基于OpenMP的运动目标跟踪算法并行化研究
|
摘要
多核并行编程技术的发展,给那些受限于单核运行速度的程序带来了新的曙光,尤其对于那些有时间死限约束的实时程序。在智能交通系统中,基于视频的串行目标跟踪程序在实际应用过程中,如果同一场景中出现的目标数过多,程序将出现严重的性能问题,其实时性无法得到保障。如何设计和开发基于多核技术的目标跟踪程序,以充分利用多核计算优势带来的系统性能提升,成为改善视频目标跟踪程序实时性的一种有效手段。
均值漂移算法和粒子滤波算法是两种常用的目标跟踪算法。均值漂移算法是一种非参数化的密度梯度上升方法,通过迭代方式找到目标的新位置。而粒子滤波算法在复杂环境下仍具有优异的跟踪性能。它是一种基于传播样本集的递归Bayes滤波器,在短时间内受遮挡丢失目标后能恢复跟踪,抗干扰能力强,但是其计算量大,在实时程序中容易成为系统的瓶颈。本文针对两种算法存在运算量大、运行速度慢等的问题,分析了两者的特点,借助Intel(?) Parallel Studio工具得出程序的瓶颈和热点区域,再利用基于OpenMP多核并行编程技术对这些地方进行了并行化。
另外,本文提出了一种车辆跟踪并行流水线模型,使得视频帧能够进行流水处理。并行区域流水线阶段模型中的每个阶段以并行线程的形式映射到各个处理器上同时执行,以加快程序的执行。模型的优缺点和实际程序的运行加速比也在本文中进行了讨论
在四核的环境下对串、并行的均值漂移算法和粒子滤波算法进行运行时间统计,可计算出并行程序的加速比。实验结果表明了多核并行编程技术在提升程序性能方面的优越性,多核程序充分利用了多核计算资源,克服了串行跟踪算法在应用中的性能瓶颈,达到了预期的优化目标。
The development of multi-core parallel programming technology has brought the new dawn for those programs which are limited to single-core, especially for those real-time programs that have dead-line constraints. In intelligence transportation system, serial video-based tracking programs will encounter the serious performance problems if excessive targets appear in a scene, consequently the real-time cannot be guaranteed. How to design and develop the target tracking programs based on multi-core technology to take full advantages of the performance promotion, becomes an interesting issue to improve the real-time of the object tracking program.
Mean shift algorithm and particle filter algorithm are two kind of commonly used target tracking algorithms. Mean shift is a non-parametric method for climbing density gradients, which iteratively finds the new position of the target. Particle filter algorithm has outstanding tracking performance under the complex environment. It is a recursive Bayes filter based on sample set, and has strong anti-interference capability. The program still continues to track the target in a short time after missing target by occluded. But the large amounts of calculation in real-time program easily become the system bottleneck. In this paper, we try to parallel the two algorithms by analyzing those characteristics to solve the problems such as intensive computation and slow speed. The bottlenecks and hotspots of program are detected with Intel Parallel Studio tools, and then the parallelization is implemented to these areas based on the OpenMP.
In addition, this paper proposes a parallel pipeline model for vehicle tracking, and makes the video frames processed in a pipeline. Each stage of the parallel pipeline model is mapped to processors, and runs concurrently in the form of parallel threads to accelerate the program. The advantages and disadvantages of the model, the speedup of actual program are also discussed, respectively.
In the quad-core environment, we compare the runtime statistics of serial/parallel mean shift algorithm and particle filter algorithm, and respectively calculate the parallel speedup of the programs. The experimental results show the superiority of multi-core parallel programming technology to enhance application performance. It takes full advantage of the computing resources of multi-core processors, thus overcomes the performance bottlenecks of serial tracking algorithms, and has achieved the optimization goal as we expected.
