基于粒子滤波的视频目标跟踪算法研究
|
摘要
视频目标跟踪是计算机视觉领域中的一个重要研究方向。粒子滤波算法具有在非线性、非高斯系统中仍能保持良好稳定性能的特点,因此可以被应用于视频目标跟踪领域。本文重点研究了基于粒子滤波的视频目标跟踪算法,针对视频目标的特点,可以将其分为彩色目标和灰度目标,文章重点了研究了这两种不同目标下的粒子滤波算法。
在彩色目标中,本文利用目标的颜色直方图,重点研究了目标快速运动、部分遮挡、旋转以及尺度缩放条件下的跟踪问题。针对粒子滤波算法计算量大、采样效率低等问题,提出了一种Camshift优化的粒子滤波改进算法。该算法结合了粒子滤波算法及Camshift算法的优点。利用Camshift具有迭代到局部极值点的速度快的特点,使状态转移后的粒子快速收敛到目标区域,进而采样粒子,使采样粒子尽可能集中在目标附近,更好地描述目标状态后验概率,提高采样效率,减小计算量。同时,算法针对相似颜色干扰问题进行了进一步处理,提出了根据目标受干扰程度分别处理的策略。当目标周围相似颜色干扰物较小时,采取根据目标周围背景中相似颜色比例自适应调整参与Camshift优化的粒子数的方法。当目标周围相似颜色干扰物较多时,采取融合目标的颜色直方图以及边缘直方图的方法来对计算粒子的权值。该方法只在目标周围相似颜色物体比较多时使用,这样不仅节省了算法的时间,而且解决了相似颜色干扰问题,增加了算法稳定性。实验结果表明,该算法具有很好的实时性和鲁棒性。
针对灰度视频中的灰度目标的跟踪,本文提出了一种在粒子滤波算法框架下的模板匹配新方法。该方法将模板匹配方法与粒子滤波方法相结合,将模板匹配概率化。针对灰度分布特征具有只能适应目标小角度旋转,小范围姿态变化的缺点,提出了主动轮廓模型更新算法。当更新模型时,首先使用主动轮廓模型算法得到目标的轮廓信息,然后根据这个轮廓信息来合理地更新模型。实验表明该算法能够更好地实时适应目标姿态变化、短暂遮挡等情况下进行可靠跟踪。
Video object tracking is an important research direction in the filed of computer vision. In the non-linear, non-Gaussian systems, so it can be applied to the field of video object tracking. Particle filter algorithm can still maintain good and stable performance characteristics. This paper focuses on particle filter. Target for video features, it can be divided into goals and gray color targets, the article focus on the study of these two different objectives tracking.
In color targets, this paper targets the color histogram, which focuses on the target fast movement, part of the block, rotate, and zoom scale under the conditions of tracking problem. For the large amount of sample and low efficiency problem in particle filter algorithm, this paper proposed a Camshift optimized Particle filter Tracking Algorithm. The algorithm combines the particle filter algorithm and Camshift algorithm advantages. Camshift can make the particles aftered the transfer fastly move to the target area, so sample particles concentrated in the vicinity of the target to improve sampling efficiency and reduce the computational complexity.At the same time, For the similar color interference problems, the algorithm is to further processing, and Proposing separate treatment strategies. when the target similar to the color interference with surrounding objects is small, to take depending on the target percentage of the surrounding background of similar color Camshift optimization involved in adaptive.When more similar color disruptors, we will take a fusion target color and edge histogram method to calculate the particle weights. This method is only used in much similar color objects, so the algorithm can not only save time but also solve similar color interference, increasing the stability of the algorithm. The experimental results show that the algorithm has good real-time performance and robustness.
For the gray video target tracking, this paper presents a new template match method in the framework of particle filter. This approach combines the correlation-matching method with particle filter. For the gray distribution features can only be adapted with the goal of small angle rotation and the small-scale changes in posture, active contour model proposed to update algorithm. During the template refreshing of the correlation algorithm, this paper applies the active model contours algorithm to get access to the object contours to reach the accurate object area so as to refresh the template exactly. Experimental results also demonstrate this method can track objects when object part-occlusion and various sharps scales.
