图像序列中目标跟踪技术研究
|
摘要
目标跟踪一直以来都是计算机视觉领域中研究的难点跟热点。由于光照变化、背景杂乱、视角变化、遮挡以及目标形变等因素的影响,当前大部分的目标跟踪算法仍然很难达到理想的跟踪效果,距离实际的应用还有一定的距离。然而目标跟踪又是高层计算机视觉任务,如越界、翻越等异常行为检测、道路车流量和公共场所人流量统计、事件分析和事件理解的基础,因此,对于该课题的研究仍然具有十分重要的理论意义和现实意义。
本文主要围绕均值漂移这种简单高效的产生式目标跟踪算法和现阶段研究比较热门的基于判别式模型的目标跟踪算法进行研究。主要研究成果如下：
首先,基于背景加权和运动方向信息,我们提出了一种产生式目标跟踪算法。针对传统均值漂移算法目标模板可能包含一部分背景信息,本文用背景加权直方图来减少背景信息对跟踪模板的影响,并重点分析了它的作用原理。基于分析所得结论,我们用局部运动滤波器来估计目标的运动方向,然后通过相同的方式将跟踪目标的运动方向信息嵌入到均值漂移目标跟踪算法中,以提高跟踪算法的性能。此外,针对传统的均值漂移跟踪算法不能适应目标外观的变化这个缺点,我们提出了一个新的目标模板在线更新策略。对于背景模型的更新,不但用到了背景本身的信息而且还用到了待跟踪目标的信息。在真实的图像序列上的对比实验结果表明,本文提出的算法提高了原始算法的跟踪性能。
其次,基于空间信息和模型更新,我们提出了一种判别式目标跟踪算法。在基于图像块袋的判别式目标外观模型中,针对图像块和目标本身的空间位置依赖关系以及图像块与图像块之间的上下文关系,在建立判别式模型和构造置信度图的时候,我们将空间和上下文信息以加权的方式融合到判别式跟踪算法中,使得所建立的目标外观模型更加科学合理、描述能力更强,置信度图更加精确。此外,我们提出了一种新的在线模型更新策略来适应不断变化的目标外观。与现有的几个比较流行的跟踪算法进行了比较,实验结果证明我们提出的方法提高了目标跟踪的精度和稳定性,相对于产生式目标跟踪算法具有较好的区分目标跟背景的能力。
然后,基于判别式目标模型区分目标跟踪背景的能力,我们首先提出了一种判别式均值漂移目标跟踪算法。我们利用判别式模型区分目标跟周围背景的能力,将其嵌入到产生式目标跟踪算法-均值漂移目标跟踪算法中,以此来提高均值漂移目标跟踪算法区分目标跟周围背景的能力,从而提高跟踪性能,改善跟踪效果。此外,针对目标运动过程中的尺度变化,我们基于随机厥理论并结合产生式和判别式目标模型,提出了一种尺度自适应目标跟踪算法。跟几个主流的尺度处理目标跟踪算法的对比实验显示,该算法在跟踪变尺度目标方面具有一定的有效性,它提高了原始算法跟踪变尺度目标的能力。
最后,我们对我们在本文中所做的工作进行了归纳总结,给出了本文的主要创新点,并基于本文的研究内容,探讨了未来在目标跟踪方面仍然可以研究的内容。
Target tracking has been one of the focuses and difficulties in computer vision. Due to the illumination changing, background clutter, view changing, occlusion and deformation, at the present stage, most of these the tracking algorithms can not meet the requirement of application. However, the object tracking is the base of the high level computer vision task, such as abnormal behavior like crossing detection, people counting in public places and cars counting on the roads, event analysis and event understand. Therefore, research on this issue has important theoretical significance and practical significance.
In this paper, we start our research beginning with the mean shift object tracking algorithm as well as these tracking approaches based on the discriminative object model The mean shift object tracking is a simple and effective algorithm which has been studied by lots of researchers. The tracking methods based on discriminative model have become a hot issue due to the development of the machine learning technology. The major results of our research are as follow:
Firstly, we proposed an improved generative tracking algorithm based on the back-ground weighted histogram and the motion direction information. Since the object rect-angle used in the mean shift object tracking maybe include some background pixels, this paper utilizes the background weighted histogram to reduce the influence of the background information. We analyze its principle at details. Based on the analysis, we estimate the motion direction of the object using the motion filters. After that the motion direction in-formation is embedded into the mean shift tracking algorithm to improve the performance of the tracking approach. In addition, we propose a new method for model updating in or-der to track the objects whose appearance change continually. As to the background model updating, we utilize not only the background information, but also we make full use of the target object information. The experiment results show that our proposed method improve the performance of the original method.
Secondly, based on the spatial information and model updating we proposed a discrim- inative object tracking algorithm. In the tracking algorithm based on bag of patches, in consideration of the spatial position dependence between these small image patches and the target object as well as the spatial context between these small images patches. We make full use of them when we build the appearance model and construct the confidence map so that the appearance is more scientific and reasonable and the confidence map is more accurate. In addition, a new appearance model updating strategy is proposed to adapt to the variance of the object appearance. The experiment results show that the improved tracking method enhances the performance in accuracy and stability. Comparing with the generative method, the discriminative method does better in distinguishing the object from the background.
After that, we proposed a discriminative mean shift tracking method based on the good performance of the discriminative method in distinguishing the target object from the back-ground. We embed the discriminative model into the mean shift tracking framework and make use of its discriminative ability to separate the object from the background. In ad-dition, as to the scale change during the process, we propose a scale adaptive tracking al-gorithm based on random ferns classifiers as well as generative and discriminative model. The compared experiment results illustrate that the proposed method improves the ability of tracking object with scale change.
Finally, we summarize our work in this paper, present its innovative points, and then we discuss the future work and research.
本文主要围绕均值漂移这种简单高效的产生式目标跟踪算法和现阶段研究比较热门的基于判别式模型的目标跟踪算法进行研究。主要研究成果如下：
首先,基于背景加权和运动方向信息,我们提出了一种产生式目标跟踪算法。针对传统均值漂移算法目标模板可能包含一部分背景信息,本文用背景加权直方图来减少背景信息对跟踪模板的影响,并重点分析了它的作用原理。基于分析所得结论,我们用局部运动滤波器来估计目标的运动方向,然后通过相同的方式将跟踪目标的运动方向信息嵌入到均值漂移目标跟踪算法中,以提高跟踪算法的性能。此外,针对传统的均值漂移跟踪算法不能适应目标外观的变化这个缺点,我们提出了一个新的目标模板在线更新策略。对于背景模型的更新,不但用到了背景本身的信息而且还用到了待跟踪目标的信息。在真实的图像序列上的对比实验结果表明,本文提出的算法提高了原始算法的跟踪性能。
其次,基于空间信息和模型更新,我们提出了一种判别式目标跟踪算法。在基于图像块袋的判别式目标外观模型中,针对图像块和目标本身的空间位置依赖关系以及图像块与图像块之间的上下文关系,在建立判别式模型和构造置信度图的时候,我们将空间和上下文信息以加权的方式融合到判别式跟踪算法中,使得所建立的目标外观模型更加科学合理、描述能力更强,置信度图更加精确。此外,我们提出了一种新的在线模型更新策略来适应不断变化的目标外观。与现有的几个比较流行的跟踪算法进行了比较,实验结果证明我们提出的方法提高了目标跟踪的精度和稳定性,相对于产生式目标跟踪算法具有较好的区分目标跟背景的能力。
然后,基于判别式目标模型区分目标跟踪背景的能力,我们首先提出了一种判别式均值漂移目标跟踪算法。我们利用判别式模型区分目标跟周围背景的能力,将其嵌入到产生式目标跟踪算法-均值漂移目标跟踪算法中,以此来提高均值漂移目标跟踪算法区分目标跟周围背景的能力,从而提高跟踪性能,改善跟踪效果。此外,针对目标运动过程中的尺度变化,我们基于随机厥理论并结合产生式和判别式目标模型,提出了一种尺度自适应目标跟踪算法。跟几个主流的尺度处理目标跟踪算法的对比实验显示,该算法在跟踪变尺度目标方面具有一定的有效性,它提高了原始算法跟踪变尺度目标的能力。
最后,我们对我们在本文中所做的工作进行了归纳总结,给出了本文的主要创新点,并基于本文的研究内容,探讨了未来在目标跟踪方面仍然可以研究的内容。
Target tracking has been one of the focuses and difficulties in computer vision. Due to the illumination changing, background clutter, view changing, occlusion and deformation, at the present stage, most of these the tracking algorithms can not meet the requirement of application. However, the object tracking is the base of the high level computer vision task, such as abnormal behavior like crossing detection, people counting in public places and cars counting on the roads, event analysis and event understand. Therefore, research on this issue has important theoretical significance and practical significance.