均值漂移算法和粒子滤波算法是两种常用的目标跟踪算法。均值漂移算法是一种非参数化的密度梯度上升方法,通过迭代方式找到目标的新位置。而粒子滤波算法在复杂环境下仍具有优异的跟踪性能。它是一种基于传播样本集的递归Bayes滤波器,在短时间内受遮挡丢失目标后能恢复跟踪,抗干扰能力强,但是其计算量大,在实时程序中容易成为系统的瓶颈。本文针对两种算法存在运算量大、运行速度慢等的问题,分析了两者的特点,借助Intel(?) Parallel Studio工具得出程序的瓶颈和热点区域,再利用基于OpenMP多核并行编程技术对这些地方进行了并行化。
另外,本文提出了一种车辆跟踪并行流水线模型,使得视频帧能够进行流水处理。并行区域流水线阶段模型中的每个阶段以并行线程的形式映射到各个处理器上同时执行,以加快程序的执行。模型的优缺点和实际程序的运行加速比也在本文中进行了讨论
在四核的环境下对串、并行的均值漂移算法和粒子滤波算法进行运行时间统计,可计算出并行程序的加速比。实验结果表明了多核并行编程技术在提升程序性能方面的优越性,多核程序充分利用了多核计算资源,克服了串行跟踪算法在应用中的性能瓶颈,达到了预期的优化目标。
The development of multi-core parallel programming technology has brought the new dawn for those programs which are limited to single-core, especially for those real-time programs that have dead-line constraints. In intelligence transportation system, serial video-based tracking programs will encounter the serious performance problems if excessive targets appear in a scene, consequently the real-time cannot be guaranteed. How to design and develop the target tracking programs based on multi-core technology to take full advantages of the performance promotion, becomes an interesting issue to improve the real-time of the object tracking program.
Mean shift algorithm and particle filter algorithm are two kind of commonly used target tracking algorithms. Mean shift is a non-parametric method for climbing density gradients, which iteratively finds the new position of the target. Particle filter algorithm has outstanding tracking performance under the complex environment. It is a recursive Bayes filter based on sample set, and has strong anti-interference capability. The program still continues to track the target in a short time after missing target by occluded. But the large amounts of calculation in real-time program easily become the system bottleneck. In this paper, we try to parallel the two algorithms by analyzing those characteristics to solve the problems such as intensive computation and slow speed. The bottlenecks and hotspots of program are detected with Intel Parallel Studio tools, and then the parallelization is implemented to these areas based on the OpenMP.
In addition, this paper proposes a parallel pipeline model for vehicle tracking, and makes the video frames processed in a pipeline. Each stage of the parallel pipeline model is mapped to processors, and runs concurrently in the form of parallel threads to accelerate the program. The advantages and disadvantages of the model, the speedup of actual program are also discussed, respectively.
In the quad-core environment, we compare the runtime statistics of serial/parallel mean shift algorithm and particle filter algorithm, and respectively calculate the parallel speedup of the programs. The experimental results show the superiority of multi-core parallel programming technology to enhance application performance. It takes full advantage of the computing resources of multi-core processors, thus overcomes the performance bottlenecks of serial tracking algorithms, and has achieved the optimization goal as we expected.
引文
[I]OpenMP. Available from:http://openmp.org/wp/.
[2]Yilmaz A., Javed O., Shah M.. Object tracking:A survey[J]. ACM Comput,2006. Surv.38,4(Article 13):p. 45.
[3]Dorin Comaniciu, Visvanathan Ramesh, Peter Meer. Kernel-Based Object Tracking[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2003.25(5):p.564-575.
[4]Yizong Cheng. Mean Shift, Mode Seeking, and Clustering[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1995. 17(8):p.790-799.
[5]Mark Fashing, Carlo Tomasi. Mean Shift Is a Bound Optimization[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2005.27(3):p.471-474.
[6]OpenCV. Available from:sourceforge.net/projects/opencvlibrary/.
[7]Gary R. Bradski, Santa Clara. Computer Vision Face Tracking For Use in a Perceptual User Interface[J]. Intel Technology Journal,1998. Q21998.
[8]Allan D. Jepson. Robust online appearance models for visual tracking[J]. University of Toronto.2003.
[9]Luo-Wei Tsai. Jun-Wei Hsieh. Kao-Chin Fan. Vehicle detection using normalized color and edge map[J]. Image Processing,2005. ICIP 2005. IEEE International Conference on 2005(11-14 Sept.2005):p. II-598-601.
