基于可移动拍摄大场景下的人体运动跟踪关键技术的研究与应用
|
摘要
计算机视觉是已成为计算机领域中最热门的课题之一,然而,目前还没有一个标准的模式来解决所谓的“计算机视觉问题”,计算机视觉中的问题是根据实际应用而产生的,通常情况下,一类应用上已经验证的算法却很难推广到其他应用上。
本文主要研究在可移动拍摄大场景下的人体运动跟踪的关键技术,主要包括:针对大场景下,使用单摄像机架在三脚架上进行不变焦旋转拍摄,目标跟踪时需要补偿摄像机的自身旋转运动,即计算相邻两帧之间的单应矩阵,由于单应矩阵的计算是一个随机过程,因此,当跟踪过程中引入补偿摄像机自身运动的单应矩阵时,其单应矩阵的计算稳定性直接影响着跟踪的结果,如何对二者之间的关系进行评测;同时,如何将每帧图像快速准确配准到真实的场景模型中,即计算每帧图像到真实场景模型之间的单应矩阵,其精确度如何评测;大场景下的人体运动跟踪是一个非常复杂的问题,因为图像分辨率低、背景复杂、目标移动迅速以及存在遮挡,因此,需要更多的先验知识,包括更加精确的目标描述和更加鲁棒的跟踪器。
针对以上实际中存在的问题,本文以跟踪在大冰面上快速滑行的短道速滑运动员为应用背景,主要研究内容和创新点包括以下几个方面:
(1)提出了在大场景使用单摄像机进行旋转拍摄下的人体运动跟踪的应用算法框架,确保了在复杂的体育应用中,也可具有较好的鲁棒性和稳定性。
(2)提出了一种新的有效算法以减小对于长图像序列自动配准多造成的累积误差,在该算法中,任何一帧图像只需经过3次映射便可转换到真实冰场坐标系下,即每帧图像到其对应的参考帧,参考帧到全景冰场,全景冰场到真实冰场模型,该算法避免了传统算法的多帧变换连续累乘,从而有效的降低了累积误差,而且这对于提高实际应用的稳定性是十分必要的。
(3)提出了描述目标更加精确的层次模型,这有助于在跟踪过程中,使得跟踪器知道什么时候以及如何来更新层次模型,这确保了模型更新的精确性:
(4)采用多线索跟踪技术,即针对较小的头部区域使用模板匹配技术,对身体区域使用直方图匹配技术,这使得当运动员发生在弯道遮挡时或是滑到冰场上端挡板有颜色干扰时,跟踪表现的更加稳定;
(5)提出了一种新的颜色核直方图的构建方法,在核函数中引入一个遮罩函数,有效的滤除了作为背景信息的干扰像素,大大提高了直方图匹配时的精确度;
(6)利用UKF(Unscented Kalman Filter)本身的特性,可以精确的近似统计变量的均值和协方差,同时,采用Sigma点确定性采样,相比PF,采样点少,实际和理论上计算的效率都更高。并巧妙的将描述目标的层次模型和多线索跟踪技术融合到了UKF的跟踪框架中;
(7)提出了一套新的对于在大场景进行旋转拍摄下的人体运动跟踪的评测方案,包括两个方面:1.与传统的跟踪方法相比,在跟踪的预测阶段多引入了一个去除摄像机自运动的计算,即相邻图像之间的单应矩阵,通过在手工标定的目标位置上加入不同噪声对此过程进行仿真模拟,详细的分析了其精确度与跟踪结果之间的关系。2.采用了一种间接方法,即标记点的实际冰场坐标系下的配准误差来作为实际跟踪结果的估计,来评测每一帧与真实冰场模型之间的单应矩阵的精确度,并从理论上分析了影响其精确度的因素所在。
本文提出的新的在大场景使用单摄像机进行旋转拍摄下的人体运动跟踪的应用算法框架还可推广到其他的相似应用中,如田径、自行车、赛车以及一些球类等场地运动项目中,尤其适合应用于体育运动项目的实时运动信息获取,体育电视转播中实时数据统计和战术模拟演示。同时,本文涉及到的一些关键技术还可应用在机器人视觉导航与定位,军事,虚拟现实,安全监控等方面。
Computer vision becomes one of the most popular topics, however, there is nostandard formulation of how the so-called”computer vision problem”should be solved,these problems mainly come from the practical applications, in general, the methods areproofed to be valid for a specific task, but it is hard to make them work well over a widerange of other applications.
This dissertation focuses on the key technology of human motion tracking in a largescene by using a panning camera, which include the following aspects: For a large scene,a single panning camera on a tripod has to be chosen, at the same time, zooming is aban-doned. The camera own panning motion needs to be compensated in tracking process byusing the computation of homography of two consecutive frames, it is a random process,therefore, when this computation has been introduced into the tracking process, the com-putation stability of this homography affects the tracking results directly, how to evaluatethe relation of them. At the same time, how to calculate the other homography mappingeach frame into the real scene model fast and accurately, and how to evaluate the preci-sion of this homography. Human motion tracking becomes a challenging task because oflower image resolution, complex background, fast object motion and occlusions, there-fore, more prior knowledge, more accurate object representation and more robust trackerare badly needed.
In view of the above problems in the practical application, this dissertation makesuse of the skater tracking in a large rink as an application background, the main researchcontents and innovations include the following aspects:
(1) A novel application algorithm framework of human motion tracking in a largescene by using a panning camera is proposed, especially for complex sports applications,it maybe have better robustness and stability.
(2) A novel efficient algorithm to reduce the accumulative registration error for along image sequence is proposed, in which any frame are transformed to the real rinkmodel only needs three steps, namely, mapping each frame to its corresponding refer-ence frame, then mapping reference frame to the panorama of the rink, last, mappingthe panorama to the real rink model. Compared with the traditional methods, the pro- posed algorithm avoids to a concatenation multiplication of the homography of consecu-tive frames, therefore, it can reduce the accumulative registration error efficiently and isvery important to improve the stability of the practical application.
(3) The hierarchical model, which represents tracked object more accurately, is pro-posed. It can help the tracker to know when and how to update the hierarchical model.That ensures the accuracy of the model update in tracking process.
(4) Using multiple cues in tracking process, namely, the template matching methodfor helmet and the color histogram matching for body, that can make the tracker morerobust when a skater moving through the advertisement board or occlusions appear on thecurve.
(5) A new method of constructing a color kernel histogram is proposed, it introducesa mask function into the kernel, which can filter the rink pixels considered as a kind ofbackground interference and improve the accuracy of histogram matching efficiently.
(6) To make use of UKF (Unscented Kalman Filter) own properties, UKF can cap-ture the mean and covariance of the statistical variables accurately, compared with theparticle filter, it is specified using a minimal set of deterministically chosen sample points,therefore, its computational efficiency is more higher. At the same time, object represen-tation and multiple cues are integrated cleverly into the tracking framework of UKF.
(7) This dissertation proposes a novel evaluation of human motion tracking in alarge scene by using a panning camera, which includes two aspects: 1. Compared withthe traditional tracking method, the calculation of the homography of the consecutiveframes, which is used to remove the camera motion, is introduced into the prediction stepof the tracking process. The effect of the introduction of this homography is simulatedby adding many different groups of the noise to the object position marked manually,through which the analysis of the relation between the accuracy of this homography andthe tracking performance is discussed in detail. 2. The accuracy of the homography thattransforms each frame to the real rink is evaluated by an indirect approach, that is to say,the accuracy of this homography can be estimated by the registration error of the markedblock in the coordinate of the real rink. In addition, the factors, which can affect thisaccuracy, have been analyzed in theory.
A novel application algorithm framework of human motion tracking in a large sceneby using a panning camera is proposed, it can be extended to other similar applications easily, such as track and field events, cycling and ball games, especially suitable for sportsinformation access in real-time, data statistics and presentation of tactical simulation insports television. At the same time, some of the key technology detailed in this disserta-tion can also be used in robot vision navigation and localization, military, virtual reality,safety monitoring and so on.
本文主要研究在可移动拍摄大场景下的人体运动跟踪的关键技术,主要包括:针对大场景下,使用单摄像机架在三脚架上进行不变焦旋转拍摄,目标跟踪时需要补偿摄像机的自身旋转运动,即计算相邻两帧之间的单应矩阵,由于单应矩阵的计算是一个随机过程,因此,当跟踪过程中引入补偿摄像机自身运动的单应矩阵时,其单应矩阵的计算稳定性直接影响着跟踪的结果,如何对二者之间的关系进行评测;同时,如何将每帧图像快速准确配准到真实的场景模型中,即计算每帧图像到真实场景模型之间的单应矩阵,其精确度如何评测;大场景下的人体运动跟踪是一个非常复杂的问题,因为图像分辨率低、背景复杂、目标移动迅速以及存在遮挡,因此,需要更多的先验知识,包括更加精确的目标描述和更加鲁棒的跟踪器。
针对以上实际中存在的问题,本文以跟踪在大冰面上快速滑行的短道速滑运动员为应用背景,主要研究内容和创新点包括以下几个方面:
(1)提出了在大场景使用单摄像机进行旋转拍摄下的人体运动跟踪的应用算法框架,确保了在复杂的体育应用中,也可具有较好的鲁棒性和稳定性。
(2)提出了一种新的有效算法以减小对于长图像序列自动配准多造成的累积误差,在该算法中,任何一帧图像只需经过3次映射便可转换到真实冰场坐标系下,即每帧图像到其对应的参考帧,参考帧到全景冰场,全景冰场到真实冰场模型,该算法避免了传统算法的多帧变换连续累乘,从而有效的降低了累积误差,而且这对于提高实际应用的稳定性是十分必要的。
(3)提出了描述目标更加精确的层次模型,这有助于在跟踪过程中,使得跟踪器知道什么时候以及如何来更新层次模型,这确保了模型更新的精确性:
(4)采用多线索跟踪技术,即针对较小的头部区域使用模板匹配技术,对身体区域使用直方图匹配技术,这使得当运动员发生在弯道遮挡时或是滑到冰场上端挡板有颜色干扰时,跟踪表现的更加稳定;
(5)提出了一种新的颜色核直方图的构建方法,在核函数中引入一个遮罩函数,有效的滤除了作为背景信息的干扰像素,大大提高了直方图匹配时的精确度;
(6)利用UKF(Unscented Kalman Filter)本身的特性,可以精确的近似统计变量的均值和协方差,同时,采用Sigma点确定性采样,相比PF,采样点少,实际和理论上计算的效率都更高。并巧妙的将描述目标的层次模型和多线索跟踪技术融合到了UKF的跟踪框架中;
(7)提出了一套新的对于在大场景进行旋转拍摄下的人体运动跟踪的评测方案,包括两个方面:1.与传统的跟踪方法相比,在跟踪的预测阶段多引入了一个去除摄像机自运动的计算,即相邻图像之间的单应矩阵,通过在手工标定的目标位置上加入不同噪声对此过程进行仿真模拟,详细的分析了其精确度与跟踪结果之间的关系。2.采用了一种间接方法,即标记点的实际冰场坐标系下的配准误差来作为实际跟踪结果的估计,来评测每一帧与真实冰场模型之间的单应矩阵的精确度,并从理论上分析了影响其精确度的因素所在。
本文提出的新的在大场景使用单摄像机进行旋转拍摄下的人体运动跟踪的应用算法框架还可推广到其他的相似应用中,如田径、自行车、赛车以及一些球类等场地运动项目中,尤其适合应用于体育运动项目的实时运动信息获取,体育电视转播中实时数据统计和战术模拟演示。同时,本文涉及到的一些关键技术还可应用在机器人视觉导航与定位,军事,虚拟现实,安全监控等方面。
Computer vision becomes one of the most popular topics, however, there is nostandard formulation of how the so-called”computer vision problem”should be solved,these problems mainly come from the practical applications, in general, the methods areproofed to be valid for a specific task, but it is hard to make them work well over a widerange of other applications.