In this paper, we start our research beginning with the mean shift object tracking algorithm as well as these tracking approaches based on the discriminative object model The mean shift object tracking is a simple and effective algorithm which has been studied by lots of researchers. The tracking methods based on discriminative model have become a hot issue due to the development of the machine learning technology. The major results of our research are as follow:
Firstly, we proposed an improved generative tracking algorithm based on the back-ground weighted histogram and the motion direction information. Since the object rect-angle used in the mean shift object tracking maybe include some background pixels, this paper utilizes the background weighted histogram to reduce the influence of the background information. We analyze its principle at details. Based on the analysis, we estimate the motion direction of the object using the motion filters. After that the motion direction in-formation is embedded into the mean shift tracking algorithm to improve the performance of the tracking approach. In addition, we propose a new method for model updating in or-der to track the objects whose appearance change continually. As to the background model updating, we utilize not only the background information, but also we make full use of the target object information. The experiment results show that our proposed method improve the performance of the original method.
Secondly, based on the spatial information and model updating we proposed a discrim- inative object tracking algorithm. In the tracking algorithm based on bag of patches, in consideration of the spatial position dependence between these small image patches and the target object as well as the spatial context between these small images patches. We make full use of them when we build the appearance model and construct the confidence map so that the appearance is more scientific and reasonable and the confidence map is more accurate. In addition, a new appearance model updating strategy is proposed to adapt to the variance of the object appearance. The experiment results show that the improved tracking method enhances the performance in accuracy and stability. Comparing with the generative method, the discriminative method does better in distinguishing the object from the background.
After that, we proposed a discriminative mean shift tracking method based on the good performance of the discriminative method in distinguishing the target object from the back-ground. We embed the discriminative model into the mean shift tracking framework and make use of its discriminative ability to separate the object from the background. In ad-dition, as to the scale change during the process, we propose a scale adaptive tracking al-gorithm based on random ferns classifiers as well as generative and discriminative model. The compared experiment results illustrate that the proposed method improves the ability of tracking object with scale change.
Finally, we summarize our work in this paper, present its innovative points, and then we discuss the future work and research.
引文
[1]姚秀娟,彭晓乐,张永科.几种精确制导技术简述.激光与红外,2006,36(5)：338-340.
[2]Gavrila D. M. The visual analysis of human movement:A survey. Computer vision and image understanding,1999,73(1):82-98.
[3]Sanfeliu A., Villanueva J. J. An approach of visual motion analysis. Pattern recogni-tion letters,2005,26(3):355-368.
[4]Pentland A. Looking at people:Sensing for ubiquitous and wearable computing. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(1):107-119.
[5]Zhu Z., Xu G., Yang B., et al. VISATRAM:A real-time vision system for automatic traffic monitoring. Image and Vision Computing,2000,18(10):781-794.
[6]Pai C.-J., Tyan H.-R., Liang Y.-M., et al. Pedestrian detection and tracking at cross-roads. Pattern Recognition,2004,37(5):1025-1034.
[7]Betke M., Haritaoglu E., Davis L. S. Real-time multiple vehicle detection and track-ing from a moving vehicle. Machine Vision and Applications,2000,12(2):69-83.
[8]Bonin-Font F., Ortiz A., Oliver G. Visual navigation for mobile robots:A survey. Journal of intelligent and robotic systems,2008,53(3):263-296.
[9]Papanikolopoulos N. P., Khosla P. K., Kanade T. Visual tracking of a moving tar-get by a camera mounted on a robot:A combination of control and vision. IEEE Transactions on Robotics and Automation,1993,9(1):14-35.
[10]Li T.-H., Chang S.-J. Autonomous fuzzy parking control of a car-like mobile robot. IEEE Transactions on Systems, Man and Cybernetics, Part A:Systems and Humans, 2003,33(4):451-465.
[11]Bardinet E., Cohen L. D., Ayache N. Tracking medical 3D data with a parametric deformable model, in:Proceedings of International Symposium on Computer Vision, Florida, USA.,1995,299-304.
[12]Guerrero J., Salcudean S. E., McEwen J. A., et al. Real-time vessel segmentation and tracking for ultrasound imaging applications. IEEE Transactions on Medical Imaging,2007,26(8):1079-1090.
[13]Tang C.-W. Spatiotemporal visual considerations for video coding. IEEE Transac-tions on Multimedia,2007,9(2):231-238.
[14]Agrafiotis D., Davies S., Canagarajah N., et al. Towards efficient context-specific video coding based on gaze-tracking analysis. ACM Transactions on Multimedia Computing, Communications, and Applications,2007,3(4):4.
[15]Hu W., Xie D., Fu Z., et al. Semantic-based surveillance video retrieval. IEEE Transactions on Image Processing,2007,16(4):1168-1181.
[16]Zheng J. Y., Murata A. Acquiring a complete 3D model from specular motion un-der the illumination of circular-shaped light sources. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):913-920.
[17]Remondino F.3-D reconstruction of static human body shape from image sequence. Computer Vision and Image Understanding,2004,93(1):65-85.
[18]Abdelkader M. F., Chellappa R., Zheng Q., et al. Integrated motion detection and tracking for visual surveillance. in:Proceedings of IEEE International Conference on Computer Vision Systems.
[19]Babu R. V, Perez P., Bouthemy P. Robust tracking with motion estimation and local kernel-based color modeling. Image and Vision Computing,2007,25(8):1205-1216.
[20]Elgammal A., Duraiswami R., Harwood D., et al. Background and foreground mod-eling using nonparametric kernel density estimation for visual surveillance. Proceed-ings of the IEEE,2002,90(7):1151-1163.
[21]张建宇. 后DVR时代来临—视频监控产品的市场分析.http://www.21csp.com.cn/html/View_2008/03/27/2E3C5C9004.shtml,2013.04.04.
[22]国际电子商情. 中国安防设备市场分析与瞭望.http://www.ca800.com/news/html/2006-3-16/n40469_0.htm,2013.04.04.
[23]百度知道.平安城市.http://baike.baidu.com/view/1162195.htm,2013.04.04.
[24]中国报告大厅.2009-2012年中国视频监控系统市场研究及发展前景预测报告.http://www.chinabgao.com/reports/61141.html,2013.04.04.
[25]CCTIME飞象网.智能视频监控技术与应用分析.http://www.cctime.com/html/2010-8-6/2010861710277893.htm,2013.04.04.
[26]Yilmaz A., Javed O., Shah M. Object tracking:A survey. Acm Computing Surveys (CSUR),2006,38(4):1-45.