[10]Horn, Berthold K. P., Schunck, Brian G. Determining optical flow[J]. Artificial Intelligence,1981.17(1-3): p.185-203.
[11]Kumar A. Tannenbaum A.R.. Balas GJ.. Optical flow:a curve evolution approach[J]. Image Processing, IEEE Transactions on,1996.5 Issue:4 (Apr 1996):p.598-610.
[12]Bruce D. Lucas. Takeo Kanade. An Iterative Image Registration Technique with an Application to Stereo Vision[J]. Proceedings of Imaging Understanding Workshop,1981:p.121-130.
[13]T J Broida, R Chellappa. Estimation of object motion parameters from noisy images[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1986.8(1):p.90-99.
[14]Kitagawa. Genshiro. Non-Gaussian State-Space Modeling of Nonstationary Time Series[J]. Journal of the American Statistical Association,1987.82(400):p.1032-1041.
[15]Huttenlocher D.P., Noh J.J., Rucklidge W.J.. Tracking non-rigid objects in complex scenes[J]. Computer Vision,1993. Proceedings., Fourth International Conference on.1993.
[16]Kang, J.M.[Jin-Man], Cohen, I., Medioni. G. Object reacquisition using invariant appearance model[J]. ICPR04,2004:p. Ⅳ:759-762.
[17]Kass M, Witkin A, Terzopoulous D.. Snakes:Active contour models[J]. Proceedings of the 1 st International Conference on Computer Vision.London:IEEE Computer Society Press,1987:p.259-268.
[18]Demetri Terzopoulos, Richard Szeliski. Tracking with Kalman snakes[J], Active vision,1993. MIT Press, p. 3-20.
[19]K Fukunaga. The estimation of the gradient of a density function, with applications in pattern recognition[J]. Information Theory. IEEE Transactions,1975.21 Issue:l(Jan 1975):p.32-40.
[20]Dorin Comaniciu, Peter Meer. Mean Shift:A Robust Approach Toward Feature Space Analysis[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2002.24(5):p.603-619.
[21]Comaniciu D., Ramesh V., Meer P..Real-time tracking of non-rigid objects using mean shift[J]. Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662),2000. Hilton Head Island, SC, USA:IEEE Comput. Soc.
[22]Richard Y. D. Xu, John G Allen. Jesse S. Jin. Robust real-time tracking of non-rigid objects[J], Proceedings of the Pan-Sydney area workshop on Visual information processing,2004. Australian Computer Society, Inc. p.95-98.
[23]Bogdan Georgescu. Ilan Shimshoni, and Peter Meer. Mean Shift Based Clustering in High Dimensions:A Texture Classification Example[J], Proceedings of the Ninth IEEE International Conference on Computer Vision-Volume 2.2003, IEEE Computer Society, p.456.
[24]Sungchan Park, Youngmin Ha. Hong Jeong. A Parallel and Memory-Efficient Mean Shift Filter on a Regular Graph[J], Proceedings of the The 2007 International Conference on Intelligent Pervasive Computing,2007. p.254-259.
[25]Peihua Li, Lijuan Xiao. Mean Shift Parallel Tracking on GPU[J]. Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis,2009. Springer-Verlag;voa de Varzim. Portugal, p.120-127.
[26]Fangfang Zhou, Ying Zhao. Kwan-Liu Ma. Parallel mean shift for interactive volume segmentation[J], Proceedings of the First international conference on Machine learning in medical imaging,2010. Springer-Verlag:Beijing. China, p.67-75.
[27]陈加,吴晓军,蔡荣.GPu并行加速的均值偏移算法[J].计算机辅助设计与图形学学报.2010.03.
[28]沈占锋,骆剑承,吴炜,胡晓东.遥感影像均值漂移分割算法的并行化实现[J].哈尔滨上业大学学报,2010.42.
[29]Li Xiangru, Hu Zhanyi, Wu Fuchao. A note on the convergence of the mean shift[J]. Pattern Recognition, 2007.40(6):p.1756-1762.