This dissertation focuses on the key technology of human motion tracking in a largescene by using a panning camera, which include the following aspects: For a large scene,a single panning camera on a tripod has to be chosen, at the same time, zooming is aban-doned. The camera own panning motion needs to be compensated in tracking process byusing the computation of homography of two consecutive frames, it is a random process,therefore, when this computation has been introduced into the tracking process, the com-putation stability of this homography affects the tracking results directly, how to evaluatethe relation of them. At the same time, how to calculate the other homography mappingeach frame into the real scene model fast and accurately, and how to evaluate the preci-sion of this homography. Human motion tracking becomes a challenging task because oflower image resolution, complex background, fast object motion and occlusions, there-fore, more prior knowledge, more accurate object representation and more robust trackerare badly needed.
In view of the above problems in the practical application, this dissertation makesuse of the skater tracking in a large rink as an application background, the main researchcontents and innovations include the following aspects:
(1) A novel application algorithm framework of human motion tracking in a largescene by using a panning camera is proposed, especially for complex sports applications,it maybe have better robustness and stability.
(2) A novel efficient algorithm to reduce the accumulative registration error for along image sequence is proposed, in which any frame are transformed to the real rinkmodel only needs three steps, namely, mapping each frame to its corresponding refer-ence frame, then mapping reference frame to the panorama of the rink, last, mappingthe panorama to the real rink model. Compared with the traditional methods, the pro- posed algorithm avoids to a concatenation multiplication of the homography of consecu-tive frames, therefore, it can reduce the accumulative registration error efficiently and isvery important to improve the stability of the practical application.
(3) The hierarchical model, which represents tracked object more accurately, is pro-posed. It can help the tracker to know when and how to update the hierarchical model.That ensures the accuracy of the model update in tracking process.
(4) Using multiple cues in tracking process, namely, the template matching methodfor helmet and the color histogram matching for body, that can make the tracker morerobust when a skater moving through the advertisement board or occlusions appear on thecurve.
(5) A new method of constructing a color kernel histogram is proposed, it introducesa mask function into the kernel, which can filter the rink pixels considered as a kind ofbackground interference and improve the accuracy of histogram matching efficiently.
(6) To make use of UKF (Unscented Kalman Filter) own properties, UKF can cap-ture the mean and covariance of the statistical variables accurately, compared with theparticle filter, it is specified using a minimal set of deterministically chosen sample points,therefore, its computational efficiency is more higher. At the same time, object represen-tation and multiple cues are integrated cleverly into the tracking framework of UKF.
(7) This dissertation proposes a novel evaluation of human motion tracking in alarge scene by using a panning camera, which includes two aspects: 1. Compared withthe traditional tracking method, the calculation of the homography of the consecutiveframes, which is used to remove the camera motion, is introduced into the prediction stepof the tracking process. The effect of the introduction of this homography is simulatedby adding many different groups of the noise to the object position marked manually,through which the analysis of the relation between the accuracy of this homography andthe tracking performance is discussed in detail. 2. The accuracy of the homography thattransforms each frame to the real rink is evaluated by an indirect approach, that is to say,the accuracy of this homography can be estimated by the registration error of the markedblock in the coordinate of the real rink. In addition, the factors, which can affect thisaccuracy, have been analyzed in theory.
A novel application algorithm framework of human motion tracking in a large sceneby using a panning camera is proposed, it can be extended to other similar applications easily, such as track and field events, cycling and ball games, especially suitable for sportsinformation access in real-time, data statistics and presentation of tactical simulation insports television. At the same time, some of the key technology detailed in this disserta-tion can also be used in robot vision navigation and localization, military, virtual reality,safety monitoring and so on.
引文
1 B. Zitova′, J. Flusser. Image Registration Methods: A Survey. Image and VisionComputing. 2003, 21(11):977–1000
2 J. Matas, O. Chum, M.Urban, et al. Robust Wide Baseline Stereo from MaximallyStable Extremal Regions. P. L. Rosin, A. D. Marshall, (Editors) British Machine Vi-sion Conference. Cardiff, UK, 2002:384–396. http://www.bmva.ac.uk/bmvc/2002/papers/113/full 113.pdf
3 J. Canny. A Computational Approach to Edge Detection. IEEE Transactions onPattern Analysis and Machine Intelligence. 1986, 8(6):679–698
4 H. Li, B. S. Manjunath, S. K. Mitra. A Contour-based Approach to MultisensorImage Registration. IEEE Transactions on Image Processing. 1995, 4(3):320–334
5 S. Moss, E. R. Hancock. Multiple Line-template Matching with Em Algorithm.Pattern Recognition Letters. 1997, 18(11–13):1283–1292
6 S. M. Smith, J. M. Brady. SUSAN―A New Approach to Low Level Image Pro-cessing. International Journal of Computer Vision. 1997, 23(1):45–78
7 C. Harris, M. Stephens. A Combined Corner and Edge Detector. Proceedings ofthe Fourth Alvey Vision Conference. Manchester, UK, 1988:147–151
8 B. Georgescu, P. Meer. Point Matching under Large Image Deformations and Il-lumination Changes. IEEE Transactions on Pattern Analysis and Machine Intelli-gence. 2004, 26(6):674–688
9 A. Yilmaz, O. Javed, M. Shah. Object Tracking: A Survey. ACM ComputingSurveys. 2006, 38(4):1–45
10侯志强,韩崇昭.视觉跟踪技术综述.自动化学报. 2006, 32(4):603–617
11 Y. Luo, T.-D. Wu, J.-N. Hwang. Object-based Analysis and Interpretation of Hu-man Motion in Sports Video Sequences by Dynamic Bayesian Networks. ComputerVision and Image Understanding. 2003, 92(2-3):196–216
12 C. J. Veenman, M. J. Reinders, E. Backer. Resolving Motion Correspondence forDensely Moving Points. IEEE Transactions on Pattern Analysis and Machine In-telligence. 2001, 23(1):54–72
13 D. Comaniciu, V. Ramesh, P. Meer. Kernel-Based Object Tracking. IEEE Transac-tions on Pattern Analysis and Machine Intelligence. 2003, 25(5):564–577
14 A. Yilmaz, X. li, M. Shah. Contour-Based Object Tracking with Occlusion Han-dling in Video Acquired Using Mobile Cameras. IEEE Transactions on PatternAnalysis and Machine Intelligence. 2004, 26(11):1531–1536
15 I. Haritaoglu, D. Harwood, L. S. Davis. W4: Real-time Surveillance of People andTheir Activities. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000, 22(8):809–830
16 H. Ning, T. Tan, L. Wang, et al. Kinematics-based Tracking of Human Walking inMonocular Video Sequences. Image and Vision Computing. 2004, 22(5):429–441
17 T. B. Moeslund, A. Hilton, V. Kru¨ger. A Survey of Advances in Vision-basedHuman Motion Capture and Analysis. Computer Vision and Image Understanding.2006, 104(2-3):90–126
18 R. Poppe. Vision-based Human Motion Analysis: An Overview. Computer Visionand Image Understanding. 2007, 108(1-2):4–18
19 J. K. Aggarwal, Q. Cai. Human Motion Analysis: A Review. Computer Vision andImage Understanding. 1999, 73(3):428–440
20 P. Fieguth, D. Terzopoulos. Color-Based Tracking of Heads and Other MobileObjects at Video Frame Rates. IEEE Computer Society Conference on ComputerVision and Pattern Recognition. San Juan, Puerto Rico, 1997:21–27
21 M. J. Black, A. D. Jepson. EigenTracking: Robust Matching and Tracking of Artic-ulated Objects Using a View-based Representation. International Journal of Com-puter Vision. 1998, 26(1):63–84
22 G. Paschos. Perceptually Uniform Color Spaces for Color Texture Analysis: AnEmpirical Evaluation. IEEE Transactions on Image Processing. 2001, 10(6):932–937
23 H. D. Cheng, X. H. Jiang, Y. Sun, et al. Color Image Segmentation: Advances andProspects . Pattern Recognition. 2001, 34(12):2259–2281
24 G. R. Bradski, S. Clara. Computer Vision Face Tracking for Use in a PerceptualUser Interface. Intel Technology Journal. 1998, 2(2):1–15. http://download.intel.com/technology/itj/q21998/pdf/camshift.pdf
25 P. Pe′rez, C. Hue, J. Vermaak, et al. Color-Based Probabilistic Tracking. EuropeanConference on Computer Vision. Copenhagen, Denmark, 2002, 2350:661–675
26 K. Nummiaro, E. Koller-Meier, L. V. Gool. An Adaptive Color-based Particle Filter.Image and Vision Computing. 2003, 21(1):99–110
27 J. Czyz, B. Ristic, B. Macq. A Particle Filter for Joint Detection and Tracking ofColor Objects. Image and Vision Computing. 2007, 25(8):1271–1281
28 K. Bowyer, C. Kranenburg, S. Dougherty. Edge Detector Evaluation Using Empir-ical Roc Curves. Computer Vision and Image Understanding. 2001, 84(1):77–103