[27]Sethi I. K., Jain R. Finding trajectories of feature points in a monocular image se-quence. IEEE Transactions on Pattern Analysis and Machine Intelligence,1987, 9(1):56-73.
[28]Salari V, Sethi I. K. Feature point correspondence in the presence of occlusion. IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):87-91.
[29]Rangarajan K., Shah M. Establishing motion correspondence. in:Proceedings of IEEE Conference Vision Graphies Image Proces, Orlando, FL, USA,1991,56-73.
[30]Intille S. S., Davis J. W., Bobick A. F. Real-time closed-world tracking. in:Pro-ceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA,1997,697-703.
[31]Veenman C. J., Reinders M. J. T., Backer E. Resolving motion correspondence for densely moving points. IEEE Transactions on Pattern Analysis and Machine Intelli-gence,2001,23(1):54-72.
[32]Shafique K., Shah M. A non-iterative greedy algorithm for multi-frame point corre-spondence. in:Proceedings of IEEE International Conference on Computer Vision, Nice, France,2003,110-115.
[33]Stalder S., Grabner H., Van Gool L. Cascaded confidence filtering for improved tracking-by-detection,.in:Proceedings of European conference on Computer Vision, Crete,Greece,2010, Springer-Verlag,369-382.
[34]Broida T. J., Chellappa R. Estimation of object motion parameters from noisy images. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986, (1):90-99.
[35]Arulampalam M. S., Maskell S., Gordon N., et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. Signal Processing, IEEE Transac-tions on,2002,50(2):174-188.
[36]Beymer D., Konolige K. Real-time tracking of multiple people using continuous detection, in:Proceedings of IEEE International Conference on Computer Vision Frame-Rate Workshop, Kerkyra, Greece,1999,56-60.
[37]Rosales R., Sclaroff S.3D trajectory recovery for tracking multiple objects and trajec-tory guided recognition of actions. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Ft. Collins, CO, USA,1999,117-123.
[38]Kitagawa G. Non-Gaussian State—Space Modeling of Nonstationary Time Series. Journal of the American statistical association,1987,82(400):1032-1041.
[39]Isard M., Blake A. Condensation—conditional density propagation for visual track-ing. International journal of computer vision,1998,29(1):5-28.
[40]Rasmussen C., Hager G. D. Joint probabilistic data association methods for tracking complex visual objects. IEEE Transactions on Pattern Analysis and Machine Intelli-gence,2001,23(6):560-576.
[41]Reid D. An algorithm for tracking multiple targets. IEEE Transactions on Automatic Control,1979,24(6):843-854.
[42]Chang Y.-L., Aggarwal J.3d structure reconstruction from an ego motion sequence using statistical estimation and detection theory, in:Proceedings of IEEE Workshop on Visual Motion, Princeton, NJ, USA,1991,268-273.
[43]Streit R. L., Luginbuhl T. E. Maximum likelihood method for probabilistic multi-hypothesis tracking. in:Proceedings of SPIE's International Symposium on Optical Engineering and Photonics in Aerospace Sensing, Orlando, FL, USA,1994,394-405.
[44]Cox I. J., Hingorani S. L. An efficient implementation of Reid's multiple hypoth-esis tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(2):138-150.
[45]Murty K. G. Letter to the Editor-An Algorithm for Ranking all the Assignments in Order of Increasing Cost. Operations Research,1968,16(3):682-687.
[46]Huttenlocher D. P., Noh J. J., Rucklidge W. J. Tracking non-rigid objects in complex scenes.in:Proceedings of International Conference on Computer Vision., Berlin, Germany,1993,93-101.
[47]Li B., Chellappa R., Zheng Q., et al. Model-based temporal object verification using video. IEEE Transactions on Image Processing,2001,10(6):897-908.
[48]Jech T. J. Set theory, volume 79. Academic press,1978.
[49]Haritaoglu I., Harwood D., Davis L. S. W4:real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):809-830.
[50]Sato K., Aggarwal J. Temporal spatio-velocity transform and its application to track-ing and interaction. Computer Vision Image Understande,2004,96(2):100-128.
[51]Shi Y., Karl W. C. Real-time tracking using level sets, in:Proceedings of IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA,2005,34-41.
[52]Bertalmfo M., Sapiro G., Randall G. Morphing active contours. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(7):733-737.
[53]Mansouri A.-R. Region tracking via level set PDEs without motion computation. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2002,24(7):947-961.
[54]Cremers D., Schnorr C. Statistical shape knowledge in variational motion segmenta-tion. Image and Vision Computing,2003,21(1):77-86.
[55]Ronfard R. Region-based strategies for active contour models. International Journal of Computer Vision,1994,13(2):229-251.
[56]Yilmaz A., Li X., Shah M. Contour-based object tracking with occlusion handling in video acquired using mobile cameras. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(11):1531-1536.
[57]Terzopoulos D., Szeliski R. Tracking with Kalman snakes. in:Proceedings of Active vision. MIT press,1993,3-20.
[58]MacCormick J., Blake A. Probabilistic exclusion and partitioned sampling for multi-ple object tracking. International Journal of Computer Vision,2000,39(1):57-71.
[59]Chen Y., Rui Y., Huang T. S. JPDAF based HMM for real-time contour tracking. in: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA,2001, IEEE,I-543.
[60]Wang X., Hua G., Han T. X. Discriminative tracking by metric learning. in:Proceed-ings of European Conference on Computer Vision, Crete, Greece,2010,200-214.
[61]Murase H., Nayar S. K. Visual learning and recognition of 3-Dobjects from appear-ance. Int'1. J. Computer Vision,1995,14:5-24.
[62]Hager G. D., Belhumeur P. N. Efficient region tracking with parametric models of geometry and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(10):1025-1039.
[63]Black M. J., Jepson A. D. Eigentracking:Robust matching and tracking of articulated objects using a view-based representation. in:Proceedings of European Conf. on Computer Vision, Cambridge, UK,1996,329-342.
[64]Ho J., Lee K.-C., Yang M.-H., et al. Visual tracking using learned linear subspaces. in: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA,2004,1-782.
[65]Ross D., Lim J., Yang M.-H. Adaptive probabilistic visual tracking with incremen-tal subspace update. in:Proceedings of European Conference on Computer Vision, Prague, Czech Republic,2004,470-482.
[66]Lim J., Ross D., Lin R.-S., et al. Incremental learning for visual tracking. Advances in neural information processing systems,2004,17:793-800.
[67]Ross D. A., Lim J., Lin R.-S., et al. Incremental learning for robust visual tracking. International Journal of Computer Vision,2008,77(1-3):125-141.
[68]Li X., Hu W., Zhang Z., et al. Robust visual tracking based on incremental tensor subspace learning. in:Proceedings of IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil,2007,1-8.
[69]Li X., Hu W., Zhang Z., et al. Visual tracking via incremental log-euclidean rieman-nian subspace learning. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, USA,2008, IEEE,1-8.
[70]Cootes T. F., Edwards G. J., Taylor C. J. Active appearance models. IEEE Transac-tions on Pattern Analysis and Machine Intelligence,2001,23(6):681-685.
[71]Fukunaga K., Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions on Information Theory,1975, 21(1):32-40.
[72]Cheng Y. Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
[73]Comaniciu D., Ramesh V., Meer P. Real-time tracking of non-rigid objects using mean shift, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, SC, USA,2000,142-149.
[74]Comaniciu D., Ramesh V., Meer P. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[75]Haritaoglu I., Flickner M. Detection and tracking of shopping groups in stores. in: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA,2001,1-431.
[76]Ning J., Zhang L., Zhang D., et al. Robust object tracking using joint color-texture histogram. International Journal of Pattern Recognition and Artificial Intelligence, 2009,23(7):1245-1263.