在彩色目标中,本文利用目标的颜色直方图,重点研究了目标快速运动、部分遮挡、旋转以及尺度缩放条件下的跟踪问题。针对粒子滤波算法计算量大、采样效率低等问题,提出了一种Camshift优化的粒子滤波改进算法。该算法结合了粒子滤波算法及Camshift算法的优点。利用Camshift具有迭代到局部极值点的速度快的特点,使状态转移后的粒子快速收敛到目标区域,进而采样粒子,使采样粒子尽可能集中在目标附近,更好地描述目标状态后验概率,提高采样效率,减小计算量。同时,算法针对相似颜色干扰问题进行了进一步处理,提出了根据目标受干扰程度分别处理的策略。当目标周围相似颜色干扰物较小时,采取根据目标周围背景中相似颜色比例自适应调整参与Camshift优化的粒子数的方法。当目标周围相似颜色干扰物较多时,采取融合目标的颜色直方图以及边缘直方图的方法来对计算粒子的权值。该方法只在目标周围相似颜色物体比较多时使用,这样不仅节省了算法的时间,而且解决了相似颜色干扰问题,增加了算法稳定性。实验结果表明,该算法具有很好的实时性和鲁棒性。
针对灰度视频中的灰度目标的跟踪,本文提出了一种在粒子滤波算法框架下的模板匹配新方法。该方法将模板匹配方法与粒子滤波方法相结合,将模板匹配概率化。针对灰度分布特征具有只能适应目标小角度旋转,小范围姿态变化的缺点,提出了主动轮廓模型更新算法。当更新模型时,首先使用主动轮廓模型算法得到目标的轮廓信息,然后根据这个轮廓信息来合理地更新模型。实验表明该算法能够更好地实时适应目标姿态变化、短暂遮挡等情况下进行可靠跟踪。
Video object tracking is an important research direction in the filed of computer vision. In the non-linear, non-Gaussian systems, so it can be applied to the field of video object tracking. Particle filter algorithm can still maintain good and stable performance characteristics. This paper focuses on particle filter. Target for video features, it can be divided into goals and gray color targets, the article focus on the study of these two different objectives tracking.
In color targets, this paper targets the color histogram, which focuses on the target fast movement, part of the block, rotate, and zoom scale under the conditions of tracking problem. For the large amount of sample and low efficiency problem in particle filter algorithm, this paper proposed a Camshift optimized Particle filter Tracking Algorithm. The algorithm combines the particle filter algorithm and Camshift algorithm advantages. Camshift can make the particles aftered the transfer fastly move to the target area, so sample particles concentrated in the vicinity of the target to improve sampling efficiency and reduce the computational complexity.At the same time, For the similar color interference problems, the algorithm is to further processing, and Proposing separate treatment strategies. when the target similar to the color interference with surrounding objects is small, to take depending on the target percentage of the surrounding background of similar color Camshift optimization involved in adaptive.When more similar color disruptors, we will take a fusion target color and edge histogram method to calculate the particle weights. This method is only used in much similar color objects, so the algorithm can not only save time but also solve similar color interference, increasing the stability of the algorithm. The experimental results show that the algorithm has good real-time performance and robustness.
For the gray video target tracking, this paper presents a new template match method in the framework of particle filter. This approach combines the correlation-matching method with particle filter. For the gray distribution features can only be adapted with the goal of small angle rotation and the small-scale changes in posture, active contour model proposed to update algorithm. During the template refreshing of the correlation algorithm, this paper applies the active model contours algorithm to get access to the object contours to reach the accurate object area so as to refresh the template exactly. Experimental results also demonstrate this method can track objects when object part-occlusion and various sharps scales.
引文
[1] Shijie Zhang, Stentiford F. Motion detection using a model of visual attention[J]. IEEE International Conference on Image Processing, 2007, 3:513~516.
[2]李安平.复杂环境下视频目标跟踪算法研究. [博士学位论文],上海:上海交通大学, 2007.
[3]王宝安,卢焕章.粒子滤波器及其在目标跟踪中的应用[J].雷达科学与技术,2003,1(3):170~ 174.