29 B. K. Horn, B. G. Rhunck. Determining Optical Flow. Artificial Intelligence. 1981,17(1-3):185–203
30 B. D. Lucas, T. Kanade. An Iterative Image Registration Technique with an Appli-cation to Stereo Vision. International Joint Conference on Artificial Intelligence.Vancouver, British Columbia, Canada, 1981:674–679
31 J. L. Barron, D. J. Fleet, S. S. Beauchemin. Performance of Optical Flow Tech-niques. International Journal of Computer Vision. 1994, 12(1):43–77
32 K. Mikolajczyk, C. Schmid. A Performance Evaluation of Local Descriptors. IEEETransactions on Pattern Analysis and Machine Intelligence. 2005, 27(10):1615–1630
33 H. Moravec. Obstacle Avoidance and Navigation in the Real World by a SeeingRobot Rover. Tech. Rep. CMU-RI-TR-80-03, Robotics Institute, Carnegie MellonUniversity, 1980. http://www.ri.cmu.edu/pubs/pub 22.html
34 J. Shi, C. Tomasi. Good Features to Track. IEEE Computer Society Conference onComputer Vision and Pattern Recognition. Seattle, WA, USA, 1994:593–600
35 C. Tomasi, T. Kanade. Detection and Tracking of Point Features. Tech. Rep.CMU-CS-91-132, Carnegie Mellon University, Pittsburgh, PA 15213, 1991. http://reports-archive.adm.cs.cmu.edu/anon/1991/CMU-CS-91-132.ps
36 D. G. Lowe. Distinctive Image Features from Scale-invariant Keypoints. Interna-tional Journal of Computer Vision. 2004, 60(2):91–110
37 H. Zhou, Y. Yuan, C. Shi. Object Tracking Using SIFT Features and Mean Shift.Computer Vision and Image Understanding. 2009, 113(3):345–352
38 R. Jain, H. Nagel. On the Analysis of Accumulative Difference Pictures from Im-age Sequences of Real World Scenes. IEEE Transactions on Pattern Analysis andMachine Intelligence. 1979, 1(2):206–214
39 C. R. Wren, A. Azarbayejani, T. Darrell, et al. Pfinder: Real-time Tracking of theHuman Body. IEEE Transactions on Pattern Analysis and Machine Intelligence.1997, 19(7):780–785
40 A. M. Elgammal, D. Harwood, L. S. Davis. Non-parametric Model for BackgroundSubtraction. European Conference on Computer Vision. Dublin, Ireland, 2000,Lecture Notes in Computer Science:751–767
41 L. Taycher, J. W. F. III, T. Darrell. Combining Object and Feature Dynamics inProbabilistic Tracking. IEEE Computer Society Conference on Computer Visionand Pattern Recognition. San Diego, CA, USA, 2005, 2:106–113
42 D. Comaniciu, P. Meer. Mean Shift: A Robust Approach Toward Feature SpaceAnalysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002,24(5):603–619
43 J. Shi, J. Malik. Normalized Cuts and Image Segmentation. IEEE Transactions onPattern Analysis and Machine Intelligence. 2000, 22(8):888–905
44 M. Kass, A. Witkin, D. Terzopoulos. Snakes: Active Contour Models. InternationalJournal of Computer Vision. 1988, 1(4):321–331
45 D. Cremers. Dynamical Statistical Shape Priors for Level Set-based Tracking. IEEETransactions on Pattern Analysis and Machine Intelligence. 2006, 28(8):1262–1273
46 T. Zhang, D. Freedman. Improving Performance of Distribution Tracking ThroughBackground Mismatch. IEEE Transactions on Pattern Analysis and Machine Intel-ligence. 2005, 27(2):282–287
47 P. Viola, M. J. Jones, D. Snow. Detecting Pedestrians Using Patterns of Motion andAppearance. IEEE International Conference on Computer Vision. Nice, France,2003, 2:734–741
48 K. Okuma, A. Taleghani, N. D. Freitas, et al. A Boosted Particle Filter: MultitargetDetection and Tracking. European Conference on Computer Vision. Prague, CzechRepublic, 2004, 3021:28–39
49 S. Avidan. Ensemble Tracking. IEEE Computer Society Conference on ComputerVision and Pattern Recognition. San Diego, CA, USA, 2005, 2:494–501
50 S. Avidan. Support Vector Tracking. IEEE Transactions on Pattern Analysis andMachine Intelligence. 2004, 26(8):1064–1072
51 C. Papageorgiou, M. Oren, T. Poggio. A General Framework for Object Detection.IEEE International Conference on Computer Vision. Bombay, India, 1998:555–562
52 H. W. Kuhn. The Hungarian Method for the Assignment Problem. Naval ResearchLogistics Quarterly. 1955, 2(1-2):83–97
53 I. K. Sethi, R. Jain. Finding Trajectories of Feature Points in a Monocular ImageSequence. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1987,9(1):56–73
54 K. Shafique, M. Shah. A Noniterative Greedy Algorithm for Multiframe PointCorrespondence. IEEE Transactions on Pattern Analysis and Machine Intelligence.2005, 27(1):51–65
55 S. S. Intille, J. W. Davis, A. F. Bobick. Real-Time Closed-world Tracking. IEEEComputer Society Conference on Computer Vision and Pattern Recognition. SanJuan, Puerto Rico, 1997:697–703
56 Y. Bar-Shalom, T. E. Fortmann. Tracking and Data Association. Academic Press,1988
57 I. J. Cox. A Review of Statistical Data Association Techniques for Motion Corre-spondence. International Journal of Computer Vision. 1993, 10(1):53–66
58 C. Rasmussen, G. D. Hager. Probabilistic Data Association Methods for Track-ing Complex Visual Objects. IEEE Transactions on Pattern Analysis and MachineIntelligence. 2001, 23(6):560–576
59 D. B. Reid. An Algorithm for Tracking Multiple Targets. IEEE Transactions onAutomatic Control. 1979, 24(6):843–854
60 C. Hue, J.-P. L. Cadre, P. Pe′rez. Sequential Monte Carlo Methods for MultipleTarget Tracking and Data Fusion. IEEE Transactions on Signal Processing. 2002,50(2):309–325
61 H. Schweitzer, J. W. Bell, F. Wu. Very Fast Template Matching. European Confer-ence on Computer Vision. Copenhagen, Denmark, 2002, 2353:358–372
62 I. Matthews, T. Ishikawa, S. Baker. The Template Update Problem. IEEE Transac-tions on Pattern Analysis and Machine Intelligence. 2004, 26(6):810–815
63 A. D. Jepson, D. J. Fleet, T. F. El-Maraghi. Robust Online Appearance Models forVisual Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence.2003, 25(10):1296–1311
64 M. Isard, J. MacCormick. BraMBLe: A Bayesian Multiple-blob Tracker. IEEE In-ternational Conference on Computer Vision. Vancouver, British Columbia, Canada,2001, 2:34–41
65 H. Tao, H. S. Sawhney, R. Kumar. Object Tracking with Bayesian Estimation ofDynamic Layer Representations. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence. 2002, 24(1):75–89
66 D. P. Huttenlocher, J. J. Noh, W. J. Rucklidge. Tracking Non-rigid Objects in Com-plex Scenes. IEEE International Conference on Computer Vision. Berlin, Germany,1993:93–101
67 F. Hausdorff. Set Theory. 3rd edn. Chelsea Publishing Company, 1978. ISBN:0828401195
68 M. Isard, A. Blake. CONDENSATION―Conditional Density Propagation for Vi-sual Tracking. International Journal of Computer Vision. 1998, 29(1):5–28
69 J. MacCormick, A. Blake. A Probabilistic Exclusion Principle for Tracking Multi-ple Objects. International Journal of Computer Vision. 2000, 39(1):57–71
70 M. Bertalmio, G. Sapiro, G. Randall. Morphing Active Contours. IEEE Transac-tions on Pattern Analysis and Machine Intelligence. 2000, 22(7):733–737
71 A.-R. Mansouri. Region Tracking via Level Set PDEs without Motion Compu-tation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002,24(7):947–961
72 S. S. Intille, A. F. Bobick. Recognizing Planned, Multiperson Action. ComputerVision and Image Understanding. 2001, 81(3):414–445
73 C. J. Needham. Tracking and Modelling of Team Game Interactions. Ph.D. thesis,The University of Leeds. 2003
74 Y. Gong, M. Han, W. Hua, et al. Maximum Entropy Model-based Baseball High-light Detection and Classification. Computer Vision and Image Understanding.2004, 96(2):181–199
75 H. Denman, N. Rea, A. Kokaram. Content-based Analysis for Video from SnookerBroadcasts. Computer Vision and Image Understanding. 2003, 92(2-3):176–195
76 S. S. Intille, A. F. Bobick. Closed-World Tracking. IEEE International Con-ference on Computer Vision. Massachusetts Institute of Technology, Cambridge,1995:672–678
77 J. Assfalg, M. Bertini, C. Colombo, et al. Semantic Annotation of Soccer Videos:Automatic Highlights Identification. Computer Vision and Image Understanding.2003, 92(2-3):285–305
78 F. Li, R. J. Woodham. Analysis of Player Actions in Selected Hockey Game Situa-tions. Canadian Conference on Computer and Robot Vision. Victoria, BC, Canada,2005:152–159
79 M. Persˇe, M. Kristan, J. Persˇ. A Template-based Multi-player Action Recognitionof the Basketball Game. ECCV Workshop on Computer Vision Based Analysis inSport Environments. Graz, Austria, 2006:71–82
80 R. Leonardi, P. Migliorati, M. Prandini. Semantic Indexing of Sports Program Se-quences by Audio-visual Analysis. International Conference on Image Processing.Barcelona, Spain, 2003, 1:9–12
81 Hawk-Eye Innovations. http://www.hawkeyeinnovations.co.uk/
82 G. S. Pingali, Y. Jean, I. Carlborn. Real Time Tracking for Enhanced Tennis Broad-casts. IEEE Computer Society Conference on Computer Vision and Pattern Recog-nition. Santa Barbara, CA, USA, 1998:260–265
83 F. Yan, A. Kostin, W. Christmas, et al. A Novel Data Association Algorithm forObject Tracking in Clutter with Application to Tennis Video Analysis. IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition. New York,2006, 1:634–641
84 F. Yan, W. Christmas, J. Kittler. Layered Data Association Using Graph-theoretic Formulation with Application to Tennis Ball Tracking in Monocular Se-quences. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008,30(10):1814–1830
85 SIMI. Http://www.simi.com
86 Dartfish. Http://www.dartfish.com
87吴思,林守勋,张勇东.基于动态背景构造的视频运动对象自动分割.计算机学报. 2005,28(8):1386–1392