[77]Nguyen Q. A., Robles-Kelly A., Shen C. Enhanced kernel-based tracking for monochromatic and thermographic video. in:Proceedings of IEEE International Conference on Video and Signal Based Surveillance, Sydney, NSW, Australia,2006, 28-28.
[78]张涛,蔡灿辉.基于多特征Mean Shift的人脸跟踪算法.电子与信息学报,2009,31(8)：1816-1820.
[79]Ojala T., Pietikainen M., Maenpaa T. Multiresolution gray-scale and rotation invari-ant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[80]Tan X., Triggs B. Enhanced local texture feature sets for face recognition under diffi-cult lighting conditions. IEEE Transactions on Image Processing,2010,19(6):1635-1650.
[81]Wang J., Chen X., Gao W. Online selecting discriminative tracking features using particle filter. in:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA,2005,1037-1042.
[82]Wang J., Yagi Y. Integrating color and shape-texture features for adaptive real-time object tracking. IEEE Transactions on Image Processing,2008,17(2):235-240.
[83]袁广林,薛模根,韩裕生等.基于自适应多特征融合的nean shift目标跟踪.计算机研究与发展,2010,(009)：1663-1671.
[84]王永忠,梁彦,赵春晖等.基于多特征自适应融合的核跟踪方法.自动化学报,2008,34(4)：393-399.
[85]颜佳,吴敏渊,陈淑珍等.跟踪窗口自适应的Mean Shift跟踪.光学精密工程,2009,17(10)：2606-2611.
[86]Liu B., Huang J., Yang L., et al. Robust tracking using local sparse appearance model and k-selection. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA,2011,1313-1320.
[87]Collins R. T. Mean-shift blob tracking through scale space, in:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, WI, USA,2003,Ⅱ-234.
[88]陈晓鹏,李成荣,罗杨宇等.自适应带宽均值移动算法及目标跟踪.机器人,2008,30(2)：147-154.
[89]Khan Z. H., Gu I., Backhouse A. G. Robust visual object tracking using multi-mode anisotropic mean shift and particle filters. IEEE Transactions on Circuits and Systems for Video Technology,2011,21(1):74-87.
[90]齐苏敏,黄贤武,伊怀峰.基于各向异性核函数的均值漂移跟踪算法.电子与信息学报,2007,29(3)：686-689.
[91]Zivkovic Z., Krose B. An EM-like algorithm for color-histogram-based object track-ing. in:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA,2004,1-798.
[92]Zivkovic Z., Cemgil A. T., Krose B. Approximate Bayesian methods for kernel-based object tracking. Computer Vision and Image Understanding,2009,113(6):743-749.
[93]彭宁嵩,杨杰,刘志.Mean shift跟踪算法中核函数带宽的自动选择.软件学报,2005,16(9)：1542-1500.
[94]康一梅,谢晚冬,胡江等.目标尺度自适应的Mean Shift跟踪算法.兵工学报,2011,32(2)：210-216.
[95]Zhao C., Knight A., Reid I. Target tracking using mean-shift and affine structure. in:Proceedings of International Conference on Pattern Recognition, Tampa, Florida, USA,2008,1-5.
[96]Chen A.-h., Zhu M., Wang Y.-h., et al. Mean shift tracking combining SIFT. in: Proceedings of International Conference on Signal Processing, Beijing, China,2008, 1532-1535.
[97]Ning J., Zhang L., Zhang D., et al. Scale and orientation adaptive mean shift tracking. IET Computer Vision,2012,6(1):52-61.
[98]Bradski G. R. Real time face and object tracking as a component of a perceptual user interface. in:Proceedings of IEEE Workshop on Applications of Computer Vision, Washington, DC, USA,1998,214-219.
[99]Isard M., Blake A. Contour tracking by stochastic propagation of conditional density, in:Proceedings of European Conference on Computer Vision, Cambridge, UK,1996, 343-356.
[100]Isard M., Blake A. Condensation-conditional density propagation for visual track-ing. International journal of computer vision,1998,29(1):5-28.
[101]Nummiaro K., Koller-Meier E., Van Gool L. An adaptive color-based particle filter. Image and Vision Computing,2003,21(1):99-110.
[102]Okuma K., Taleghani A., De Freitas N., et al. A boosted particle filter:Multitarget detection and tracking. in:Proceedings of European Conference on Computer Vision, Prague, Czech Republic,2004,28-39.
[103]Mei X., Ling H. Robust visual tracking using L1 minimization, in:Proceedings of IEEE International Conference on Computer Vision, Kyoto, Japan,2009,1436-1443.
[104]Mei X., Ling H. Robust visual tracking and vehicle classification via sparse repre-sentation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011, 33(11):2259-2272.
[105]Wu Y., Ling H., Yu J., et al. Blurred target tracking by blur-driven tracker. in:Pro-ceedings of IEEE International Conference on Computer Vision, Barcelona, Spain, 2011,1100-1107.
[106]Mei X., Ling H., Wu Y., et al. Minimum error bounded efficient L1 tracker with occlusion detection. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA,2011,1257-1264.
[107]Yin Z., Collins R. Spatial divide and conquer with motion cues for tracking through clutter. in:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA,2006,570-577.
[108]Mahadevan V., Vasconcelos N. Saliency-based discriminant tracking. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA,2009,1007-1013.
[109]Avidan S. Support vector tracking. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence,2004,26(8):1064-1072.
[110]Avidan S. Ensemble tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(2):261-271.
[111]Grabner H., Grabner M., Bischof H. Real-time tracking via on-line boosting. in: Proceedings of BMVC, Edinburgh, England,2006,47-56.
[112]Grabner H., Bischof H. On-line boosting and vision. in:Proceedings of IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA,2006,260-267.
[113]Grabner H., Leistner C., Bischof H. Semi-supervised on-line boosting for robust tracking. in:Proceedings of European Conference on Computer Vision, Marseilles, France,2008,234-247.
[114]Stalder S., Grabner H., Van Gool L. Beyond semi-supervised tracking:Tracking should be as simple as detection, but not simpler than recognition. in:Proceedings of IEEE International Conference on Computer Vision Workshops, Kyoto, Japan,2009, 1409-1416.
[115]Babenko B., Yang M.-H., Belongie S. Visual tracking with online multiple instance learning, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA,2009,983-990.
[116]Zhang K., Song H. Real-time visual tracking via online weighted multiple instance learning. Pattern Recognition,46.
[117]Zeisl B., Leistner C., Saffari A., et al. On-line semi-supervised multiple-instance boosting, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA,2010,1879-1879.
[118]Yang F., Lu H., Chen Y.-W. Human tracking by multiple kernel boosting with local-ity affinity constraints. in:Proceedings of Asian Conference on Computer Vision, Queenstown,New Zealand,2011,39-50.
[119]Jia X., Wang D., Lu H. Fragment-based tracking using online multiple kernel learn-ing, in:Proceedings of IEEE International Conference on Image Processing, Orlando, Florida, U.S.A,2012,393-396.
[120]Lu H., Zhang W., Chen Y.-W. On feature combination and multiple kernel learn-ing for object tracking. in:Proceedings of Asian Conference on Computer Vision, Queenstown,New Zealand,2011,511-522.
[121]Luo W., Li X., Li W., et al. Robust visual tracking via transfer learning. in:Pro-ceedings of IEEE International Conference on Image Processing, Brussels, Belguim, 2011,485-488.
[122]Gao C., Sang N., Huang R. Online Transfer Boosting for object tracking, in:Pro-ceedings of International Conference on Pattern Recognition, Tsukuba Science City, JAPAN,2012,906-909.