[4] Y.Bar-Shalom, X.R.Li. Estimation with Applications to Tracking and Navigation. New York:John Wiley&Sons,2001,179~192.
[5]章毓晋.图像处理和分析[M].北京:清华大学出版社, 1999:239~261.
[6] Ananda P. A computational framework and an algorithm for the measurement of visual motion[C]. International Conference of Computer Vision, 1989, 2(3):283~310.
[7] String E, Regazzoni C S. Real-time video-shot detection for scene applications[J]. IEEE Transactions on Image Processing, 2000, 9(1):69~79.
[8]余静,游志胜.自动目标识别与跟踪技术研究综述[J].计算机应用研究, 2005, 1:12~15.
[9]楼建光,柳崎峰,谭铁牛等.基于三维模型的交通场景视觉监控[J].自动化学报, 2003,29 (3):434~449.
[10]候志强,韩崇昭.视觉跟踪技术综述[J].自动化学报, 2006, 32(4): 603~618.
[11] I.Haritaoglu, D.Harwood, L.Davis. A Fast Background scene Modeling and Maintenance forout- do or surveillance[C]. Proceedings of the 15th International Conference on Pattern Recognition,2000, 9(4):179~183.
[12] A.Lipton, H.Fujiyoshi, R.Patil. Moving Target Classification and Tracking from Real-time Video[J]. Proceedings of IEEE Workshop on Applications of Computer Vision,1998,4:8~14.
[13] S.H.Lim, A.E.Gamal. Optical flow estimation using high frame rate sequences[C]. International Conference on Image Processing,2001,10(2):925~928.
[14]方帅,迟健男,徐心和.视频监控中的运动目标跟踪算法[J].控制与决策,2005,20 (12) :1388~1391.
[15] S.M.Smith, J.M.Brady. SUSAN-A New Approach to Low Level Image Processing. International Journal of Computer Vision,1993,23(1):45~78.
[16] D. Comaniciu, V. Ramesh and P. Meer. Kernel-based object tracking[J]. IEEE Transaction on Pa- ttern Analysis and Machine Intelligence, 2003, 25(5): 564~577.
[17] C. Yang, R. Duraiswami and L. Davis. Efficient mean-shift tracking via a new similarity mea- sure[J]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,San Diego, CA, United States, 2005, 1:176~183.
[18] K. Nummiaro, E. Koller-Meier and L. Van Gool. An adaptive color-based particle filter[J]. Image andVision Computing, 2003, 21(1): 99~110.
[19] M. Isard and A. Blake. CONDENSATION-Conditional density propagation for visual tracking [J].International Journal of Computer Vision, 1998, 29(1): 5~28.
[20]宋新,罗军,王鲁平等.基于GVF Snake的运动目标跟踪方法[J].红外与激光工程,2007 36(2): 226~228.
[21] I. Cohen and G. Medioni. Detecting and tracking moving objects for video surveillance[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, FortCollins, CO, USA, 1999, 2:319~325.
[22] T. Zhao and R. Nevatia. Tracking multiple humans in complex situations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1208~1221.
[23] J. Wang and M. F. Cohen. Very low frame-rate video streaming for face-to-face teleconference. In:Proceedings of Data Compression Conference Snowbird, UT, United States, 2005, 309~318.
[24] B. Jung and G. S. Sukhatme.Detecting moving objects using a single camera on a mobile robot in an outdoor environment[C]. Proceedings of International Conference on Intelligent Autonomous Systems, 2004, 2:980~987.
[25] J. MacCormick and A. Blake. A probabilistic exclusion principle for tracking multiple objects[J].International Journal of Computer Vision, 2000, 39(1): 57~71.
[26] N.J.Gordon. A hybrid Bootstrap filter for target tracking in clutter[J]. IEEE Transactions on Aerospace and Electronic Systems,1997,33(1):353~358.
[27] B.Efron,R.J.Tibshirani. An Introduction to the Bootstrap. Chapman&Hall,1993: 34~69.
[28] P. KaewTrakulPong and R. Bowden. A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes[J]. Image and Vision Computing, 2003,21(10): 913~929.
