人体目标的跨视域识别
|
摘要
随着摄像机的普及和人工智能的发展，视频监控系统被越来越广泛地用于各种场合。由于单个摄像机视域是非常有限的，很多监控系统使用多个视域不重叠的摄像机以监控更广阔的区域，因此，在摄像机网络中对人体目标进行跟踪成为了监控领域的重要研究课题。
单摄像机跟踪算法仅对单个视域内的人体目标进行跟踪，要在多个视域互不重叠的摄像机构建的网络中对人体目标进行跟踪，必须把同一个人在不同视域中的轨迹关联起来，这一关联的过程即跨视域识别。但由于人的外观在不同的视角、不同的光照强度下存在极大的差异，这些差异对跨视域识别提出了极大的挑战。针对这些挑战，本文给出解决方案。本文的创新点和贡献如下：
（1）本文阐述了跨视域识别的三种不同的框架以及与之对应的评估方法，这三种框架分别对应于三种不同的情形：1）表观数据库不存在；2）表观数据库存在但不完整；3）表观数据库存在且完整。
（2）本文提出了模糊空间颜色直方图，并把它作为表观特征进行跨视域识别。实验证明该特征在跨视域识别中的准确度能够媲美领域内公认的优秀特征，且计算效率显著优于后者，能够应用于实时场合。本文使用相关性度量作为表观相似度的度量方法。确定了表观特征和相似度的度量方法，无论表观数据库是否存在，系统都可进行最基本的跨视域识别。
（3）本文提出了在无重叠视域摄像机网络中表观数据库的学习方法，并把学得的表观数据库用于跨视域识别。因为学得的表观数据库包含了每个人在不同视域、不同角度下的表观模型，因此把该表观数据库应用于跨视域识别，很好地解决了视角的变化和不同视域间光照的差异给跨视域识别带来的挑战。
（4）本文综合了特征提取、表观数据库的学习和跨视域识别算法，构建了跨视域识别系统。该系统能够在无重叠视域摄像机网络中对人体目标进行跨视域识别。实验表明，该系统取得了较高的跨视域识别正确率。
With the mass production of the cameras and development in artificialintelligence, video surveillance becomes popular in our daily life. As onecamera can only cover a limited field of view (FoV), multiple cameras aredeployed, composing a camera network with non-overlapped FoV. Trackinga person in such a camera network becomes an imperative task for the scien-tist in this area.
Traditional tracking algorithm focuses on intra-camera tracking. Totrack people across the camera, person re-identification technique is needed.It is a process that associates different instances of the same person in differ-ent cameras and different times. It is critical, yet challenging, because theappearance of a person varies significantly in different viewpoints and dif-ferent light conditions. This dissertation provides the solutions to these chal-lenges. The following is the innovations and contributions of this disserta-tion:
(1) This dissertation has stated clearly the re-identification frameworkand the evaluation method are different in three conditions:1) the gallery ofpersons is absent;2) the gallery is available but not complete;3) the full gal-lery is available.
(2) This dissertation develops a feature, Fuzzy Space Color Histogram,for person re-identification purpose. The results of the experiments verifythat the performance of this feature is comparable to the state of art feature inperson re-identification, and with much lower computational cost. The over-all re-identification system can run in real time. The correlation is used as themetric of the appearance similarity. With the feature and similarity metric,the elementary re-identification system can be built, no matter whether thegallery is available or not.
(3) This dissertation proposes the offline and online methods for learn-ing a gallery of persons who frequently appear in the camera network. Thegallery contains appearance models of these persons consisting of appearancefeatures of the person from each camera and viewpoint. Given the cameraidentity, viewpoint identity, person identity, the model is decided. Since theseappearance models are specific to each camera and viewpoint, the problemsof viewpoint variations and illumination variations between cameras are ex-plicitly solved. Experiments demonstrate that the framework provides signif- icant improvement in addressing the re-identification problem.
(4) This dissertation presents a re-identification system that includes thefeature extraction module, the gallery learning module and there-identification module. Experiments demonstrate the high performance ofthis system in addressing the re-identification problem.
单摄像机跟踪算法仅对单个视域内的人体目标进行跟踪，要在多个视域互不重叠的摄像机构建的网络中对人体目标进行跟踪，必须把同一个人在不同视域中的轨迹关联起来，这一关联的过程即跨视域识别。但由于人的外观在不同的视角、不同的光照强度下存在极大的差异，这些差异对跨视域识别提出了极大的挑战。针对这些挑战，本文给出解决方案。本文的创新点和贡献如下：
（1）本文阐述了跨视域识别的三种不同的框架以及与之对应的评估方法，这三种框架分别对应于三种不同的情形：1）表观数据库不存在；2）表观数据库存在但不完整；3）表观数据库存在且完整。
（2）本文提出了模糊空间颜色直方图，并把它作为表观特征进行跨视域识别。实验证明该特征在跨视域识别中的准确度能够媲美领域内公认的优秀特征，且计算效率显著优于后者，能够应用于实时场合。本文使用相关性度量作为表观相似度的度量方法。确定了表观特征和相似度的度量方法，无论表观数据库是否存在，系统都可进行最基本的跨视域识别。
（3）本文提出了在无重叠视域摄像机网络中表观数据库的学习方法，并把学得的表观数据库用于跨视域识别。因为学得的表观数据库包含了每个人在不同视域、不同角度下的表观模型，因此把该表观数据库应用于跨视域识别，很好地解决了视角的变化和不同视域间光照的差异给跨视域识别带来的挑战。
（4）本文综合了特征提取、表观数据库的学习和跨视域识别算法，构建了跨视域识别系统。该系统能够在无重叠视域摄像机网络中对人体目标进行跨视域识别。实验表明，该系统取得了较高的跨视域识别正确率。
With the mass production of the cameras and development in artificialintelligence, video surveillance becomes popular in our daily life. As onecamera can only cover a limited field of view (FoV), multiple cameras aredeployed, composing a camera network with non-overlapped FoV. Trackinga person in such a camera network becomes an imperative task for the scien-tist in this area.