88王兆其,张勇东,夏时洪.体育训练三维人体运动模拟与视频分析系统.计算机研究与发展. 2005,42(2):344–352
89 TRUAKUS. Http://www.trakus.com
90 A. A. Efros, A. C. Berg, G. Mori, et al. Recognizing Action at a Distance. IEEEInternational Conference on Computer Vision. Nice, France,, 2003, 2:726–733
91 A. Ekin, A. M. Tekalp. Automatic Soccer Video Analysis and Summarization.IEEE Transactions on Image Processing. 2001, 12(7):796–807
92 P. J. Figueroa, N. J. Leite, R. M. Barros. Tracking Soccer Players Aiming TheirKinematical Motion Analysis. Computer Vision and Image Understanding. 2006,101(2):122–135
93 S. Iwase, H. Saito. Tracking Soccer Players Based on Homography Among Mul-tiple Views. T. Ebrahimi, T. Sikora, (Editors) Visual Communications and ImageProcessing. Lugano, Switzerland, 2003, 5150:283–292
94 M. Xu, J. Orwell, L. Lowey, et al. Architecture and Algorithms for Tracking Foot-ball Players with Multiple Cameras. IEE Proceedings Vision, Image and SignalProcessing. 2005, 152:232–241
95 T. Misu, M. Naemura, W. Zheng, et al. Robust Tracking of Soccer Players Basedon Data Fusion. International Conference on Pattern Recognition. Quebec, Canada,2002, 1:556–561
96 N. Vandenbroucke, L. Macaire, J.-G. Postaire. Color Image Segmentation by PixelClassification in an Adapted Hybrid Color Space. Applications to Soccer ImageAnalysis. Computer Vision and Image Understanding. 2003, 90(2):190–216
97 C. J. Needham, R. D. Boyle. Tracking Multiple Sports Players Through Occlusion,Congestion and Scale. British Machine Vision Conference. 2001, 1:93–102
98 B. M. Junior, R. de Oliveira Anido. Distributed Real-time Soccer Tracking. Pro-ceedings of the ACM Second International Workshop on Video Surveillance &Sensor Networks. New York, USA, 2004:97–103
99 V. Lumikero. Football Tracking in Wide-screen Video Sequences. Master’s thesis,Royal Institute of Technology. 2004. http://www.nada.kth.se/utbildning/grukth/exjobb/rapportlistor/2004/rapporter04/lumikero ville 04010.pdf
100 J. Persˇ, G. Vucˇkovicˇ, S. Kovacˇicˇ, et al. A Low-cost Real-time Tracker of LiveSport Events. The 2nd international symposium on image and signal processingand analysis. Pula, Croatia, 2001:362–365
101 J. Persˇ, M. Bon, S. Kovacˇicˇ, et al. Observation and Analysis of Large-scale HumanMotion. Human Movement Science. 2002, 21(2):295–311
102 M. Jug, J. Pers?, B. Dez?man, et al. Trajectory Based Assessment of CoordinatedHuman Activity. International Conference on Computer Vision Systems. Graz,Austria, 2003, 2626:534–543
103 S. S. Intille, A. F. Bobick. Tracking Using a Local Closed-world Assumption:Tracking in the Football Domain. MIT Media Lab Perceptual Computing GroupTechnical Report 296, 1994
104 K. Okuma. Automatic Acquisition of Motion Trajectories: Tracking Hockey Play-ers. Master’s thesis, The University of British Columbia. 2003
105 K. Okuma, J. J. Little, D. G. Lowe. Automatic Rectification of Long Image Se-quences. Asian Conference on Computer Vision. Jeju Island, Korea, 2004
106 Y. Cai. Robust Visual Tracking for Multiple Targets. Master’s thesis, The Universityof British Columbia. 2005
107 F. Li. Description, Analysis and Prediction of Player Actions in Selected HockeyGame Situations. Master’s thesis, The University of British Columbia. 2004
108 ISU: International Skating Union. Http://www.isu.org/
109 Y. Caspi, M. Irani. Aligning Non-overlapping Sequences. International Journal ofComputer Vision. 2002, 48(1):39–51
110 Y. Caspi, D. Simakov, M. Irani. Feature-Based Sequence-to-sequence Matching.International Journal of Computer Vision. 2006, 68(1):53–64
111 E. Hayman, D. W. Murray. The Effects of Translational Misalignment When Self-calibrating Rotating and Zooming Cameras. IEEE Transactions on Pattern Analysisand Machine Intelligence. 2003, 25(8):1015–1020
112 D. Farin, S. Krabbe, P. H. de With, et al. Robust Camera Calibration for SportVideos Using Court Models. SPIE Storage and Retrieval Methods and Applica-tions for Multimedia. San Jose, CA, USA, 2004, 5307:80–91. http://vca.ele.tue.nl/publications/data/Farin2004b.pdf
113 J.-B. Hayet, J. Piater, J. Verly. Robust Incremental Rectification of Sport Video Se-quences. British Machine Vision Conference. Kingston University, London, 2004.http://www.bmva.org/bmvc/2004/papers/paper 215.pdf
114 F. Devernay, O. Faugeras. Automatic Calibration and Removal of Distortion fromScenes of Structured Environments. SPIE. San Diego, CA, 1995, 2567:62–72
115 F. Devernay. A Non-maxima Suppression Method for Edge Detection withSub-pixel Accuracy. Tech. Rep. 2724, INRIA, 1995. ftp://ftp.inria.fr/INRIA/publication/publi-pdf/RR/RR-2724.pdf
116 R. I. Hartley. In Defense of the Eight-point Algorithm. IEEE Transactions onPattern Analysis and Machine Intelligence. 1997, 19(6):580–593
117 R. I. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision. Secondedn. Cambridge University Press, 2003. ISBN: 0521540518
118 M. A. Fischler, R. C. Bolles. Random Sample Consensus: A Paradigm for ModelFitting with Applications to Image Analysis and Automated Cartography. Commu-nications of the ACM. 1981, 24(6):381–395
119 P. H. S. Torr, D. W. Murray. The Development and Comparison of Robust Methodsfor Estimating the Fundamental Matrix. International Journal of Computer Vision.1997, 24(3):271–300
120 Z. Zhang. Determining the Epipolar Geometry and its Uncertainty: A Review.International Journal of Computer Vision. 1998, 27(2):161–195
121 P. H. S. Torr, A. Zisserman. MLESAC: A New Robust Estimator with Applicationto Estimating Image Geometry. Computer Vision and Image Understanding. 2000,78(1):138–156
122 O. Chum, J. Matas. Matching with Prosac - Progressive Sample Consensus. IEEEComputer Society Conference on Computer Vision and Pattern Recognition. SanDiego, CA, USA, 2005, 1:220–226
123 T. Lindeberg. Edge Detection and Ridge Detection with Automatic Scale Selection.International Journal of Computer Vision. 1998, 30(2):117–156
124 P.-E. Forsse′n. Maximally Stable Colour Regions for Recognition and Matching.IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Minneapolis, Minnesota, USA, 2007:1–8
125 P.-E. Forsse′n, D. G. Lowe. Shape Descriptors for Maximally Stable Extremal Re-gions. IEEE International Conference on Computer Vision. Rio de Janeiro, Brazil,2007:1–8
126 Y. Ke, R. Sukthankar. PCA-SIFT: A more Distinctive Representation for LocalImage Descriptors. IEEE Computer Society Conference on Computer Vision andPattern Recognition. Washington, DC, USA, 2004, 2:506–513. http://www.cs.cmu.edu/～yke/pcasift/
127 K. Mikolajczyk, C. Schmid. Scale & Affine Invariant Interest Point Detectors.International Journal of Computer Vision. 2004, 60(1):63–86
128 T. Kadir, A. Zisserman, M. Brady. An Affine Invariant Salient Region Detector. Eu-ropean Conference on Computer Vision. Prague, Czech Republic, 2004, 3021:228–241
129 H. Deng, W. Zhang, E. Mortensen, et al. Principal Curvature-based Region Detectorfor Object Recognition. IEEE Computer Society Conference on Computer Visionand Pattern Recognition. Minneapolis, Minnesota, USA, 2007:1–8
130 H. Bay, A. Essa, T. Tuytelaarsb, et al. Speeded-Up Robust Features (SURF). Com-puter Vision and Image Understanding. 2008, 110(3):346–359
131 K. Mikolajczyk, T. Tuytelaars, C. Schmid, et al. A Comparison of Affine RegionDetectors. International Journal of Computer Vision. 2005, 65(1-2):43–72
132 A. Noble. Descriptions of Image Surfaces. Ph.D. thesis, Department of EngineeringScience, Oxford University. 1989
133 S. M. Smith. Extracting Information from Images. First year D.Phil. report,Robotics Research Group, Department of Engineering Science, Oxford University,1990
134 S. Birchfield. KLT: An Implementation of the Kanade-lucas-tomasi FeatureTracker. Version 1.3.4 (30 Aug 2007), http://www.ces.clemson.edu/～stb/klt/
135 Intel. OpenCV. http://sourceforge.net/projects/opencvlibrary/
136 D. G. Lowe. Object Recognition from Local Scale-invariant Features. IEEE Inter-national Conference on Computer Vision. Kerkyra, Corfu, Greece, 1999, 2:1150–1157
137 M. Brown, D. G. Lowe. Recognising Panoramas. IEEE International Conference onComputer Vision. Nice, France, 2003:1218–1225. http://www.cs.ubc.ca/～mbrown/panorama/panorama.html
138 M. Brown, D. G. Lowe. Automatic Panoramic Image Stitching Using InvariantFeatures. International Journal of Computer Vision. 2007, 74(1):59–73
139 A. P. Witkin. Scale-Space Filtering. International Joint Conference on ArtificialIntelligence. Karlsruhe, Germany, 1983:1019–1022
140 J. J. Koenderink. The Structure of Images. Biological Cybernetics. 1984,50(5):363–370
141 T. Lindeberg. Scale-space Theory: A Basic Tool for Analysing Structures atDifferent Scales. Journal of Applied Statistics. 1994, 21(2):225–270. http://www.nada.kth.se/～tony/abstracts/Lin94-SI-abstract.html
142 P. J. Burt. Fast Filter Transforms for Image Processing. Computer Graphics andImage Processing. 1981, 16:20–51
143 P. J. Burt, E. H. Adelson. The Laplacian Pyramid as a Compact Image Code. IEEETransactions on Communications. 1983, 31(4):532–540. http://web.mit.edu/persci/people/adelson/pub pdfs/pyramid83.pdf
144 K. Mikolajczyk. Detection of Local Features Invariant to Affines Transformations.Ph.D. thesis, Institut National Polytechnique de Grenoble, France. 2002. http://perception.inrialpes.fr/Publications/2002/Mik02/Mikolajczyk these2002.pdf