[29] A.Doucet, S.J.Godsill, C.Andrieu. On sequential simulation-based methods for Baysian filtering [J]. Statistics and Computing,2000,10(3) : 197~208.
[30] M.Pitt, N.Shephard. Filtering via simulation: Auxiliary particle filters[J]. Journal of the American Statistical Association,1999,94(2):590~599.
[31] Y. Wu and T. S. Huang. Robust visual tracking by integrating multiple cues based on co-inferencelearning[J]. International Journal of Computer Vision, 2004, 58(1): 55~71.
[32] J. P. Norton, G. V. Veres. Improvement of the Particle Filter by Better Choice of the Predicted Sample Set. Proceeding 15th IFAC. 2002:904~909.
[33] P. M. Djuric, J. H. Kotecha, J. Y. Tourneret, et al. Adaptive Signal Processing by Particle Filters and Discounting of Old Measurements.Accoustics,Speech, and Signal Processing. 2001,6:3733~3736.
[34] H. Nait-Charif and S. J. McKenna. Head tracking and action recognition in a smart meeting room[J]. Proceedings of 4th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Graz, Austria, 2003, 2:4~10.
[35] A. Pentland. Looking at people: Sensing for ubiquitous and wearable computing[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence, 2000, 22(1): 107~119.
[36] O.Brun, V.Teulieve, J.Garcia. Parallel particle filtering[J]. Journal of Parallel and Distributed Computing,2002,62(7) : 1186~1202.
[37] M. Isard and A. Blake. CONDENSATION-conditional density propagation for visual tracking [J].International Journal of Computer Vision, 1998, 29(1): 5~28.
[38] N. J. Gordon, D. J. Salmond and A. F. M. Smith. Novel approach to nonlinear/non-Gaussian Bay- esian state estimation[J]. IEE Proceedings-F of Radar and Signal Processing, 1993, 140(2): 107~113.
[39] A. Doucet, S. Godsill, C. Andrieu. On Sequential Monte Carlo Sampling Methods for Bayesian Filtering[J]. Statistics and Computing. 2000,10:197~208.
[40]查宇飞,张育,毕笃彦.一种基于粒子滤波的自适应运动目标跟踪方法[J].电子与信息学报,2007,29(1):92~95.
[41] L. Mun Wai, I. Cohen and J. Soon Ki. Particle filter with analytical inference for human body tracking[J]. In: Proceedings of IEEE Workshop on Motion and Video Computing, 2002,3:159~165.
[42]张波.基于粒子滤波的图像跟踪算法研究:[博士学位论文].上海:上海交通大学,2007:14~32.
[43]王其聪.复杂观测条件下的基于粒子滤波的视觉跟踪:[博士学位论文].杭州:浙江大学,2007:33~41.
[44]黄飞,李德华,姚讯.基于相关匹配及自适应模板更新的目标跟踪新方法.计算机工程, 2007, 33(16): 147~149.
[45]黄斌.基于粒子滤波的视频目标跟踪方法研究. [硕士学位论文].四川:电子科技大学,2005.
[46] J.S.Liu, R.Chen. Sequential Monte Carlo Methods for Dynamic Systems[J]. Journal of the Amer- ican Statistical Association,1998,93(443):1032~1044.
[47] B.Efron, R.J.Tibshirani. An Introduction to the Bootstrap. Chapman&Hall,1993:34~69.
[48]A.Doucet,N.Gordon.Sequential Monte Carlo Methods in Practice.New York:Springer Verlag,2001:1~41.
[49]王绍钰.基于粒子滤波器的运动目标跟踪方法研究[硕士学位论文].湖南:中南大学,2008 .
[50]胡士强,敬忠良.粒子滤波算法综述[J].控制与决策.2005,20(4):361~365.
[51]陶霖密,徐光佑.机器视觉中的颜色问题及应用[J].科学通报.2001,46(3):178-190.
[52]何斌,马天予,王运坚,朱红莲.编著[M. Visual C++数字图像处理,北京:人民邮电出版社,2001, 4:58~67.
[53]张苗辉.基于粒子滤波的目标跟踪算法研究[硕士学位论文].河南:河南大学,2005.