[123]Dan Z., Sang N., Huang R., et al. Instance transfer boosting for object tracking. Optik-International Journal for Light and Electron Optics,2012.
[124]Wang S., Lu H., Yang F., et al. Superpixel tracking, in:Proceedings of IEEE Inter-national Conference on Computer Vision, Barcelona, Spain,2011,1323-1330.
[125]Tang M., Peng X. Robust tracking with discriminative ranking lists. IEEE Transac-tions on Image Processing,2012,21(7):3273-3281.
[126]Lepetit V., Fua P. Keypoint recognition using randomized trees. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(9):1465-1479.
[127]Ozuysal M., Calonder M., Lepetit V., et al. Fast keypoint recognition using ran-dom ferns. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010, 32(3):448-461.
[128]Ozuysal M., Fua P., Lepetit V. Fast keypoint recognition in ten lines of code. in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Min-neapolis, Minnesota, USA,2007,1-8.
[129]Bosch A., Zisserman A., Muoz X. Image classification using random forests and ferns, in:Proceedings of IEEE International Conference on Computer Vision, Riode Janeiro, Brazil,2007,1-8.
[130]Villamizar M., Moreno-Noguer F., Andrade-Cetto J., et al. Efficient rotation invariant object detection using boosted random ferns, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA,2010,1038-1045.
[131]Villamizar M., Moreno-Noguer F., Andrade-Cetto J., et al. Shared random ferns for efficient detection of multiple categories, in:Proceedings of International Conference on Pattern Recognition, Istanbul, Turkey,2010,388-391.
[132]Gonzalez R.C. W. R.数字图像处理,第二版.阮秋琦,阮宇星等译.中国,北京：电子工业出版社,March,2003.
[133]Lienhart R., Maydt J. An extended set of haar-like features for rapid object detection. in:Proceedings of International Conference on Image Processing, Rochester,New York,2002,I-900.
[134]Dalal N., Triggs B. Histograms of oriented gradients for human detection. in:Pro-ceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA,2005,886-893.
[135]Kumar R., Sawhney H., Samarasekera S., et al. Aerial video surveillance and ex-ploitation. IEEE Generation Surveil System,2001,89(10):1518-1539.
[136]Jeyakar J., Babu R. V., Ramakrishnan K. Robust object tracking with background-weighted local kernels. Computer Vision and Image Understanding,2008, 112(3):296-309.
[137]Li L., Feng Z. An efficient object tracking method based on adaptive nonparametric approach. Opto-Electronics Review,2005,13(4):325.
[138]Allen J. G., Xu R. Y, Jin J. S. Mean shift object tracking for a SIMD computer. in:Proceedings of International Conference on Information Technology and Appli-cations, Washington, DC, USA,2005,692-697.
[139]Ning J., Zhang L., Zhang D., et al. Robust mean-shift tracking with corrected background-weighted histogram. IET Computer Vision,2012,6(1):62-69.
[140]Horn B. K., Schunck B. G. Determining optical flow. Artificial intelligence,1981, 17(1):185-203.
[141]Barron J. L., Fleet D. J., Beauchemin S. Performance of optical flow techniques. International journal of computer vision,1994,12(1):43-77.
[142]Bigun J., Granlund G. H., Wiklund J. Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Transactions on Pattern Anal-ysis and Machine Intelligence,1991,13(8):775-790.
[143]Beauchemin S. S., Barron J. L. The computation of optical flow. ACM Computing Surveys (CSUR),1995,27(3):433-466.
[144]Liu B., Zaccarin A. New fast algorithms for the estimation of block motion vectors. IEEE Transactions on Circuits and Systems for Video Technology,1993,3(2):148-157.
[145]Po L.-M., Ma W.-C. A novel four-step search algorithm for fast block motion es-timation. IEEE Transactions on Circuits and Systems for Video Technology,1996, 6(3):313-317.
[146]Li R., Zeng B., Liou M. L. A new three-step search algorithm for block motion estimation. IEEE Transactions on Circuits and Systems for Video Technology,1994, 4(4):438-442.
[147]Wang J., Yagi Y. Adaptive mean-shift tracking with auxiliary particles. IEEE Trans-actions on Systems, Man, and Cybernetics, Part B:Cybernetics,2009,39(6):1578-1589.
[148]Viola P., Jones M. J., Snow D. Detecting pedestrians using patterns of motion and appearance. International Journal of Computer Vision,2005,63(2):153-161.
[149]Perazzi F., Krahenbuhl P., Pritch Y., et al. Saliency filters:Contrast based filtering for salient region detection, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA,2012,733-740.
[150]Santner J., Leistner C., Saffari A., et al. Prost:Parallel robust online simple tracking, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA,2010,723-730.
[151]Yang F., Lu H., Chen Y.-W. Bag of features tracking. in:Proceedings of International Conference on Pattern Recognition, Hong Kong, China,2010,153-156.
[152]Zheng F., Webb G. I. A comparative study of semi-naive Bayes methods in classifica-tion learning. in:Proceedings of 4Th Australasian data mining conference, Sydney, Australia,2005,141-156.
[153]Trajkovic M., Hedley M. Fast corner detection. Image and Vision Computing,1998, 16(2):75-87.
[154]Schmid C., Mohr R., Bauckhage C. Evaluation of interest point detectors. Interna-tional Journal of computer vision,2000,37(2):151-172.
[155]Ren X., Malik J. Learning a classification model for segmentation, in:Proceedings of IEEE International Conference on Computer Vision, Nice, France,2003,10-17.
[2]Gavrila D. M. The visual analysis of human movement:A survey. Computer vision and image understanding,1999,73(1):82-98.
[3]Sanfeliu A., Villanueva J. J. An approach of visual motion analysis. Pattern recogni-tion letters,2005,26(3):355-368.
[4]Pentland A. Looking at people:Sensing for ubiquitous and wearable computing. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(1):107-119.
[5]Zhu Z., Xu G., Yang B., et al. VISATRAM:A real-time vision system for automatic traffic monitoring. Image and Vision Computing,2000,18(10):781-794.
[6]Pai C.-J., Tyan H.-R., Liang Y.-M., et al. Pedestrian detection and tracking at cross-roads. Pattern Recognition,2004,37(5):1025-1034.
[7]Betke M., Haritaoglu E., Davis L. S. Real-time multiple vehicle detection and track-ing from a moving vehicle. Machine Vision and Applications,2000,12(2):69-83.
[8]Bonin-Font F., Ortiz A., Oliver G. Visual navigation for mobile robots:A survey. Journal of intelligent and robotic systems,2008,53(3):263-296.
[9]Papanikolopoulos N. P., Khosla P. K., Kanade T. Visual tracking of a moving tar-get by a camera mounted on a robot:A combination of control and vision. IEEE Transactions on Robotics and Automation,1993,9(1):14-35.
[10]Li T.-H., Chang S.-J. Autonomous fuzzy parking control of a car-like mobile robot. IEEE Transactions on Systems, Man and Cybernetics, Part A:Systems and Humans, 2003,33(4):451-465.
[11]Bardinet E., Cohen L. D., Ayache N. Tracking medical 3D data with a parametric deformable model, in:Proceedings of International Symposium on Computer Vision, Florida, USA.,1995,299-304.
[12]Guerrero J., Salcudean S. E., McEwen J. A., et al. Real-time vessel segmentation and tracking for ultrasound imaging applications. IEEE Transactions on Medical Imaging,2007,26(8):1079-1090.
[13]Tang C.-W. Spatiotemporal visual considerations for video coding. IEEE Transac-tions on Multimedia,2007,9(2):231-238.