[30]李乡儒,胡占义.均值漂移算法的收敛性[J].软件学报.2005.03.
[31]Crisan D, Doucet A. A survey of convergence results on particle filtering methods for practitioners[J]. IEEE Transactions on Signal Processing,2002. vol.50 Issue:3. p.736-746.
[32]Michael Isard, Andrew Blake. CONDENSATION -- conditional density propagation for visual tracking[J]. Int. J. Computer Vision,1998. vol.29, 1,5-28.
[33]Dongbing Gu. Distributed Particle Filter for Target Tracking[J]. Robotics and Automation,2007 IEEE International Conference,2007. p.3856-3861.
[34]Mark Coates. Distributed particle filters for sensor networks[J]. Proceedings of the 3rd international symposium on Information processing in sensor networks,2004. p.99-107.
[35]Brun Olivier, Teuliere Vincent, Garcia Jean-Marie. Parallel Particle Filtering[J]. Journal of Parallel and Distributed Computing,2002.62(7). p.1186-1202.
[36]Howida Abd A. El-Halym, Imbaby I, Mahmoud, S.E.-D. Habib. Efficient hardware architecture for Particle Filter based object tracking[J]. Image Processing (ICIP).201017th IEEE International Conference,2010. p.4497-4500.
[37]Bolic M, Djuric P.M,, Sangjin Hong. Resampling algorithms and architectures for distributed particle filters[J]. Vol.53.2005. New York, NY, ETATS-UNIS:Institute of Electrical and Electronics Engineers.9.
[38]Sangjin Hong, Shu-Shin Chin, Magesh S. A flexible resampling mechanism for parallel particle filters[J]. VLSI Technology, Systems, and Applications,2003 International Symposium on,2003(2003):p.288-291.
[39]Medeiros Henry. Holgu韓Germ醤, Shin Paul J., Park Johnny. A parallel histogram-based particle filter for object tracking on SIMD-based smart cameras[J]. Computer Vision and Image Understanding,2010. 114(11):p.1264-1272.
[40]Matthew A. Goodrum, Michael J. Trotter, Alla Aksel. Scott T. Acton, Kevin Skadron, Kevin Skadron. Parallelization of Particle Filter Algorithms[J]. Proceedings of the 3rd Workshop on Emerging Applications and Many-core Architecture(EAMA), in conjunction with ISCA2010,2010.
[41]明新勇.基于均值漂移和粒子滤波的目标跟踪算法研究[D].2008,南京理工大学.p22-23.
[42]ARULAMPALAM. et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking[J],2002. New York, NY, ETATS-UNIS:Institute of Electrical and Electronics Engineers.277.
[43]Doucet, Arnaud. On Sequential Simulation-Based Methods for Bayesian Filtering[J],1998.
[44]李涛.基于Mean Shift算法和Particle Filter算法的目标跟踪[D],2007,南京理工大学.p19.
[45]Liu Jun, Chen Rong. Sequential Monte Carlo Methods for Dynamic Systems[J]. Journal of the American Statistical Association,1998.93. p.1032-1044.
[46]W.J.Roger. An introduction to the bootstrap[J]. Teaching Statistics,2001.49-55.
[47]Nummiaro Katja, Koller-Meier Esther, Van Gool Luc. An adaptive color-based particle filter[J]. Image and Vision Computing,2003,21(1). p.99-110.
[48]Katja Nummiaro. Esther Koller-Meier, Luc J. Van Gool. Object Tracking with an Adaptive Color-Based Particle Filter[J]. Pattern Recognition, L. Van Gool. Editor.2002, Springer Berlin/Heidelberg. p.353-360.
[49](美)格兰马.并行计算导论[M].机械工业出版社.2004.p20-22.
[50]殷顺昌OpenMP并行程序性能分析[D].国防科学技术大学研究生院.2006.p8.
[51]Synthetic Data Example. Current version dates from:November 27,2003]; Available from: http://coewww.rutgers.edu/riul/research/code/AMS/index.html.
[52]刘运杰.基于粒子滤波器的目标跟踪算法研究[D].大连理工大学,2010.p8.