[54] T. Kailath. The Divergence and Bhattacharyya Distance Measures in Signal Selection[J]. IEEE Trans. Commun. Tech., 1967, 15:52~60.
[55] C. F. Shan, Y. C. Wei, T. N. Tan, et al. Real time hand tracking by combining particle filtering and mean shift[C]. Proceedings of 6th International Conference on Automatic Face and Gesture Recognition, 2004: 669~ 674.
[56]姚剑敏.粒子滤波跟踪方法研究:[博士学位论文].长春:中科院长春光机所,2004:29-44.
[57]明新勇.基于均值漂移和粒子滤波的目标跟踪算法研究: [硕士学位论文].南京:南京理工大学,2008.
[58] Cheng Chang ,Rashid Ansari. Kernel particle filter for visual tracking[J].IEEE Signal Processing Letters ,2005 ,12(3):242-245.
[59] Perez, P., Hue, C., Vermaak, J., Gangnet, M.. Color-based probabilistic tracking[J] .European Conf. on Computer Vision. 2002,32(6):661~675.
[60]胡士强,敬忠良. PF算法综述[J ] .控制与决策,2005 ,20 (4) :361~365.
[61] K. Fukunaga, L. D. Hostetler. The Estimation of the Gradient of a Density Function with Applications in Pattern Recognition[J]. IEEE Transactions on Information Theory. 1975, 21(1):32~40.
[62] G. R. Bradski. Computer Vision Face Tracking for Use in a Perceptual User Interface[J]. Intel Technology Journal. 1998, 2(2):12~21.
[63]彭宁嵩,杨杰等.Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报.2005,16(9): 1542~1551.
[64] Caifeng Shan,Tieniu Tan,YuchengWei. Real-time hand tracking using a mean shift[J] embedded particle filterPattern Recognition . 2007, 4 :1958~1970.
[65] Zhaowen Wang, Xiaokang Yang, Yi Xu, Songyu Yu .CamShift guided particle filter for visual tracking[J].Pattern Recognition Letters, 2009, 30: 407~413.
[66]孙昀,刘富强,李志鹏.基于空间梯度直方图的行人检测算法[J].中国图象图形学报, 2008,13(10):1825~1828.
[67]王新红,王晶,田敏等.基于空间边缘方向直方图的Mean Shift跟踪算法[J].中国图象图形学报, 2008,13(3):586~592.
[68]刘惟锦,章毓晋.基于Kalman滤波和边缘直方图的实时目标跟踪[J].清华大学学报(自然科学版)2008 ,48(7):1104~1107 .
[69]文志强,蔡自兴.一种基于meanshift的鲁棒性目标跟踪方法[J].计算机应用研究.2008, 25(6):1753~1758.
[70]吴铮.基于特征的图像配准算法研究. [硕士学位论文],杭州:浙江大学, 2006.
[71] Nguyen H T, Worring M, Rvan D B. Occlusion robust adaptive template tracking[C]. Proceeding Of IEEE Conference on Computer Vision, 2001, 1:678~683.
[72]贾云得.机器视觉[M],北京:科学出版社, 2002, 4:82~138.
[73]姚红革,齐华,郝重阳.复杂情形下目标跟踪的自适应粒子滤波算法[J].电子与信息学报, 2009, 31(2):275~278.
[74]任仙怡,廖运涛,张桂林等.一种新的相关跟踪方法研究[J].中国图像图形学报(A版), 2002, 7(6):553~557.
[75]黄飞,李德华,姚讯.基于相关匹配及自适应模板更新的目标跟踪新方法[J].计算机工程, 2007, 33(16): 147~149.
[76] Kass M, Witkin A, Terzopoulos D. Snakes: Active Contour Models. International Journal of Computer Vision, 1987:321~331.
[77]王震.主动轮廓模型在人脸人耳检测方面的应用. [硕士学位论文].黑龙江:哈尔滨工业大学, 2006.
[78] Williams D J, Shah M. A fast algorithm for active contours and curvature estimation[J]. CVGIP: Image Understanding, 1992, 55(1): 14~26.
[2]李安平.复杂环境下视频目标跟踪算法研究. [博士学位论文],上海:上海交通大学, 2007.