[14]Agrafiotis D., Davies S., Canagarajah N., et al. Towards efficient context-specific video coding based on gaze-tracking analysis. ACM Transactions on Multimedia Computing, Communications, and Applications,2007,3(4):4.
[15]Hu W., Xie D., Fu Z., et al. Semantic-based surveillance video retrieval. IEEE Transactions on Image Processing,2007,16(4):1168-1181.
[16]Zheng J. Y., Murata A. Acquiring a complete 3D model from specular motion un-der the illumination of circular-shaped light sources. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):913-920.
[17]Remondino F.3-D reconstruction of static human body shape from image sequence. Computer Vision and Image Understanding,2004,93(1):65-85.
[18]Abdelkader M. F., Chellappa R., Zheng Q., et al. Integrated motion detection and tracking for visual surveillance. in:Proceedings of IEEE International Conference on Computer Vision Systems.
[19]Babu R. V, Perez P., Bouthemy P. Robust tracking with motion estimation and local kernel-based color modeling. Image and Vision Computing,2007,25(8):1205-1216.
[20]Elgammal A., Duraiswami R., Harwood D., et al. Background and foreground mod-eling using nonparametric kernel density estimation for visual surveillance. Proceed-ings of the IEEE,2002,90(7):1151-1163.
[21]张建宇. 后DVR时代来临—视频监控产品的市场分析.http://www.21csp.com.cn/html/View_2008/03/27/2E3C5C9004.shtml,2013.04.04.
[22]国际电子商情. 中国安防设备市场分析与瞭望.http://www.ca800.com/news/html/2006-3-16/n40469_0.htm,2013.04.04.
[23]百度知道.平安城市.http://baike.baidu.com/view/1162195.htm,2013.04.04.
[24]中国报告大厅.2009-2012年中国视频监控系统市场研究及发展前景预测报告.http://www.chinabgao.com/reports/61141.html,2013.04.04.
[25]CCTIME飞象网.智能视频监控技术与应用分析.http://www.cctime.com/html/2010-8-6/2010861710277893.htm,2013.04.04.
[26]Yilmaz A., Javed O., Shah M. Object tracking:A survey. Acm Computing Surveys (CSUR),2006,38(4):1-45.
[27]Sethi I. K., Jain R. Finding trajectories of feature points in a monocular image se-quence. IEEE Transactions on Pattern Analysis and Machine Intelligence,1987, 9(1):56-73.
[28]Salari V, Sethi I. K. Feature point correspondence in the presence of occlusion. IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):87-91.
[29]Rangarajan K., Shah M. Establishing motion correspondence. in:Proceedings of IEEE Conference Vision Graphies Image Proces, Orlando, FL, USA,1991,56-73.
[30]Intille S. S., Davis J. W., Bobick A. F. Real-time closed-world tracking. in:Pro-ceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA,1997,697-703.
[31]Veenman C. J., Reinders M. J. T., Backer E. Resolving motion correspondence for densely moving points. IEEE Transactions on Pattern Analysis and Machine Intelli-gence,2001,23(1):54-72.
[32]Shafique K., Shah M. A non-iterative greedy algorithm for multi-frame point corre-spondence. in:Proceedings of IEEE International Conference on Computer Vision, Nice, France,2003,110-115.
[33]Stalder S., Grabner H., Van Gool L. Cascaded confidence filtering for improved tracking-by-detection,.in:Proceedings of European conference on Computer Vision, Crete,Greece,2010, Springer-Verlag,369-382.
[34]Broida T. J., Chellappa R. Estimation of object motion parameters from noisy images. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986, (1):90-99.
[35]Arulampalam M. S., Maskell S., Gordon N., et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. Signal Processing, IEEE Transac-tions on,2002,50(2):174-188.
[36]Beymer D., Konolige K. Real-time tracking of multiple people using continuous detection, in:Proceedings of IEEE International Conference on Computer Vision Frame-Rate Workshop, Kerkyra, Greece,1999,56-60.
[37]Rosales R., Sclaroff S.3D trajectory recovery for tracking multiple objects and trajec-tory guided recognition of actions. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Ft. Collins, CO, USA,1999,117-123.
[38]Kitagawa G. Non-Gaussian State—Space Modeling of Nonstationary Time Series. Journal of the American statistical association,1987,82(400):1032-1041.
[39]Isard M., Blake A. Condensation—conditional density propagation for visual track-ing. International journal of computer vision,1998,29(1):5-28.
[40]Rasmussen C., Hager G. D. Joint probabilistic data association methods for tracking complex visual objects. IEEE Transactions on Pattern Analysis and Machine Intelli-gence,2001,23(6):560-576.
[41]Reid D. An algorithm for tracking multiple targets. IEEE Transactions on Automatic Control,1979,24(6):843-854.
[42]Chang Y.-L., Aggarwal J.3d structure reconstruction from an ego motion sequence using statistical estimation and detection theory, in:Proceedings of IEEE Workshop on Visual Motion, Princeton, NJ, USA,1991,268-273.
[43]Streit R. L., Luginbuhl T. E. Maximum likelihood method for probabilistic multi-hypothesis tracking. in:Proceedings of SPIE's International Symposium on Optical Engineering and Photonics in Aerospace Sensing, Orlando, FL, USA,1994,394-405.
[44]Cox I. J., Hingorani S. L. An efficient implementation of Reid's multiple hypoth-esis tracking algorithm and its evaluation for the purpose of visual tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(2):138-150.
[45]Murty K. G. Letter to the Editor-An Algorithm for Ranking all the Assignments in Order of Increasing Cost. Operations Research,1968,16(3):682-687.
[46]Huttenlocher D. P., Noh J. J., Rucklidge W. J. Tracking non-rigid objects in complex scenes.in:Proceedings of International Conference on Computer Vision., Berlin, Germany,1993,93-101.
[47]Li B., Chellappa R., Zheng Q., et al. Model-based temporal object verification using video. IEEE Transactions on Image Processing,2001,10(6):897-908.
[48]Jech T. J. Set theory, volume 79. Academic press,1978.
[49]Haritaoglu I., Harwood D., Davis L. S. W4:real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):809-830.
[50]Sato K., Aggarwal J. Temporal spatio-velocity transform and its application to track-ing and interaction. Computer Vision Image Understande,2004,96(2):100-128.
[51]Shi Y., Karl W. C. Real-time tracking using level sets, in:Proceedings of IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA,2005,34-41.
[52]Bertalmfo M., Sapiro G., Randall G. Morphing active contours. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(7):733-737.
[53]Mansouri A.-R. Region tracking via level set PDEs without motion computation. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2002,24(7):947-961.
[54]Cremers D., Schnorr C. Statistical shape knowledge in variational motion segmenta-tion. Image and Vision Computing,2003,21(1):77-86.
[55]Ronfard R. Region-based strategies for active contour models. International Journal of Computer Vision,1994,13(2):229-251.
[56]Yilmaz A., Li X., Shah M. Contour-based object tracking with occlusion handling in video acquired using mobile cameras. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(11):1531-1536.
[57]Terzopoulos D., Szeliski R. Tracking with Kalman snakes. in:Proceedings of Active vision. MIT press,1993,3-20.
[58]MacCormick J., Blake A. Probabilistic exclusion and partitioned sampling for multi-ple object tracking. International Journal of Computer Vision,2000,39(1):57-71.
[59]Chen Y., Rui Y., Huang T. S. JPDAF based HMM for real-time contour tracking. in: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA,2001, IEEE,I-543.
[60]Wang X., Hua G., Han T. X. Discriminative tracking by metric learning. in:Proceed-ings of European Conference on Computer Vision, Crete, Greece,2010,200-214.