[53]Ananth Grama. Anshul Gupta, George Karypis, Vipin Kumar. Introduction to Parallel Computing.2002: Addison-Wesley Longman Publishing Co. Inc,2002, p.138-141.
[54]Timothy GMattson, Beverly A. Sanders, Berna L.Massingill. Patterns for Parallel Programming. Addison Wesley,2004. p101-102.
[55]Barry Wilkinson, Michael Allen. Parallel Programming:Techniques and Applications Using Networked Workstations and Parallel Computers. China Machine Press,2002. p203-205.
[56]Gary Bradski, Adrian Kaehler. Learning OpenCV:Computer Vision with the OpenCV Library[M]. O'Relilly Media.Inc,2008. p316.
[57]Barbara Chapman, Gabriele Jost, Ruud van der Pas. Using OpenMP Portable Shared Memory Parallel Programming[M]. The MIT Press,2007. p98.
[58]Daniel Baudisch, Jens Brandt, and Klaus Schneider. Multithreaded Code from Synchronous Programs: Generating Software Pipelines for OpenMP[J]. Methoden undBeschreibungssprachen zur Modellierung und Verifikation von Schaltungen undSystemen (MBMV), Dresden, Germany,2010.
[59]李学干.计算机系统结构(第四版)[M].西安：西安电子科技大学出版社,2006.160-162.
[60]Huimin QIAN, Yaobin MAO, Jason GENG. Zhiquan WANG. Object tracking with self-updating tracking window. PAISI'2007.
[2]Yilmaz A., Javed O., Shah M.. Object tracking:A survey[J]. ACM Comput,2006. Surv.38,4(Article 13):p. 45.
[3]Dorin Comaniciu, Visvanathan Ramesh, Peter Meer. Kernel-Based Object Tracking[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2003.25(5):p.564-575.
[4]Yizong Cheng. Mean Shift, Mode Seeking, and Clustering[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1995. 17(8):p.790-799.
[5]Mark Fashing, Carlo Tomasi. Mean Shift Is a Bound Optimization[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2005.27(3):p.471-474.
[6]OpenCV. Available from:sourceforge.net/projects/opencvlibrary/.
[7]Gary R. Bradski, Santa Clara. Computer Vision Face Tracking For Use in a Perceptual User Interface[J]. Intel Technology Journal,1998. Q21998.
[8]Allan D. Jepson. Robust online appearance models for visual tracking[J]. University of Toronto.2003.
[9]Luo-Wei Tsai. Jun-Wei Hsieh. Kao-Chin Fan. Vehicle detection using normalized color and edge map[J]. Image Processing,2005. ICIP 2005. IEEE International Conference on 2005(11-14 Sept.2005):p. II-598-601.
[10]Horn, Berthold K. P., Schunck, Brian G. Determining optical flow[J]. Artificial Intelligence,1981.17(1-3): p.185-203.
[11]Kumar A. Tannenbaum A.R.. Balas GJ.. Optical flow:a curve evolution approach[J]. Image Processing, IEEE Transactions on,1996.5 Issue:4 (Apr 1996):p.598-610.
[12]Bruce D. Lucas. Takeo Kanade. An Iterative Image Registration Technique with an Application to Stereo Vision[J]. Proceedings of Imaging Understanding Workshop,1981:p.121-130.
[13]T J Broida, R Chellappa. Estimation of object motion parameters from noisy images[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1986.8(1):p.90-99.
[14]Kitagawa. Genshiro. Non-Gaussian State-Space Modeling of Nonstationary Time Series[J]. Journal of the American Statistical Association,1987.82(400):p.1032-1041.
[15]Huttenlocher D.P., Noh J.J., Rucklidge W.J.. Tracking non-rigid objects in complex scenes[J]. Computer Vision,1993. Proceedings., Fourth International Conference on.1993.
[16]Kang, J.M.[Jin-Man], Cohen, I., Medioni. G. Object reacquisition using invariant appearance model[J]. ICPR04,2004:p. Ⅳ:759-762.