145 M. Brown, D. G. Lowe. Invariant Features from Interest Point Groups. British Ma-chine Vision Conference. Cardiff, UK, 2002. http://www.bmva.ac.uk/bmvc/2002/papers/92/full 92.pdf
146 H.-Y. Shum, R. Szeliski. Systems and Experiment Paper: Construction ofPanoramic Image Mosaics with Global and Local Alignment. International Journalof Computer Vision. 2000, 36(2):101–130
147 P. J. Burt, E. H. Adelson. A Multiresolution Spline with Application to ImageMosaics. ACM Transactions on Graphics. 1983, 2(4):217–236. http://web.mit.edu/persci/people/adelson/pub pdfs/spline83.pdf
148 A. Papoulis. Probability, Random Variables, and Stochastic Processes. 2nd edn.McGraw-Hill Companies, 1984. ISBN: 0070484686
149 R. E. Kalman. A New Approach to Linear Filtering and Prediction Problems. Trans-actions of the ASME-Journal of Basic Engineering. 1960, 82(Series D):35–45
150 K. J. Bradshaw, I. D. Reid, D. W. Murray. The Active Recovery of 3d MotionTrajectories and Their Use in Prediction. IEEE Transactions on Pattern Analysisand Machine Intelligence. 1997, 19(3):219–234
151 P. S. Maybeck. Stochastic Models, Estimation, and Control. vol. 1. AcademicPress, 1979. ISBN: 0124807011
152 H. W. Sorenson. Least-squares Estimation: From Gauss to Kalman. IEEE Spec-trum. 1970, 7:63–68
153 D. A. Forsyth, J. Ponce. Computer Vision: A Modern Approach . Prentice Hall,2002. ISBN: 0130851981
154 M. Isard, A. Blake. Contour Tracking by Stochastic Propagation of ConditionalDensity. European Conference on Computer Vision. Cambridge, UK, 1996, Lec-ture Notes in Computer Science:343–356
155 M. S. Arulampalam, S. Maskell, N. Gordon, et al. A Tutorial on Particle Filters forOnline Nonlinear/non-gaussian Bayesian Tracking. IEEE Transactions on SignalProcessing. 2002, 50(2):174–188
156 O. King, D. Forsyth. How Does Condensation Behave with a Finite Number ofSamples? European Conference on Computer Vision. Dublin, Ireland, 2000, Lec-ture Notes in Computer Science:695–709
157 A. Doucet, S. Godsill, C. Andrieu. On Sequential Monte Carlo Sampling Methodsfor Bayesian Filtering. Statistics and Computing. 2000, 10(3):197–208
158 C. Chang, R. Ansari, A. Khokhar. Multiple Object Tracking with Kernel Parti-cle Filter. IEEE Computer Society Conference on Computer Vision and PatternRecognition. San Diego, CA, USA, 2005, 1:566–573
159 S. McKenna, H. Nait-Charif. Tracking Human Motion Using Auxiliary ParticleFilters and Iterated Likelihood Weighting. Image and Vision Computing. 2007,25(6):852–862
160 J. Vermaak, A. Doucet, P. Pe′rez. Maintaining Multi-modality Through MixtureTracking. IEEE International Conference on Computer Vision. Nice, France,2003:1110–1116
161袁泽剑,郑南宁,贾新春.高斯-厄米特粒子滤波器.电子学报. 2003, 31(7):970–973
162陈睿,刘国翌,赵国英,等.基于序列蒙特卡罗方法的3D人体运动跟踪.计算机辅助设计与图形学学报. 2005,17(1):85–92
163 Z. Khan, T. Balch, F. Dellaert. MCMC-Based Particle Filtering for Tracking aVariable Number of Interacting Targets. IEEE Transactions on Pattern Analysisand Machine Intelligence. 2005, 27(11):1805–1819
164 K. Smith, D. Gatica-Perez, J.-M. Odobez. Using Particles to Track Varying Num-bers of Interacting People. IEEE Computer Society Conference on Computer Vi-sion and Pattern Recognition. San Diego, CA, USA, 2005, 1:962–969
165 O. L. R. Jacobs. Introduction to Control Theory. Second edn. Oxford UniversityPress, 1994
166 S. J. Julier, J. K. Uhlmann, H. F. Durrant-Whyte. A New Approach for FilteringNonlinear Systems. Proceedings of the American Control Conference. 1995:1628–1632
167 S. J. Julier, J. K. Uhlmann. A New Extention of the Kalman Filter to NonlinearSystems. Int. Symp. Aerospace/Defense Sensing, Simul. and Controls, Orlando,FL. 1997
168 Y. Rui, Y. Chen. Better Proposal Distributions: Object Tracking Using UnscentedParticle Filter. International Conference on Computer Vision and Pattern Recogni-tion. Kauai, HI, USA, 2001, 2:786–793
169 C. Shen, A. van den Hengel, M. J. Brooks. Enhanced Importance Sampling: Un-scented Auxiliary Particle Filtering for Visual Tracking. Advances in ArtificialIntelligence: 17th Australian Joint Conference on Artificial Intelligence. Cairns,Australia, 2004, 3339:180–191
170 P. Wang, J. M. Rehg. A Modular Approach to the Analysis and Evaluation of Par-ticle Filters for Figure Tracking. IEEE Computer Society Conference on ComputerVision and Pattern Recognition. New York, NY, USA, 2006, 1:790–797
171潘泉,杨峰,叶亮,等.一类非线性滤波器–UKF综述.控制与决策. 2005,20(5):481–489
172 B. Stenger, P. R. S. Mendonca, R. Cipolla. Model-Based Hand Tracking Using anUnscented Kalman Filter. British Machine Vision Conference. Manchester, UK,2001, 1:63–72. http://www.bmva.ac.uk/bmvc/2001/papers/89/89.html
173 B. Stenger. Model-Based Hand Tracking Using a Hierarchical Bayesian Filter.Ph.D. thesis, Department of Engineering, University of Cambridge. 2004. http://mi.eng.cam.ac.uk/～bdrs2/pubs.html
174 Y. Chen, Y. Rui, T. S. Huang. Multicue HMM-UKF for Real-time Contour Track-ing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006,28(9):1525–1529
175 S. J. Julier. Process Models for the Navigation of High-speed Land Vehicles. Ph.D.thesis, Robotics Research Group, Department of Engineering Science, Universityof Oxford. 1997. http://www.cs.ucl.ac.uk/staff/S.Julier/publications/index.html
176 R. van der Merwe, A. Doucet, N. de Freitas, et al. The Unscented Particle Filter.Tech. Rep. CUED/F-INFENG/TR380, Cambridge University Engineering Depart-ment, 2000
177 S. J. Julier, J. K. Uhlmann, H. F. Durrant-Whyte. A New Method for the Non-linear Transformation of Means and Covariances in Filters and Estimators. IEEETransactions on Automatic Control. 2000, 45(3):477–482
178 M. J. Swain, D. H. Ballard. Color Indexing . International Journal of ComputerVision. 1991, 7(1):11–32
179 F. J. Aherne, N. A. Thacker, P. I. Rockett. The Bhattacharyya Metric as an AbsoluteSimilarity Measure for Frequency Coded Data. Kybernetika. 1997, 34(4):363–368
180 A. Bhattacharyya. On a Measure of Divergence between Two Statistical Popula-tions Defined by Their Probability Distributions. Bulletin of the Calcutta Mathe-matical Society. 1943, 35:99–110
181 G. Bradski, A. Kaehler. Learning OpenCV. First edn. 1005 Gravenstein HighwayNorth, Sebastopol, CA 95472: O’Reilly Media, Inc., 2008. ISBN: 978-0-596-51613-0
182 Z. Fan, M. Yang, Y. Wu, et al. Efficient Optimal Kernel Placement for ReliableVisual Tracking. IEEE Computer Society Conference on Computer Vision andPattern Recognition. New York, NY, USA, 2006, 1:658–665
183 I. Guskov. Kernel-based Template Alignment. IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition. New York, NY, USA, 2006, 1:610–617
184 V. Parameswaran, V. Ramesh, I. Zoghlami. Tunable Kernels for Tracking. IEEEComputer Society Conference on Computer Vision and Pattern Recognition. NewYork, NY, USA, 2006, 2:2179–2186
185 A. Yilmaz. Object Tracking by Asymmetric Kernel Mean Shift with AutomaticScale and Orientation Selection. IEEE Computer Society Conference on ComputerVision and Pattern Recognition. Minneapolis, Minnesota, USA, 2007:1–6
186 C. J. Needham, R. D. Boyle. Performance Evaluation Metrics and Statistics forPositional Tracker Evaluation. International Conference on Computer Vision Sys-tems. Graz, Austria, 2003, 2626:278–289
2 J. Matas, O. Chum, M.Urban, et al. Robust Wide Baseline Stereo from MaximallyStable Extremal Regions. P. L. Rosin, A. D. Marshall, (Editors) British Machine Vi-sion Conference. Cardiff, UK, 2002:384–396. http://www.bmva.ac.uk/bmvc/2002/papers/113/full 113.pdf
3 J. Canny. A Computational Approach to Edge Detection. IEEE Transactions onPattern Analysis and Machine Intelligence. 1986, 8(6):679–698
4 H. Li, B. S. Manjunath, S. K. Mitra. A Contour-based Approach to MultisensorImage Registration. IEEE Transactions on Image Processing. 1995, 4(3):320–334
5 S. Moss, E. R. Hancock. Multiple Line-template Matching with Em Algorithm.Pattern Recognition Letters. 1997, 18(11–13):1283–1292
6 S. M. Smith, J. M. Brady. SUSAN―A New Approach to Low Level Image Pro-cessing. International Journal of Computer Vision. 1997, 23(1):45–78
7 C. Harris, M. Stephens. A Combined Corner and Edge Detector. Proceedings ofthe Fourth Alvey Vision Conference. Manchester, UK, 1988:147–151
8 B. Georgescu, P. Meer. Point Matching under Large Image Deformations and Il-lumination Changes. IEEE Transactions on Pattern Analysis and Machine Intelli-gence. 2004, 26(6):674–688
9 A. Yilmaz, O. Javed, M. Shah. Object Tracking: A Survey. ACM ComputingSurveys. 2006, 38(4):1–45
10侯志强,韩崇昭.视觉跟踪技术综述.自动化学报. 2006, 32(4):603–617
11 Y. Luo, T.-D. Wu, J.-N. Hwang. Object-based Analysis and Interpretation of Hu-man Motion in Sports Video Sequences by Dynamic Bayesian Networks. ComputerVision and Image Understanding. 2003, 92(2-3):196–216
12 C. J. Veenman, M. J. Reinders, E. Backer. Resolving Motion Correspondence forDensely Moving Points. IEEE Transactions on Pattern Analysis and Machine In-telligence. 2001, 23(1):54–72
13 D. Comaniciu, V. Ramesh, P. Meer. Kernel-Based Object Tracking. IEEE Transac-tions on Pattern Analysis and Machine Intelligence. 2003, 25(5):564–577
14 A. Yilmaz, X. li, M. Shah. Contour-Based Object Tracking with Occlusion Han-dling in Video Acquired Using Mobile Cameras. IEEE Transactions on PatternAnalysis and Machine Intelligence. 2004, 26(11):1531–1536