[61]Murase H., Nayar S. K. Visual learning and recognition of 3-Dobjects from appear-ance. Int'1. J. Computer Vision,1995,14:5-24.
[62]Hager G. D., Belhumeur P. N. Efficient region tracking with parametric models of geometry and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(10):1025-1039.
[63]Black M. J., Jepson A. D. Eigentracking:Robust matching and tracking of articulated objects using a view-based representation. in:Proceedings of European Conf. on Computer Vision, Cambridge, UK,1996,329-342.
[64]Ho J., Lee K.-C., Yang M.-H., et al. Visual tracking using learned linear subspaces. in: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA,2004,1-782.
[65]Ross D., Lim J., Yang M.-H. Adaptive probabilistic visual tracking with incremen-tal subspace update. in:Proceedings of European Conference on Computer Vision, Prague, Czech Republic,2004,470-482.
[66]Lim J., Ross D., Lin R.-S., et al. Incremental learning for visual tracking. Advances in neural information processing systems,2004,17:793-800.
[67]Ross D. A., Lim J., Lin R.-S., et al. Incremental learning for robust visual tracking. International Journal of Computer Vision,2008,77(1-3):125-141.
[68]Li X., Hu W., Zhang Z., et al. Robust visual tracking based on incremental tensor subspace learning. in:Proceedings of IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil,2007,1-8.
[69]Li X., Hu W., Zhang Z., et al. Visual tracking via incremental log-euclidean rieman-nian subspace learning. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, USA,2008, IEEE,1-8.
[70]Cootes T. F., Edwards G. J., Taylor C. J. Active appearance models. IEEE Transac-tions on Pattern Analysis and Machine Intelligence,2001,23(6):681-685.
[71]Fukunaga K., Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions on Information Theory,1975, 21(1):32-40.
[72]Cheng Y. Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
[73]Comaniciu D., Ramesh V., Meer P. Real-time tracking of non-rigid objects using mean shift, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, SC, USA,2000,142-149.
[74]Comaniciu D., Ramesh V., Meer P. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[75]Haritaoglu I., Flickner M. Detection and tracking of shopping groups in stores. in: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA,2001,1-431.
[76]Ning J., Zhang L., Zhang D., et al. Robust object tracking using joint color-texture histogram. International Journal of Pattern Recognition and Artificial Intelligence, 2009,23(7):1245-1263.
[77]Nguyen Q. A., Robles-Kelly A., Shen C. Enhanced kernel-based tracking for monochromatic and thermographic video. in:Proceedings of IEEE International Conference on Video and Signal Based Surveillance, Sydney, NSW, Australia,2006, 28-28.
[78]张涛,蔡灿辉.基于多特征Mean Shift的人脸跟踪算法.电子与信息学报,2009,31(8)：1816-1820.
[79]Ojala T., Pietikainen M., Maenpaa T. Multiresolution gray-scale and rotation invari-ant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[80]Tan X., Triggs B. Enhanced local texture feature sets for face recognition under diffi-cult lighting conditions. IEEE Transactions on Image Processing,2010,19(6):1635-1650.
[81]Wang J., Chen X., Gao W. Online selecting discriminative tracking features using particle filter. in:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA,2005,1037-1042.
[82]Wang J., Yagi Y. Integrating color and shape-texture features for adaptive real-time object tracking. IEEE Transactions on Image Processing,2008,17(2):235-240.
[83]袁广林,薛模根,韩裕生等.基于自适应多特征融合的nean shift目标跟踪.计算机研究与发展,2010,(009)：1663-1671.
[84]王永忠,梁彦,赵春晖等.基于多特征自适应融合的核跟踪方法.自动化学报,2008,34(4)：393-399.
[85]颜佳,吴敏渊,陈淑珍等.跟踪窗口自适应的Mean Shift跟踪.光学精密工程,2009,17(10)：2606-2611.
[86]Liu B., Huang J., Yang L., et al. Robust tracking using local sparse appearance model and k-selection. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA,2011,1313-1320.
[87]Collins R. T. Mean-shift blob tracking through scale space, in:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, WI, USA,2003,Ⅱ-234.
[88]陈晓鹏,李成荣,罗杨宇等.自适应带宽均值移动算法及目标跟踪.机器人,2008,30(2)：147-154.
[89]Khan Z. H., Gu I., Backhouse A. G. Robust visual object tracking using multi-mode anisotropic mean shift and particle filters. IEEE Transactions on Circuits and Systems for Video Technology,2011,21(1):74-87.
[90]齐苏敏,黄贤武,伊怀峰.基于各向异性核函数的均值漂移跟踪算法.电子与信息学报,2007,29(3)：686-689.
[91]Zivkovic Z., Krose B. An EM-like algorithm for color-histogram-based object track-ing. in:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, USA,2004,1-798.
[92]Zivkovic Z., Cemgil A. T., Krose B. Approximate Bayesian methods for kernel-based object tracking. Computer Vision and Image Understanding,2009,113(6):743-749.
[93]彭宁嵩,杨杰,刘志.Mean shift跟踪算法中核函数带宽的自动选择.软件学报,2005,16(9)：1542-1500.
[94]康一梅,谢晚冬,胡江等.目标尺度自适应的Mean Shift跟踪算法.兵工学报,2011,32(2)：210-216.
[95]Zhao C., Knight A., Reid I. Target tracking using mean-shift and affine structure. in:Proceedings of International Conference on Pattern Recognition, Tampa, Florida, USA,2008,1-5.
[96]Chen A.-h., Zhu M., Wang Y.-h., et al. Mean shift tracking combining SIFT. in: Proceedings of International Conference on Signal Processing, Beijing, China,2008, 1532-1535.
[97]Ning J., Zhang L., Zhang D., et al. Scale and orientation adaptive mean shift tracking. IET Computer Vision,2012,6(1):52-61.
[98]Bradski G. R. Real time face and object tracking as a component of a perceptual user interface. in:Proceedings of IEEE Workshop on Applications of Computer Vision, Washington, DC, USA,1998,214-219.
[99]Isard M., Blake A. Contour tracking by stochastic propagation of conditional density, in:Proceedings of European Conference on Computer Vision, Cambridge, UK,1996, 343-356.
[100]Isard M., Blake A. Condensation-conditional density propagation for visual track-ing. International journal of computer vision,1998,29(1):5-28.
[101]Nummiaro K., Koller-Meier E., Van Gool L. An adaptive color-based particle filter. Image and Vision Computing,2003,21(1):99-110.
[102]Okuma K., Taleghani A., De Freitas N., et al. A boosted particle filter:Multitarget detection and tracking. in:Proceedings of European Conference on Computer Vision, Prague, Czech Republic,2004,28-39.
[103]Mei X., Ling H. Robust visual tracking using L1 minimization, in:Proceedings of IEEE International Conference on Computer Vision, Kyoto, Japan,2009,1436-1443.
[104]Mei X., Ling H. Robust visual tracking and vehicle classification via sparse repre-sentation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011, 33(11):2259-2272.
[105]Wu Y., Ling H., Yu J., et al. Blurred target tracking by blur-driven tracker. in:Pro-ceedings of IEEE International Conference on Computer Vision, Barcelona, Spain, 2011,1100-1107.
[106]Mei X., Ling H., Wu Y., et al. Minimum error bounded efficient L1 tracker with occlusion detection. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA,2011,1257-1264.
[107]Yin Z., Collins R. Spatial divide and conquer with motion cues for tracking through clutter. in:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA,2006,570-577.
[108]Mahadevan V., Vasconcelos N. Saliency-based discriminant tracking. in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA,2009,1007-1013.
[109]Avidan S. Support vector tracking. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence,2004,26(8):1064-1072.
[110]Avidan S. Ensemble tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(2):261-271.