[3]王宝安,卢焕章.粒子滤波器及其在目标跟踪中的应用[J].雷达科学与技术,2003,1(3):170~ 174.
[4] Y.Bar-Shalom, X.R.Li. Estimation with Applications to Tracking and Navigation. New York:John Wiley&Sons,2001,179~192.
[5]章毓晋.图像处理和分析[M].北京:清华大学出版社, 1999:239~261.
[6] Ananda P. A computational framework and an algorithm for the measurement of visual motion[C]. International Conference of Computer Vision, 1989, 2(3):283~310.
[7] String E, Regazzoni C S. Real-time video-shot detection for scene applications[J]. IEEE Transactions on Image Processing, 2000, 9(1):69~79.
[8]余静,游志胜.自动目标识别与跟踪技术研究综述[J].计算机应用研究, 2005, 1:12~15.
[9]楼建光,柳崎峰,谭铁牛等.基于三维模型的交通场景视觉监控[J].自动化学报, 2003,29 (3):434~449.
[10]候志强,韩崇昭.视觉跟踪技术综述[J].自动化学报, 2006, 32(4): 603~618.
[11] I.Haritaoglu, D.Harwood, L.Davis. A Fast Background scene Modeling and Maintenance forout- do or surveillance[C]. Proceedings of the 15th International Conference on Pattern Recognition,2000, 9(4):179~183.
[12] A.Lipton, H.Fujiyoshi, R.Patil. Moving Target Classification and Tracking from Real-time Video[J]. Proceedings of IEEE Workshop on Applications of Computer Vision,1998,4:8~14.
[13] S.H.Lim, A.E.Gamal. Optical flow estimation using high frame rate sequences[C]. International Conference on Image Processing,2001,10(2):925~928.
[14]方帅,迟健男,徐心和.视频监控中的运动目标跟踪算法[J].控制与决策,2005,20 (12) :1388~1391.
[15] S.M.Smith, J.M.Brady. SUSAN-A New Approach to Low Level Image Processing. International Journal of Computer Vision,1993,23(1):45~78.
[16] D. Comaniciu, V. Ramesh and P. Meer. Kernel-based object tracking[J]. IEEE Transaction on Pa- ttern Analysis and Machine Intelligence, 2003, 25(5): 564~577.
[17] C. Yang, R. Duraiswami and L. Davis. Efficient mean-shift tracking via a new similarity mea- sure[J]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,San Diego, CA, United States, 2005, 1:176~183.
[18] K. Nummiaro, E. Koller-Meier and L. Van Gool. An adaptive color-based particle filter[J]. Image andVision Computing, 2003, 21(1): 99~110.
[19] M. Isard and A. Blake. CONDENSATION-Conditional density propagation for visual tracking [J].International Journal of Computer Vision, 1998, 29(1): 5~28.
[20]宋新,罗军,王鲁平等.基于GVF Snake的运动目标跟踪方法[J].红外与激光工程,2007 36(2): 226~228.
[21] I. Cohen and G. Medioni. Detecting and tracking moving objects for video surveillance[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, FortCollins, CO, USA, 1999, 2:319~325.
[22] T. Zhao and R. Nevatia. Tracking multiple humans in complex situations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1208~1221.
[23] J. Wang and M. F. Cohen. Very low frame-rate video streaming for face-to-face teleconference. In:Proceedings of Data Compression Conference Snowbird, UT, United States, 2005, 309~318.
[24] B. Jung and G. S. Sukhatme.Detecting moving objects using a single camera on a mobile robot in an outdoor environment[C]. Proceedings of International Conference on Intelligent Autonomous Systems, 2004, 2:980~987.
[25] J. MacCormick and A. Blake. A probabilistic exclusion principle for tracking multiple objects[J].International Journal of Computer Vision, 2000, 39(1): 57~71.
[26] N.J.Gordon. A hybrid Bootstrap filter for target tracking in clutter[J]. IEEE Transactions on Aerospace and Electronic Systems,1997,33(1):353~358.
[27] B.Efron,R.J.Tibshirani. An Introduction to the Bootstrap. Chapman&Hall,1993: 34~69.