[17]Kass M, Witkin A, Terzopoulous D.. Snakes:Active contour models[J]. Proceedings of the 1 st International Conference on Computer Vision.London:IEEE Computer Society Press,1987:p.259-268.
[18]Demetri Terzopoulos, Richard Szeliski. Tracking with Kalman snakes[J], Active vision,1993. MIT Press, p. 3-20.
[19]K Fukunaga. The estimation of the gradient of a density function, with applications in pattern recognition[J]. Information Theory. IEEE Transactions,1975.21 Issue:l(Jan 1975):p.32-40.
[20]Dorin Comaniciu, Peter Meer. Mean Shift:A Robust Approach Toward Feature Space Analysis[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2002.24(5):p.603-619.
[21]Comaniciu D., Ramesh V., Meer P..Real-time tracking of non-rigid objects using mean shift[J]. Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662),2000. Hilton Head Island, SC, USA:IEEE Comput. Soc.
[22]Richard Y. D. Xu, John G Allen. Jesse S. Jin. Robust real-time tracking of non-rigid objects[J], Proceedings of the Pan-Sydney area workshop on Visual information processing,2004. Australian Computer Society, Inc. p.95-98.
[23]Bogdan Georgescu. Ilan Shimshoni, and Peter Meer. Mean Shift Based Clustering in High Dimensions:A Texture Classification Example[J], Proceedings of the Ninth IEEE International Conference on Computer Vision-Volume 2.2003, IEEE Computer Society, p.456.
[24]Sungchan Park, Youngmin Ha. Hong Jeong. A Parallel and Memory-Efficient Mean Shift Filter on a Regular Graph[J], Proceedings of the The 2007 International Conference on Intelligent Pervasive Computing,2007. p.254-259.
[25]Peihua Li, Lijuan Xiao. Mean Shift Parallel Tracking on GPU[J]. Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis,2009. Springer-Verlag;voa de Varzim. Portugal, p.120-127.
[26]Fangfang Zhou, Ying Zhao. Kwan-Liu Ma. Parallel mean shift for interactive volume segmentation[J], Proceedings of the First international conference on Machine learning in medical imaging,2010. Springer-Verlag:Beijing. China, p.67-75.
[27]陈加,吴晓军,蔡荣.GPu并行加速的均值偏移算法[J].计算机辅助设计与图形学学报.2010.03.
[28]沈占锋,骆剑承,吴炜,胡晓东.遥感影像均值漂移分割算法的并行化实现[J].哈尔滨上业大学学报,2010.42.
[29]Li Xiangru, Hu Zhanyi, Wu Fuchao. A note on the convergence of the mean shift[J]. Pattern Recognition, 2007.40(6):p.1756-1762.
[30]李乡儒,胡占义.均值漂移算法的收敛性[J].软件学报.2005.03.
[31]Crisan D, Doucet A. A survey of convergence results on particle filtering methods for practitioners[J]. IEEE Transactions on Signal Processing,2002. vol.50 Issue:3. p.736-746.
[32]Michael Isard, Andrew Blake. CONDENSATION -- conditional density propagation for visual tracking[J]. Int. J. Computer Vision,1998. vol.29, 1,5-28.
[33]Dongbing Gu. Distributed Particle Filter for Target Tracking[J]. Robotics and Automation,2007 IEEE International Conference,2007. p.3856-3861.
[34]Mark Coates. Distributed particle filters for sensor networks[J]. Proceedings of the 3rd international symposium on Information processing in sensor networks,2004. p.99-107.
[35]Brun Olivier, Teuliere Vincent, Garcia Jean-Marie. Parallel Particle Filtering[J]. Journal of Parallel and Distributed Computing,2002.62(7). p.1186-1202.
[36]Howida Abd A. El-Halym, Imbaby I, Mahmoud, S.E.-D. Habib. Efficient hardware architecture for Particle Filter based object tracking[J]. Image Processing (ICIP).201017th IEEE International Conference,2010. p.4497-4500.
[37]Bolic M, Djuric P.M,, Sangjin Hong. Resampling algorithms and architectures for distributed particle filters[J]. Vol.53.2005. New York, NY, ETATS-UNIS:Institute of Electrical and Electronics Engineers.9.