15 I. Haritaoglu, D. Harwood, L. S. Davis. W4: Real-time Surveillance of People andTheir Activities. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000, 22(8):809–830
16 H. Ning, T. Tan, L. Wang, et al. Kinematics-based Tracking of Human Walking inMonocular Video Sequences. Image and Vision Computing. 2004, 22(5):429–441
17 T. B. Moeslund, A. Hilton, V. Kru¨ger. A Survey of Advances in Vision-basedHuman Motion Capture and Analysis. Computer Vision and Image Understanding.2006, 104(2-3):90–126
18 R. Poppe. Vision-based Human Motion Analysis: An Overview. Computer Visionand Image Understanding. 2007, 108(1-2):4–18
19 J. K. Aggarwal, Q. Cai. Human Motion Analysis: A Review. Computer Vision andImage Understanding. 1999, 73(3):428–440
20 P. Fieguth, D. Terzopoulos. Color-Based Tracking of Heads and Other MobileObjects at Video Frame Rates. IEEE Computer Society Conference on ComputerVision and Pattern Recognition. San Juan, Puerto Rico, 1997:21–27
21 M. J. Black, A. D. Jepson. EigenTracking: Robust Matching and Tracking of Artic-ulated Objects Using a View-based Representation. International Journal of Com-puter Vision. 1998, 26(1):63–84
22 G. Paschos. Perceptually Uniform Color Spaces for Color Texture Analysis: AnEmpirical Evaluation. IEEE Transactions on Image Processing. 2001, 10(6):932–937
23 H. D. Cheng, X. H. Jiang, Y. Sun, et al. Color Image Segmentation: Advances andProspects . Pattern Recognition. 2001, 34(12):2259–2281
24 G. R. Bradski, S. Clara. Computer Vision Face Tracking for Use in a PerceptualUser Interface. Intel Technology Journal. 1998, 2(2):1–15. http://download.intel.com/technology/itj/q21998/pdf/camshift.pdf
25 P. Pe′rez, C. Hue, J. Vermaak, et al. Color-Based Probabilistic Tracking. EuropeanConference on Computer Vision. Copenhagen, Denmark, 2002, 2350:661–675
26 K. Nummiaro, E. Koller-Meier, L. V. Gool. An Adaptive Color-based Particle Filter.Image and Vision Computing. 2003, 21(1):99–110
27 J. Czyz, B. Ristic, B. Macq. A Particle Filter for Joint Detection and Tracking ofColor Objects. Image and Vision Computing. 2007, 25(8):1271–1281
28 K. Bowyer, C. Kranenburg, S. Dougherty. Edge Detector Evaluation Using Empir-ical Roc Curves. Computer Vision and Image Understanding. 2001, 84(1):77–103
29 B. K. Horn, B. G. Rhunck. Determining Optical Flow. Artificial Intelligence. 1981,17(1-3):185–203
30 B. D. Lucas, T. Kanade. An Iterative Image Registration Technique with an Appli-cation to Stereo Vision. International Joint Conference on Artificial Intelligence.Vancouver, British Columbia, Canada, 1981:674–679
31 J. L. Barron, D. J. Fleet, S. S. Beauchemin. Performance of Optical Flow Tech-niques. International Journal of Computer Vision. 1994, 12(1):43–77
32 K. Mikolajczyk, C. Schmid. A Performance Evaluation of Local Descriptors. IEEETransactions on Pattern Analysis and Machine Intelligence. 2005, 27(10):1615–1630
33 H. Moravec. Obstacle Avoidance and Navigation in the Real World by a SeeingRobot Rover. Tech. Rep. CMU-RI-TR-80-03, Robotics Institute, Carnegie MellonUniversity, 1980. http://www.ri.cmu.edu/pubs/pub 22.html
34 J. Shi, C. Tomasi. Good Features to Track. IEEE Computer Society Conference onComputer Vision and Pattern Recognition. Seattle, WA, USA, 1994:593–600
35 C. Tomasi, T. Kanade. Detection and Tracking of Point Features. Tech. Rep.CMU-CS-91-132, Carnegie Mellon University, Pittsburgh, PA 15213, 1991. http://reports-archive.adm.cs.cmu.edu/anon/1991/CMU-CS-91-132.ps
36 D. G. Lowe. Distinctive Image Features from Scale-invariant Keypoints. Interna-tional Journal of Computer Vision. 2004, 60(2):91–110
37 H. Zhou, Y. Yuan, C. Shi. Object Tracking Using SIFT Features and Mean Shift.Computer Vision and Image Understanding. 2009, 113(3):345–352
38 R. Jain, H. Nagel. On the Analysis of Accumulative Difference Pictures from Im-age Sequences of Real World Scenes. IEEE Transactions on Pattern Analysis andMachine Intelligence. 1979, 1(2):206–214
39 C. R. Wren, A. Azarbayejani, T. Darrell, et al. Pfinder: Real-time Tracking of theHuman Body. IEEE Transactions on Pattern Analysis and Machine Intelligence.1997, 19(7):780–785
40 A. M. Elgammal, D. Harwood, L. S. Davis. Non-parametric Model for BackgroundSubtraction. European Conference on Computer Vision. Dublin, Ireland, 2000,Lecture Notes in Computer Science:751–767
41 L. Taycher, J. W. F. III, T. Darrell. Combining Object and Feature Dynamics inProbabilistic Tracking. IEEE Computer Society Conference on Computer Visionand Pattern Recognition. San Diego, CA, USA, 2005, 2:106–113
42 D. Comaniciu, P. Meer. Mean Shift: A Robust Approach Toward Feature SpaceAnalysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002,24(5):603–619
43 J. Shi, J. Malik. Normalized Cuts and Image Segmentation. IEEE Transactions onPattern Analysis and Machine Intelligence. 2000, 22(8):888–905
44 M. Kass, A. Witkin, D. Terzopoulos. Snakes: Active Contour Models. InternationalJournal of Computer Vision. 1988, 1(4):321–331
45 D. Cremers. Dynamical Statistical Shape Priors for Level Set-based Tracking. IEEETransactions on Pattern Analysis and Machine Intelligence. 2006, 28(8):1262–1273
46 T. Zhang, D. Freedman. Improving Performance of Distribution Tracking ThroughBackground Mismatch. IEEE Transactions on Pattern Analysis and Machine Intel-ligence. 2005, 27(2):282–287
47 P. Viola, M. J. Jones, D. Snow. Detecting Pedestrians Using Patterns of Motion andAppearance. IEEE International Conference on Computer Vision. Nice, France,2003, 2:734–741
48 K. Okuma, A. Taleghani, N. D. Freitas, et al. A Boosted Particle Filter: MultitargetDetection and Tracking. European Conference on Computer Vision. Prague, CzechRepublic, 2004, 3021:28–39
49 S. Avidan. Ensemble Tracking. IEEE Computer Society Conference on ComputerVision and Pattern Recognition. San Diego, CA, USA, 2005, 2:494–501
50 S. Avidan. Support Vector Tracking. IEEE Transactions on Pattern Analysis andMachine Intelligence. 2004, 26(8):1064–1072
51 C. Papageorgiou, M. Oren, T. Poggio. A General Framework for Object Detection.IEEE International Conference on Computer Vision. Bombay, India, 1998:555–562
52 H. W. Kuhn. The Hungarian Method for the Assignment Problem. Naval ResearchLogistics Quarterly. 1955, 2(1-2):83–97
53 I. K. Sethi, R. Jain. Finding Trajectories of Feature Points in a Monocular ImageSequence. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1987,9(1):56–73
54 K. Shafique, M. Shah. A Noniterative Greedy Algorithm for Multiframe PointCorrespondence. IEEE Transactions on Pattern Analysis and Machine Intelligence.2005, 27(1):51–65
55 S. S. Intille, J. W. Davis, A. F. Bobick. Real-Time Closed-world Tracking. IEEEComputer Society Conference on Computer Vision and Pattern Recognition. SanJuan, Puerto Rico, 1997:697–703
56 Y. Bar-Shalom, T. E. Fortmann. Tracking and Data Association. Academic Press,1988
57 I. J. Cox. A Review of Statistical Data Association Techniques for Motion Corre-spondence. International Journal of Computer Vision. 1993, 10(1):53–66
58 C. Rasmussen, G. D. Hager. Probabilistic Data Association Methods for Track-ing Complex Visual Objects. IEEE Transactions on Pattern Analysis and MachineIntelligence. 2001, 23(6):560–576
59 D. B. Reid. An Algorithm for Tracking Multiple Targets. IEEE Transactions onAutomatic Control. 1979, 24(6):843–854
60 C. Hue, J.-P. L. Cadre, P. Pe′rez. Sequential Monte Carlo Methods for MultipleTarget Tracking and Data Fusion. IEEE Transactions on Signal Processing. 2002,50(2):309–325
61 H. Schweitzer, J. W. Bell, F. Wu. Very Fast Template Matching. European Confer-ence on Computer Vision. Copenhagen, Denmark, 2002, 2353:358–372
62 I. Matthews, T. Ishikawa, S. Baker. The Template Update Problem. IEEE Transac-tions on Pattern Analysis and Machine Intelligence. 2004, 26(6):810–815
63 A. D. Jepson, D. J. Fleet, T. F. El-Maraghi. Robust Online Appearance Models forVisual Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence.2003, 25(10):1296–1311
64 M. Isard, J. MacCormick. BraMBLe: A Bayesian Multiple-blob Tracker. IEEE In-ternational Conference on Computer Vision. Vancouver, British Columbia, Canada,2001, 2:34–41
65 H. Tao, H. S. Sawhney, R. Kumar. Object Tracking with Bayesian Estimation ofDynamic Layer Representations. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence. 2002, 24(1):75–89
66 D. P. Huttenlocher, J. J. Noh, W. J. Rucklidge. Tracking Non-rigid Objects in Com-plex Scenes. IEEE International Conference on Computer Vision. Berlin, Germany,1993:93–101
67 F. Hausdorff. Set Theory. 3rd edn. Chelsea Publishing Company, 1978. ISBN:0828401195
68 M. Isard, A. Blake. CONDENSATION―Conditional Density Propagation for Vi-sual Tracking. International Journal of Computer Vision. 1998, 29(1):5–28
69 J. MacCormick, A. Blake. A Probabilistic Exclusion Principle for Tracking Multi-ple Objects. International Journal of Computer Vision. 2000, 39(1):57–71
70 M. Bertalmio, G. Sapiro, G. Randall. Morphing Active Contours. IEEE Transac-tions on Pattern Analysis and Machine Intelligence. 2000, 22(7):733–737
71 A.-R. Mansouri. Region Tracking via Level Set PDEs without Motion Compu-tation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002,24(7):947–961
72 S. S. Intille, A. F. Bobick. Recognizing Planned, Multiperson Action. ComputerVision and Image Understanding. 2001, 81(3):414–445
73 C. J. Needham. Tracking and Modelling of Team Game Interactions. Ph.D. thesis,The University of Leeds. 2003