[28] P. KaewTrakulPong and R. Bowden. A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes[J]. Image and Vision Computing, 2003,21(10): 913~929.
[29] A.Doucet, S.J.Godsill, C.Andrieu. On sequential simulation-based methods for Baysian filtering [J]. Statistics and Computing,2000,10(3) : 197~208.
[30] M.Pitt, N.Shephard. Filtering via simulation: Auxiliary particle filters[J]. Journal of the American Statistical Association,1999,94(2):590~599.
[31] Y. Wu and T. S. Huang. Robust visual tracking by integrating multiple cues based on co-inferencelearning[J]. International Journal of Computer Vision, 2004, 58(1): 55~71.
[32] J. P. Norton, G. V. Veres. Improvement of the Particle Filter by Better Choice of the Predicted Sample Set. Proceeding 15th IFAC. 2002:904~909.
[33] P. M. Djuric, J. H. Kotecha, J. Y. Tourneret, et al. Adaptive Signal Processing by Particle Filters and Discounting of Old Measurements.Accoustics,Speech, and Signal Processing. 2001,6:3733~3736.
[34] H. Nait-Charif and S. J. McKenna. Head tracking and action recognition in a smart meeting room[J]. Proceedings of 4th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Graz, Austria, 2003, 2:4~10.
[35] A. Pentland. Looking at people: Sensing for ubiquitous and wearable computing[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence, 2000, 22(1): 107~119.
[36] O.Brun, V.Teulieve, J.Garcia. Parallel particle filtering[J]. Journal of Parallel and Distributed Computing,2002,62(7) : 1186~1202.
[37] M. Isard and A. Blake. CONDENSATION-conditional density propagation for visual tracking [J].International Journal of Computer Vision, 1998, 29(1): 5~28.
[38] N. J. Gordon, D. J. Salmond and A. F. M. Smith. Novel approach to nonlinear/non-Gaussian Bay- esian state estimation[J]. IEE Proceedings-F of Radar and Signal Processing, 1993, 140(2): 107~113.
[39] A. Doucet, S. Godsill, C. Andrieu. On Sequential Monte Carlo Sampling Methods for Bayesian Filtering[J]. Statistics and Computing. 2000,10:197~208.
[40]查宇飞,张育,毕笃彦.一种基于粒子滤波的自适应运动目标跟踪方法[J].电子与信息学报,2007,29(1):92~95.
[41] L. Mun Wai, I. Cohen and J. Soon Ki. Particle filter with analytical inference for human body tracking[J]. In: Proceedings of IEEE Workshop on Motion and Video Computing, 2002,3:159~165.
[42]张波.基于粒子滤波的图像跟踪算法研究:[博士学位论文].上海:上海交通大学,2007:14~32.
[43]王其聪.复杂观测条件下的基于粒子滤波的视觉跟踪:[博士学位论文].杭州:浙江大学,2007:33~41.
[44]黄飞,李德华,姚讯.基于相关匹配及自适应模板更新的目标跟踪新方法.计算机工程, 2007, 33(16): 147~149.
[45]黄斌.基于粒子滤波的视频目标跟踪方法研究. [硕士学位论文].四川:电子科技大学,2005.
[46] J.S.Liu, R.Chen. Sequential Monte Carlo Methods for Dynamic Systems[J]. Journal of the Amer- ican Statistical Association,1998,93(443):1032~1044.
[47] B.Efron, R.J.Tibshirani. An Introduction to the Bootstrap. Chapman&Hall,1993:34~69.
[48]A.Doucet,N.Gordon.Sequential Monte Carlo Methods in Practice.New York:Springer Verlag,2001:1~41.
[49]王绍钰.基于粒子滤波器的运动目标跟踪方法研究[硕士学位论文].湖南:中南大学,2008 .
[50]胡士强,敬忠良.粒子滤波算法综述[J].控制与决策.2005,20(4):361~365.
[51]陶霖密,徐光佑.机器视觉中的颜色问题及应用[J].科学通报.2001,46(3):178-190.
[52]何斌,马天予,王运坚,朱红莲.编著[M. Visual C++数字图像处理,北京:人民邮电出版社,2001, 4:58~67.