[38]Sangjin Hong, Shu-Shin Chin, Magesh S. A flexible resampling mechanism for parallel particle filters[J]. VLSI Technology, Systems, and Applications,2003 International Symposium on,2003(2003):p.288-291.
[39]Medeiros Henry. Holgu韓Germ醤, Shin Paul J., Park Johnny. A parallel histogram-based particle filter for object tracking on SIMD-based smart cameras[J]. Computer Vision and Image Understanding,2010. 114(11):p.1264-1272.
[40]Matthew A. Goodrum, Michael J. Trotter, Alla Aksel. Scott T. Acton, Kevin Skadron, Kevin Skadron. Parallelization of Particle Filter Algorithms[J]. Proceedings of the 3rd Workshop on Emerging Applications and Many-core Architecture(EAMA), in conjunction with ISCA2010,2010.
[41]明新勇.基于均值漂移和粒子滤波的目标跟踪算法研究[D].2008,南京理工大学.p22-23.
[42]ARULAMPALAM. et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking[J],2002. New York, NY, ETATS-UNIS:Institute of Electrical and Electronics Engineers.277.
[43]Doucet, Arnaud. On Sequential Simulation-Based Methods for Bayesian Filtering[J],1998.
[44]李涛.基于Mean Shift算法和Particle Filter算法的目标跟踪[D],2007,南京理工大学.p19.
[45]Liu Jun, Chen Rong. Sequential Monte Carlo Methods for Dynamic Systems[J]. Journal of the American Statistical Association,1998.93. p.1032-1044.
[46]W.J.Roger. An introduction to the bootstrap[J]. Teaching Statistics,2001.49-55.
[47]Nummiaro Katja, Koller-Meier Esther, Van Gool Luc. An adaptive color-based particle filter[J]. Image and Vision Computing,2003,21(1). p.99-110.
[48]Katja Nummiaro. Esther Koller-Meier, Luc J. Van Gool. Object Tracking with an Adaptive Color-Based Particle Filter[J]. Pattern Recognition, L. Van Gool. Editor.2002, Springer Berlin/Heidelberg. p.353-360.
[49](美)格兰马.并行计算导论[M].机械工业出版社.2004.p20-22.
[50]殷顺昌OpenMP并行程序性能分析[D].国防科学技术大学研究生院.2006.p8.
[51]Synthetic Data Example. Current version dates from:November 27,2003]; Available from: http://coewww.rutgers.edu/riul/research/code/AMS/index.html.
[52]刘运杰.基于粒子滤波器的目标跟踪算法研究[D].大连理工大学,2010.p8.
[53]Ananth Grama. Anshul Gupta, George Karypis, Vipin Kumar. Introduction to Parallel Computing.2002: Addison-Wesley Longman Publishing Co. Inc,2002, p.138-141.
[54]Timothy GMattson, Beverly A. Sanders, Berna L.Massingill. Patterns for Parallel Programming. Addison Wesley,2004. p101-102.
[55]Barry Wilkinson, Michael Allen. Parallel Programming:Techniques and Applications Using Networked Workstations and Parallel Computers. China Machine Press,2002. p203-205.
[56]Gary Bradski, Adrian Kaehler. Learning OpenCV:Computer Vision with the OpenCV Library[M]. O'Relilly Media.Inc,2008. p316.
[57]Barbara Chapman, Gabriele Jost, Ruud van der Pas. Using OpenMP Portable Shared Memory Parallel Programming[M]. The MIT Press,2007. p98.
[58]Daniel Baudisch, Jens Brandt, and Klaus Schneider. Multithreaded Code from Synchronous Programs: Generating Software Pipelines for OpenMP[J]. Methoden undBeschreibungssprachen zur Modellierung und Verifikation von Schaltungen undSystemen (MBMV), Dresden, Germany,2010.
[59]李学干.计算机系统结构(第四版)[M].西安：西安电子科技大学出版社,2006.160-162.
[60]Huimin QIAN, Yaobin MAO, Jason GENG. Zhiquan WANG. Object tracking with self-updating tracking window. PAISI'2007.