[111]Grabner H., Grabner M., Bischof H. Real-time tracking via on-line boosting. in: Proceedings of BMVC, Edinburgh, England,2006,47-56.
[112]Grabner H., Bischof H. On-line boosting and vision. in:Proceedings of IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA,2006,260-267.
[113]Grabner H., Leistner C., Bischof H. Semi-supervised on-line boosting for robust tracking. in:Proceedings of European Conference on Computer Vision, Marseilles, France,2008,234-247.
[114]Stalder S., Grabner H., Van Gool L. Beyond semi-supervised tracking:Tracking should be as simple as detection, but not simpler than recognition. in:Proceedings of IEEE International Conference on Computer Vision Workshops, Kyoto, Japan,2009, 1409-1416.
[115]Babenko B., Yang M.-H., Belongie S. Visual tracking with online multiple instance learning, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA,2009,983-990.
[116]Zhang K., Song H. Real-time visual tracking via online weighted multiple instance learning. Pattern Recognition,46.
[117]Zeisl B., Leistner C., Saffari A., et al. On-line semi-supervised multiple-instance boosting, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA,2010,1879-1879.
[118]Yang F., Lu H., Chen Y.-W. Human tracking by multiple kernel boosting with local-ity affinity constraints. in:Proceedings of Asian Conference on Computer Vision, Queenstown,New Zealand,2011,39-50.
[119]Jia X., Wang D., Lu H. Fragment-based tracking using online multiple kernel learn-ing, in:Proceedings of IEEE International Conference on Image Processing, Orlando, Florida, U.S.A,2012,393-396.
[120]Lu H., Zhang W., Chen Y.-W. On feature combination and multiple kernel learn-ing for object tracking. in:Proceedings of Asian Conference on Computer Vision, Queenstown,New Zealand,2011,511-522.
[121]Luo W., Li X., Li W., et al. Robust visual tracking via transfer learning. in:Pro-ceedings of IEEE International Conference on Image Processing, Brussels, Belguim, 2011,485-488.
[122]Gao C., Sang N., Huang R. Online Transfer Boosting for object tracking, in:Pro-ceedings of International Conference on Pattern Recognition, Tsukuba Science City, JAPAN,2012,906-909.
[123]Dan Z., Sang N., Huang R., et al. Instance transfer boosting for object tracking. Optik-International Journal for Light and Electron Optics,2012.
[124]Wang S., Lu H., Yang F., et al. Superpixel tracking, in:Proceedings of IEEE Inter-national Conference on Computer Vision, Barcelona, Spain,2011,1323-1330.
[125]Tang M., Peng X. Robust tracking with discriminative ranking lists. IEEE Transac-tions on Image Processing,2012,21(7):3273-3281.
[126]Lepetit V., Fua P. Keypoint recognition using randomized trees. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(9):1465-1479.
[127]Ozuysal M., Calonder M., Lepetit V., et al. Fast keypoint recognition using ran-dom ferns. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010, 32(3):448-461.
[128]Ozuysal M., Fua P., Lepetit V. Fast keypoint recognition in ten lines of code. in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Min-neapolis, Minnesota, USA,2007,1-8.
[129]Bosch A., Zisserman A., Muoz X. Image classification using random forests and ferns, in:Proceedings of IEEE International Conference on Computer Vision, Riode Janeiro, Brazil,2007,1-8.
[130]Villamizar M., Moreno-Noguer F., Andrade-Cetto J., et al. Efficient rotation invariant object detection using boosted random ferns, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA,2010,1038-1045.
[131]Villamizar M., Moreno-Noguer F., Andrade-Cetto J., et al. Shared random ferns for efficient detection of multiple categories, in:Proceedings of International Conference on Pattern Recognition, Istanbul, Turkey,2010,388-391.
[132]Gonzalez R.C. W. R.数字图像处理,第二版.阮秋琦,阮宇星等译.中国,北京：电子工业出版社,March,2003.
[133]Lienhart R., Maydt J. An extended set of haar-like features for rapid object detection. in:Proceedings of International Conference on Image Processing, Rochester,New York,2002,I-900.
[134]Dalal N., Triggs B. Histograms of oriented gradients for human detection. in:Pro-ceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA,2005,886-893.
[135]Kumar R., Sawhney H., Samarasekera S., et al. Aerial video surveillance and ex-ploitation. IEEE Generation Surveil System,2001,89(10):1518-1539.
[136]Jeyakar J., Babu R. V., Ramakrishnan K. Robust object tracking with background-weighted local kernels. Computer Vision and Image Understanding,2008, 112(3):296-309.
[137]Li L., Feng Z. An efficient object tracking method based on adaptive nonparametric approach. Opto-Electronics Review,2005,13(4):325.
[138]Allen J. G., Xu R. Y, Jin J. S. Mean shift object tracking for a SIMD computer. in:Proceedings of International Conference on Information Technology and Appli-cations, Washington, DC, USA,2005,692-697.
[139]Ning J., Zhang L., Zhang D., et al. Robust mean-shift tracking with corrected background-weighted histogram. IET Computer Vision,2012,6(1):62-69.
[140]Horn B. K., Schunck B. G. Determining optical flow. Artificial intelligence,1981, 17(1):185-203.
[141]Barron J. L., Fleet D. J., Beauchemin S. Performance of optical flow techniques. International journal of computer vision,1994,12(1):43-77.
[142]Bigun J., Granlund G. H., Wiklund J. Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Transactions on Pattern Anal-ysis and Machine Intelligence,1991,13(8):775-790.
[143]Beauchemin S. S., Barron J. L. The computation of optical flow. ACM Computing Surveys (CSUR),1995,27(3):433-466.
[144]Liu B., Zaccarin A. New fast algorithms for the estimation of block motion vectors. IEEE Transactions on Circuits and Systems for Video Technology,1993,3(2):148-157.
[145]Po L.-M., Ma W.-C. A novel four-step search algorithm for fast block motion es-timation. IEEE Transactions on Circuits and Systems for Video Technology,1996, 6(3):313-317.
[146]Li R., Zeng B., Liou M. L. A new three-step search algorithm for block motion estimation. IEEE Transactions on Circuits and Systems for Video Technology,1994, 4(4):438-442.
[147]Wang J., Yagi Y. Adaptive mean-shift tracking with auxiliary particles. IEEE Trans-actions on Systems, Man, and Cybernetics, Part B:Cybernetics,2009,39(6):1578-1589.
[148]Viola P., Jones M. J., Snow D. Detecting pedestrians using patterns of motion and appearance. International Journal of Computer Vision,2005,63(2):153-161.
[149]Perazzi F., Krahenbuhl P., Pritch Y., et al. Saliency filters:Contrast based filtering for salient region detection, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA,2012,733-740.
[150]Santner J., Leistner C., Saffari A., et al. Prost:Parallel robust online simple tracking, in:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA,2010,723-730.
[151]Yang F., Lu H., Chen Y.-W. Bag of features tracking. in:Proceedings of International Conference on Pattern Recognition, Hong Kong, China,2010,153-156.
[152]Zheng F., Webb G. I. A comparative study of semi-naive Bayes methods in classifica-tion learning. in:Proceedings of 4Th Australasian data mining conference, Sydney, Australia,2005,141-156.
[153]Trajkovic M., Hedley M. Fast corner detection. Image and Vision Computing,1998, 16(2):75-87.
[154]Schmid C., Mohr R., Bauckhage C. Evaluation of interest point detectors. Interna-tional Journal of computer vision,2000,37(2):151-172.
[155]Ren X., Malik J. Learning a classification model for segmentation, in:Proceedings of IEEE International Conference on Computer Vision, Nice, France,2003,10-17.