74 Y. Gong, M. Han, W. Hua, et al. Maximum Entropy Model-based Baseball High-light Detection and Classification. Computer Vision and Image Understanding.2004, 96(2):181–199
75 H. Denman, N. Rea, A. Kokaram. Content-based Analysis for Video from SnookerBroadcasts. Computer Vision and Image Understanding. 2003, 92(2-3):176–195
76 S. S. Intille, A. F. Bobick. Closed-World Tracking. IEEE International Con-ference on Computer Vision. Massachusetts Institute of Technology, Cambridge,1995:672–678
77 J. Assfalg, M. Bertini, C. Colombo, et al. Semantic Annotation of Soccer Videos:Automatic Highlights Identification. Computer Vision and Image Understanding.2003, 92(2-3):285–305
78 F. Li, R. J. Woodham. Analysis of Player Actions in Selected Hockey Game Situa-tions. Canadian Conference on Computer and Robot Vision. Victoria, BC, Canada,2005:152–159
79 M. Persˇe, M. Kristan, J. Persˇ. A Template-based Multi-player Action Recognitionof the Basketball Game. ECCV Workshop on Computer Vision Based Analysis inSport Environments. Graz, Austria, 2006:71–82
80 R. Leonardi, P. Migliorati, M. Prandini. Semantic Indexing of Sports Program Se-quences by Audio-visual Analysis. International Conference on Image Processing.Barcelona, Spain, 2003, 1:9–12
81 Hawk-Eye Innovations. http://www.hawkeyeinnovations.co.uk/
82 G. S. Pingali, Y. Jean, I. Carlborn. Real Time Tracking for Enhanced Tennis Broad-casts. IEEE Computer Society Conference on Computer Vision and Pattern Recog-nition. Santa Barbara, CA, USA, 1998:260–265
83 F. Yan, A. Kostin, W. Christmas, et al. A Novel Data Association Algorithm forObject Tracking in Clutter with Application to Tennis Video Analysis. IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition. New York,2006, 1:634–641
84 F. Yan, W. Christmas, J. Kittler. Layered Data Association Using Graph-theoretic Formulation with Application to Tennis Ball Tracking in Monocular Se-quences. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008,30(10):1814–1830
85 SIMI. Http://www.simi.com
86 Dartfish. Http://www.dartfish.com
87吴思,林守勋,张勇东.基于动态背景构造的视频运动对象自动分割.计算机学报. 2005,28(8):1386–1392
88王兆其,张勇东,夏时洪.体育训练三维人体运动模拟与视频分析系统.计算机研究与发展. 2005,42(2):344–352
89 TRUAKUS. Http://www.trakus.com
90 A. A. Efros, A. C. Berg, G. Mori, et al. Recognizing Action at a Distance. IEEEInternational Conference on Computer Vision. Nice, France,, 2003, 2:726–733
91 A. Ekin, A. M. Tekalp. Automatic Soccer Video Analysis and Summarization.IEEE Transactions on Image Processing. 2001, 12(7):796–807
92 P. J. Figueroa, N. J. Leite, R. M. Barros. Tracking Soccer Players Aiming TheirKinematical Motion Analysis. Computer Vision and Image Understanding. 2006,101(2):122–135
93 S. Iwase, H. Saito. Tracking Soccer Players Based on Homography Among Mul-tiple Views. T. Ebrahimi, T. Sikora, (Editors) Visual Communications and ImageProcessing. Lugano, Switzerland, 2003, 5150:283–292
94 M. Xu, J. Orwell, L. Lowey, et al. Architecture and Algorithms for Tracking Foot-ball Players with Multiple Cameras. IEE Proceedings Vision, Image and SignalProcessing. 2005, 152:232–241
95 T. Misu, M. Naemura, W. Zheng, et al. Robust Tracking of Soccer Players Basedon Data Fusion. International Conference on Pattern Recognition. Quebec, Canada,2002, 1:556–561
96 N. Vandenbroucke, L. Macaire, J.-G. Postaire. Color Image Segmentation by PixelClassification in an Adapted Hybrid Color Space. Applications to Soccer ImageAnalysis. Computer Vision and Image Understanding. 2003, 90(2):190–216
97 C. J. Needham, R. D. Boyle. Tracking Multiple Sports Players Through Occlusion,Congestion and Scale. British Machine Vision Conference. 2001, 1:93–102
98 B. M. Junior, R. de Oliveira Anido. Distributed Real-time Soccer Tracking. Pro-ceedings of the ACM Second International Workshop on Video Surveillance &Sensor Networks. New York, USA, 2004:97–103
99 V. Lumikero. Football Tracking in Wide-screen Video Sequences. Master’s thesis,Royal Institute of Technology. 2004. http://www.nada.kth.se/utbildning/grukth/exjobb/rapportlistor/2004/rapporter04/lumikero ville 04010.pdf
100 J. Persˇ, G. Vucˇkovicˇ, S. Kovacˇicˇ, et al. A Low-cost Real-time Tracker of LiveSport Events. The 2nd international symposium on image and signal processingand analysis. Pula, Croatia, 2001:362–365
101 J. Persˇ, M. Bon, S. Kovacˇicˇ, et al. Observation and Analysis of Large-scale HumanMotion. Human Movement Science. 2002, 21(2):295–311
102 M. Jug, J. Pers?, B. Dez?man, et al. Trajectory Based Assessment of CoordinatedHuman Activity. International Conference on Computer Vision Systems. Graz,Austria, 2003, 2626:534–543
103 S. S. Intille, A. F. Bobick. Tracking Using a Local Closed-world Assumption:Tracking in the Football Domain. MIT Media Lab Perceptual Computing GroupTechnical Report 296, 1994
104 K. Okuma. Automatic Acquisition of Motion Trajectories: Tracking Hockey Play-ers. Master’s thesis, The University of British Columbia. 2003
105 K. Okuma, J. J. Little, D. G. Lowe. Automatic Rectification of Long Image Se-quences. Asian Conference on Computer Vision. Jeju Island, Korea, 2004
106 Y. Cai. Robust Visual Tracking for Multiple Targets. Master’s thesis, The Universityof British Columbia. 2005
107 F. Li. Description, Analysis and Prediction of Player Actions in Selected HockeyGame Situations. Master’s thesis, The University of British Columbia. 2004
108 ISU: International Skating Union. Http://www.isu.org/
109 Y. Caspi, M. Irani. Aligning Non-overlapping Sequences. International Journal ofComputer Vision. 2002, 48(1):39–51
110 Y. Caspi, D. Simakov, M. Irani. Feature-Based Sequence-to-sequence Matching.International Journal of Computer Vision. 2006, 68(1):53–64
111 E. Hayman, D. W. Murray. The Effects of Translational Misalignment When Self-calibrating Rotating and Zooming Cameras. IEEE Transactions on Pattern Analysisand Machine Intelligence. 2003, 25(8):1015–1020
112 D. Farin, S. Krabbe, P. H. de With, et al. Robust Camera Calibration for SportVideos Using Court Models. SPIE Storage and Retrieval Methods and Applica-tions for Multimedia. San Jose, CA, USA, 2004, 5307:80–91. http://vca.ele.tue.nl/publications/data/Farin2004b.pdf
113 J.-B. Hayet, J. Piater, J. Verly. Robust Incremental Rectification of Sport Video Se-quences. British Machine Vision Conference. Kingston University, London, 2004.http://www.bmva.org/bmvc/2004/papers/paper 215.pdf
114 F. Devernay, O. Faugeras. Automatic Calibration and Removal of Distortion fromScenes of Structured Environments. SPIE. San Diego, CA, 1995, 2567:62–72
115 F. Devernay. A Non-maxima Suppression Method for Edge Detection withSub-pixel Accuracy. Tech. Rep. 2724, INRIA, 1995. ftp://ftp.inria.fr/INRIA/publication/publi-pdf/RR/RR-2724.pdf
116 R. I. Hartley. In Defense of the Eight-point Algorithm. IEEE Transactions onPattern Analysis and Machine Intelligence. 1997, 19(6):580–593
117 R. I. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision. Secondedn. Cambridge University Press, 2003. ISBN: 0521540518
118 M. A. Fischler, R. C. Bolles. Random Sample Consensus: A Paradigm for ModelFitting with Applications to Image Analysis and Automated Cartography. Commu-nications of the ACM. 1981, 24(6):381–395
119 P. H. S. Torr, D. W. Murray. The Development and Comparison of Robust Methodsfor Estimating the Fundamental Matrix. International Journal of Computer Vision.1997, 24(3):271–300
120 Z. Zhang. Determining the Epipolar Geometry and its Uncertainty: A Review.International Journal of Computer Vision. 1998, 27(2):161–195
121 P. H. S. Torr, A. Zisserman. MLESAC: A New Robust Estimator with Applicationto Estimating Image Geometry. Computer Vision and Image Understanding. 2000,78(1):138–156
122 O. Chum, J. Matas. Matching with Prosac - Progressive Sample Consensus. IEEEComputer Society Conference on Computer Vision and Pattern Recognition. SanDiego, CA, USA, 2005, 1:220–226
123 T. Lindeberg. Edge Detection and Ridge Detection with Automatic Scale Selection.International Journal of Computer Vision. 1998, 30(2):117–156
124 P.-E. Forsse′n. Maximally Stable Colour Regions for Recognition and Matching.IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Minneapolis, Minnesota, USA, 2007:1–8
125 P.-E. Forsse′n, D. G. Lowe. Shape Descriptors for Maximally Stable Extremal Re-gions. IEEE International Conference on Computer Vision. Rio de Janeiro, Brazil,2007:1–8
126 Y. Ke, R. Sukthankar. PCA-SIFT: A more Distinctive Representation for LocalImage Descriptors. IEEE Computer Society Conference on Computer Vision andPattern Recognition. Washington, DC, USA, 2004, 2:506–513. http://www.cs.cmu.edu/～yke/pcasift/
127 K. Mikolajczyk, C. Schmid. Scale & Affine Invariant Interest Point Detectors.International Journal of Computer Vision. 2004, 60(1):63–86
128 T. Kadir, A. Zisserman, M. Brady. An Affine Invariant Salient Region Detector. Eu-ropean Conference on Computer Vision. Prague, Czech Republic, 2004, 3021:228–241
129 H. Deng, W. Zhang, E. Mortensen, et al. Principal Curvature-based Region Detectorfor Object Recognition. IEEE Computer Society Conference on Computer Visionand Pattern Recognition. Minneapolis, Minnesota, USA, 2007:1–8
130 H. Bay, A. Essa, T. Tuytelaarsb, et al. Speeded-Up Robust Features (SURF). Com-puter Vision and Image Understanding. 2008, 110(3):346–359