[53]张苗辉.基于粒子滤波的目标跟踪算法研究[硕士学位论文].河南:河南大学,2005.
[54] T. Kailath. The Divergence and Bhattacharyya Distance Measures in Signal Selection[J]. IEEE Trans. Commun. Tech., 1967, 15:52~60.
[55] C. F. Shan, Y. C. Wei, T. N. Tan, et al. Real time hand tracking by combining particle filtering and mean shift[C]. Proceedings of 6th International Conference on Automatic Face and Gesture Recognition, 2004: 669~ 674.
[56]姚剑敏.粒子滤波跟踪方法研究:[博士学位论文].长春:中科院长春光机所,2004:29-44.
[57]明新勇.基于均值漂移和粒子滤波的目标跟踪算法研究: [硕士学位论文].南京:南京理工大学,2008.
[58] Cheng Chang ,Rashid Ansari. Kernel particle filter for visual tracking[J].IEEE Signal Processing Letters ,2005 ,12(3):242-245.
[59] Perez, P., Hue, C., Vermaak, J., Gangnet, M.. Color-based probabilistic tracking[J] .European Conf. on Computer Vision. 2002,32(6):661~675.
[60]胡士强,敬忠良. PF算法综述[J ] .控制与决策,2005 ,20 (4) :361~365.
[61] K. Fukunaga, L. D. Hostetler. The Estimation of the Gradient of a Density Function with Applications in Pattern Recognition[J]. IEEE Transactions on Information Theory. 1975, 21(1):32~40.
[62] G. R. Bradski. Computer Vision Face Tracking for Use in a Perceptual User Interface[J]. Intel Technology Journal. 1998, 2(2):12~21.
[63]彭宁嵩,杨杰等.Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报.2005,16(9): 1542~1551.
[64] Caifeng Shan,Tieniu Tan,YuchengWei. Real-time hand tracking using a mean shift[J] embedded particle filterPattern Recognition . 2007, 4 :1958~1970.
[65] Zhaowen Wang, Xiaokang Yang, Yi Xu, Songyu Yu .CamShift guided particle filter for visual tracking[J].Pattern Recognition Letters, 2009, 30: 407~413.
[66]孙昀,刘富强,李志鹏.基于空间梯度直方图的行人检测算法[J].中国图象图形学报, 2008,13(10):1825~1828.
[67]王新红,王晶,田敏等.基于空间边缘方向直方图的Mean Shift跟踪算法[J].中国图象图形学报, 2008,13(3):586~592.
[68]刘惟锦,章毓晋.基于Kalman滤波和边缘直方图的实时目标跟踪[J].清华大学学报(自然科学版)2008 ,48(7):1104~1107 .
[69]文志强,蔡自兴.一种基于meanshift的鲁棒性目标跟踪方法[J].计算机应用研究.2008, 25(6):1753~1758.
[70]吴铮.基于特征的图像配准算法研究. [硕士学位论文],杭州:浙江大学, 2006.
[71] Nguyen H T, Worring M, Rvan D B. Occlusion robust adaptive template tracking[C]. Proceeding Of IEEE Conference on Computer Vision, 2001, 1:678~683.
[72]贾云得.机器视觉[M],北京:科学出版社, 2002, 4:82~138.
[73]姚红革,齐华,郝重阳.复杂情形下目标跟踪的自适应粒子滤波算法[J].电子与信息学报, 2009, 31(2):275~278.
[74]任仙怡,廖运涛,张桂林等.一种新的相关跟踪方法研究[J].中国图像图形学报(A版), 2002, 7(6):553~557.
[75]黄飞,李德华,姚讯.基于相关匹配及自适应模板更新的目标跟踪新方法[J].计算机工程, 2007, 33(16): 147~149.
[76] Kass M, Witkin A, Terzopoulos D. Snakes: Active Contour Models. International Journal of Computer Vision, 1987:321~331.
[77]王震.主动轮廓模型在人脸人耳检测方面的应用. [硕士学位论文].黑龙江:哈尔滨工业大学, 2006.
[78] Williams D J, Shah M. A fast algorithm for active contours and curvature estimation[J]. CVGIP: Image Understanding, 1992, 55(1): 14~26.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |