, Sequential Monte Carlo tracking by fusing multiple cues in video sequences[J]. Image Vision Computing. 2007, 25(8):1217~1227.
[84] Shan, C.S., Y.C. Wei,and T. Tam. Real time tracking by combing particle filter and Mean Shift[C]. in Proceeding of Sixth IEEE International Conference on Automatic Face and Gesture Recognition,2004,669~671.
[85]朱胜利,朱善安.基于卡尔曼滤波器组的Mean Shift模板更新算法[J].中国图像图形学报,2007,12(3).
[86] Freeman H. Computer Processing of Line Drawing Images[M]. Computing Surveys.1974.6(1) : 57~97.
[87]章毓晋.图像处理和分析[M].北京:清华大学出版社,l999.03.
[88]陈峰.Blackfin系列DSP原理与系统设计[M].北京:电子工业出版社.2003.
[89] RenMingwu YangJingyu SunHan. Tracing Boundary Contours in a Binary lmage[J]. Image and Vision Computing,2002,20(2) :125~131.
[90]杨万扣,任明武,杨静宇.数字图像中基于链码的目标面积计算方法[J].计算机工程2008.34(1):30~33.
[91] Tang G Y. A Discrete Version of Green’s Theorem[J]. IEEE Trans On Pattern Anal 1985 4(3):242~249.
[92] ADSP-BF561 Blackfin Processor Hardware Reference. Norwood[R], MA, USA: Analog Devices,Inc, 2005.
[93]罗志强,王耀南.Blackfin533的DMA技术及其在图像处理中的应用[J].国外电子元器件,2005,2:32~35.
[94]周鹏.JPEG2000编码器在Blackfin561上的实现与优化[D].[硕士学位论文] .西安:西安电子科技大学.2009.14~15.
[95] ADSP-BF561 Blackfin Data sheet[R]. Analog Devices, Inc.2006.
[96] ADSP-BF561 EZ-KIT Lite Board Design Database (Revision 2.1) [R]. Analog Devices, Inc.2006.
[97] Thorsten Lorenzen.Blackfin Processor SCCB Software Interface for Configuring I2CSlave Devices.Engineer to Engineer Note ANALOG DEVICES.March[R],2003.EE-204.
[98] David J. Katz Rick. Gentile Embedded Media Processing(陈喆等译) [M].北京:电子工业出版社.2007:80~82.