131 K. Mikolajczyk, T. Tuytelaars, C. Schmid, et al. A Comparison of Affine RegionDetectors. International Journal of Computer Vision. 2005, 65(1-2):43–72
132 A. Noble. Descriptions of Image Surfaces. Ph.D. thesis, Department of EngineeringScience, Oxford University. 1989
133 S. M. Smith. Extracting Information from Images. First year D.Phil. report,Robotics Research Group, Department of Engineering Science, Oxford University,1990
134 S. Birchfield. KLT: An Implementation of the Kanade-lucas-tomasi FeatureTracker. Version 1.3.4 (30 Aug 2007), http://www.ces.clemson.edu/～stb/klt/
135 Intel. OpenCV. http://sourceforge.net/projects/opencvlibrary/
136 D. G. Lowe. Object Recognition from Local Scale-invariant Features. IEEE Inter-national Conference on Computer Vision. Kerkyra, Corfu, Greece, 1999, 2:1150–1157
137 M. Brown, D. G. Lowe. Recognising Panoramas. IEEE International Conference onComputer Vision. Nice, France, 2003:1218–1225. http://www.cs.ubc.ca/～mbrown/panorama/panorama.html
138 M. Brown, D. G. Lowe. Automatic Panoramic Image Stitching Using InvariantFeatures. International Journal of Computer Vision. 2007, 74(1):59–73
139 A. P. Witkin. Scale-Space Filtering. International Joint Conference on ArtificialIntelligence. Karlsruhe, Germany, 1983:1019–1022
140 J. J. Koenderink. The Structure of Images. Biological Cybernetics. 1984,50(5):363–370
141 T. Lindeberg. Scale-space Theory: A Basic Tool for Analysing Structures atDifferent Scales. Journal of Applied Statistics. 1994, 21(2):225–270. http://www.nada.kth.se/～tony/abstracts/Lin94-SI-abstract.html
142 P. J. Burt. Fast Filter Transforms for Image Processing. Computer Graphics andImage Processing. 1981, 16:20–51
143 P. J. Burt, E. H. Adelson. The Laplacian Pyramid as a Compact Image Code. IEEETransactions on Communications. 1983, 31(4):532–540. http://web.mit.edu/persci/people/adelson/pub pdfs/pyramid83.pdf
144 K. Mikolajczyk. Detection of Local Features Invariant to Affines Transformations.Ph.D. thesis, Institut National Polytechnique de Grenoble, France. 2002. http://perception.inrialpes.fr/Publications/2002/Mik02/Mikolajczyk these2002.pdf
145 M. Brown, D. G. Lowe. Invariant Features from Interest Point Groups. British Ma-chine Vision Conference. Cardiff, UK, 2002. http://www.bmva.ac.uk/bmvc/2002/papers/92/full 92.pdf
146 H.-Y. Shum, R. Szeliski. Systems and Experiment Paper: Construction ofPanoramic Image Mosaics with Global and Local Alignment. International Journalof Computer Vision. 2000, 36(2):101–130
147 P. J. Burt, E. H. Adelson. A Multiresolution Spline with Application to ImageMosaics. ACM Transactions on Graphics. 1983, 2(4):217–236. http://web.mit.edu/persci/people/adelson/pub pdfs/spline83.pdf
148 A. Papoulis. Probability, Random Variables, and Stochastic Processes. 2nd edn.McGraw-Hill Companies, 1984. ISBN: 0070484686
149 R. E. Kalman. A New Approach to Linear Filtering and Prediction Problems. Trans-actions of the ASME-Journal of Basic Engineering. 1960, 82(Series D):35–45
150 K. J. Bradshaw, I. D. Reid, D. W. Murray. The Active Recovery of 3d MotionTrajectories and Their Use in Prediction. IEEE Transactions on Pattern Analysisand Machine Intelligence. 1997, 19(3):219–234
151 P. S. Maybeck. Stochastic Models, Estimation, and Control. vol. 1. AcademicPress, 1979. ISBN: 0124807011
152 H. W. Sorenson. Least-squares Estimation: From Gauss to Kalman. IEEE Spec-trum. 1970, 7:63–68
153 D. A. Forsyth, J. Ponce. Computer Vision: A Modern Approach . Prentice Hall,2002. ISBN: 0130851981
154 M. Isard, A. Blake. Contour Tracking by Stochastic Propagation of ConditionalDensity. European Conference on Computer Vision. Cambridge, UK, 1996, Lec-ture Notes in Computer Science:343–356
155 M. S. Arulampalam, S. Maskell, N. Gordon, et al. A Tutorial on Particle Filters forOnline Nonlinear/non-gaussian Bayesian Tracking. IEEE Transactions on SignalProcessing. 2002, 50(2):174–188
156 O. King, D. Forsyth. How Does Condensation Behave with a Finite Number ofSamples? European Conference on Computer Vision. Dublin, Ireland, 2000, Lec-ture Notes in Computer Science:695–709
157 A. Doucet, S. Godsill, C. Andrieu. On Sequential Monte Carlo Sampling Methodsfor Bayesian Filtering. Statistics and Computing. 2000, 10(3):197–208
158 C. Chang, R. Ansari, A. Khokhar. Multiple Object Tracking with Kernel Parti-cle Filter. IEEE Computer Society Conference on Computer Vision and PatternRecognition. San Diego, CA, USA, 2005, 1:566–573
159 S. McKenna, H. Nait-Charif. Tracking Human Motion Using Auxiliary ParticleFilters and Iterated Likelihood Weighting. Image and Vision Computing. 2007,25(6):852–862
160 J. Vermaak, A. Doucet, P. Pe′rez. Maintaining Multi-modality Through MixtureTracking. IEEE International Conference on Computer Vision. Nice, France,2003:1110–1116
161袁泽剑,郑南宁,贾新春.高斯-厄米特粒子滤波器.电子学报. 2003, 31(7):970–973
162陈睿,刘国翌,赵国英,等.基于序列蒙特卡罗方法的3D人体运动跟踪.计算机辅助设计与图形学学报. 2005,17(1):85–92
163 Z. Khan, T. Balch, F. Dellaert. MCMC-Based Particle Filtering for Tracking aVariable Number of Interacting Targets. IEEE Transactions on Pattern Analysisand Machine Intelligence. 2005, 27(11):1805–1819
164 K. Smith, D. Gatica-Perez, J.-M. Odobez. Using Particles to Track Varying Num-bers of Interacting People. IEEE Computer Society Conference on Computer Vi-sion and Pattern Recognition. San Diego, CA, USA, 2005, 1:962–969
165 O. L. R. Jacobs. Introduction to Control Theory. Second edn. Oxford UniversityPress, 1994
166 S. J. Julier, J. K. Uhlmann, H. F. Durrant-Whyte. A New Approach for FilteringNonlinear Systems. Proceedings of the American Control Conference. 1995:1628–1632
167 S. J. Julier, J. K. Uhlmann. A New Extention of the Kalman Filter to NonlinearSystems. Int. Symp. Aerospace/Defense Sensing, Simul. and Controls, Orlando,FL. 1997
168 Y. Rui, Y. Chen. Better Proposal Distributions: Object Tracking Using UnscentedParticle Filter. International Conference on Computer Vision and Pattern Recogni-tion. Kauai, HI, USA, 2001, 2:786–793
169 C. Shen, A. van den Hengel, M. J. Brooks. Enhanced Importance Sampling: Un-scented Auxiliary Particle Filtering for Visual Tracking. Advances in ArtificialIntelligence: 17th Australian Joint Conference on Artificial Intelligence. Cairns,Australia, 2004, 3339:180–191
170 P. Wang, J. M. Rehg. A Modular Approach to the Analysis and Evaluation of Par-ticle Filters for Figure Tracking. IEEE Computer Society Conference on ComputerVision and Pattern Recognition. New York, NY, USA, 2006, 1:790–797
171潘泉,杨峰,叶亮,等.一类非线性滤波器–UKF综述.控制与决策. 2005,20(5):481–489
172 B. Stenger, P. R. S. Mendonca, R. Cipolla. Model-Based Hand Tracking Using anUnscented Kalman Filter. British Machine Vision Conference. Manchester, UK,2001, 1:63–72. http://www.bmva.ac.uk/bmvc/2001/papers/89/89.html
173 B. Stenger. Model-Based Hand Tracking Using a Hierarchical Bayesian Filter.Ph.D. thesis, Department of Engineering, University of Cambridge. 2004. http://mi.eng.cam.ac.uk/～bdrs2/pubs.html
174 Y. Chen, Y. Rui, T. S. Huang. Multicue HMM-UKF for Real-time Contour Track-ing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006,28(9):1525–1529
175 S. J. Julier. Process Models for the Navigation of High-speed Land Vehicles. Ph.D.thesis, Robotics Research Group, Department of Engineering Science, Universityof Oxford. 1997. http://www.cs.ucl.ac.uk/staff/S.Julier/publications/index.html
176 R. van der Merwe, A. Doucet, N. de Freitas, et al. The Unscented Particle Filter.Tech. Rep. CUED/F-INFENG/TR380, Cambridge University Engineering Depart-ment, 2000
177 S. J. Julier, J. K. Uhlmann, H. F. Durrant-Whyte. A New Method for the Non-linear Transformation of Means and Covariances in Filters and Estimators. IEEETransactions on Automatic Control. 2000, 45(3):477–482
178 M. J. Swain, D. H. Ballard. Color Indexing . International Journal of ComputerVision. 1991, 7(1):11–32
179 F. J. Aherne, N. A. Thacker, P. I. Rockett. The Bhattacharyya Metric as an AbsoluteSimilarity Measure for Frequency Coded Data. Kybernetika. 1997, 34(4):363–368
180 A. Bhattacharyya. On a Measure of Divergence between Two Statistical Popula-tions Defined by Their Probability Distributions. Bulletin of the Calcutta Mathe-matical Society. 1943, 35:99–110
181 G. Bradski, A. Kaehler. Learning OpenCV. First edn. 1005 Gravenstein HighwayNorth, Sebastopol, CA 95472: O’Reilly Media, Inc., 2008. ISBN: 978-0-596-51613-0
182 Z. Fan, M. Yang, Y. Wu, et al. Efficient Optimal Kernel Placement for ReliableVisual Tracking. IEEE Computer Society Conference on Computer Vision andPattern Recognition. New York, NY, USA, 2006, 1:658–665
183 I. Guskov. Kernel-based Template Alignment. IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition. New York, NY, USA, 2006, 1:610–617
184 V. Parameswaran, V. Ramesh, I. Zoghlami. Tunable Kernels for Tracking. IEEEComputer Society Conference on Computer Vision and Pattern Recognition. NewYork, NY, USA, 2006, 2:2179–2186
185 A. Yilmaz. Object Tracking by Asymmetric Kernel Mean Shift with AutomaticScale and Orientation Selection. IEEE Computer Society Conference on ComputerVision and Pattern Recognition. Minneapolis, Minnesota, USA, 2007:1–6
186 C. J. Needham, R. D. Boyle. Performance Evaluation Metrics and Statistics forPositional Tracker Evaluation. International Conference on Computer Vision Sys-tems. Graz, Austria, 2003, 2626:278–289