Traditional tracking algorithm focuses on intra-camera tracking. Totrack people across the camera, person re-identification technique is needed.It is a process that associates different instances of the same person in differ-ent cameras and different times. It is critical, yet challenging, because theappearance of a person varies significantly in different viewpoints and dif-ferent light conditions. This dissertation provides the solutions to these chal-lenges. The following is the innovations and contributions of this disserta-tion:
(1) This dissertation has stated clearly the re-identification frameworkand the evaluation method are different in three conditions:1) the gallery ofpersons is absent;2) the gallery is available but not complete;3) the full gal-lery is available.
(2) This dissertation develops a feature, Fuzzy Space Color Histogram,for person re-identification purpose. The results of the experiments verifythat the performance of this feature is comparable to the state of art feature inperson re-identification, and with much lower computational cost. The over-all re-identification system can run in real time. The correlation is used as themetric of the appearance similarity. With the feature and similarity metric,the elementary re-identification system can be built, no matter whether thegallery is available or not.
(3) This dissertation proposes the offline and online methods for learn-ing a gallery of persons who frequently appear in the camera network. Thegallery contains appearance models of these persons consisting of appearancefeatures of the person from each camera and viewpoint. Given the cameraidentity, viewpoint identity, person identity, the model is decided. Since theseappearance models are specific to each camera and viewpoint, the problemsof viewpoint variations and illumination variations between cameras are ex-plicitly solved. Experiments demonstrate that the framework provides signif- icant improvement in addressing the re-identification problem.
(4) This dissertation presents a re-identification system that includes thefeature extraction module, the gallery learning module and there-identification module. Experiments demonstrate the high performance ofthis system in addressing the re-identification problem.
引文
1. W. Hu, T. Tan, L. Wang, and S. Maybank,"A Survey on Visual Surveillance of ObjectMotion and Behaviors," IEEE Transaction on Systems, Man, Cybernatics, Part C, vol.34, pp.334-352,2004.
2. M. Valera and S. A. Velastin,"Intelligent Distributed Surveillance Systems: a review,"IEE Proceedings-Vision, Image and Signal Processing, vol.152, pp.192-204,2005.
3.孔庆杰，刘允才，“面向广域视频监控的无重叠视域多摄像机目标跟踪”2007年中国模式识别学术会议
4.徐剑,丁晓青,王生进,"基于目标存在概率场的多视角运动目标检测与对应算法,"自动化学报, vol.34, pp.609-612,2008.
5. F. Fleuret, J. Berclaz, R. Lengagne, and P. Fua,"Multicamera People Tracking with aProbabilistic Occupancy Map," IEEE Transaction on Pattern Analysis and MachineIntelligence, vol.30, pp.267-282,2008.
6. S. Calderara, R. Cucchiara, and A. Prati,"Bayesian-Competitive Consistent Labelingfor People Surveillance," IEEE Transaction on Pattern Analysis and MachineIntelligence, vol.30, pp.354-360,2008.
7. Q. Cai and J. K. Aggarwal,"Tracking Human Motion in Structured Environmentsusing a Distributed Camera System," IEEE Transaction on Pattern Analysis andMachine Intelligence, vol.21, pp.1241-1247,1999.
8. Y. Shan, H. S. Sawhney, and R. Kumar,"Unsupervised Learning of DiscriminativeEdge Measures for Vehicle Matching between Non-Overlapping Cameras," IEEEInternational Conference on Computer Vision and Pattern Recognition, San Diego,CA, USA,2005.
9. Y. Shan, H. S. Sawhney, and R. Kumar,"Vehicle Identification betweenNon-Overlapping Cameras without Direct Feature Matching," The10th IEEEInternational Conference on Computer Vision, Beijing, China,2005.
10. Y. Shan, H. S. Sawhney, and R. Kumar,"Unsupervised Learning of DiscriminativeEdge Measures for Vehicle Matching between Non-Overlapping Cameras," IEEETransaction on Pattern Analysis and Machine Intelligence, vol.30, pp.700-711,2008.
11. Y. Guo, S. Hsu, Y. Shan, H. Sawhney, and R. Kumar,"Vehicle Fingerprinting forReacquisition&Tracking in Videos," IEEE International Conference on ComputerVision and Pattern Recognition, San Diego, CA, USA,2005.
12. Y. Guo, H. S. Sawhney, R. Kumar, and S. Hsu,"Robust Object Matching forPersistent Tracking with Heterogeneous Features," Joint IEEE International Workshopon VS-PETS,2005.
13. Y. Guo, S. Hsu, H. S. Sawhney, R. Kumar, and Y. Shan,"Robust Object Matching forPersistent Tracking with Heterogeneous Features," IEEE Transaction on PatternAnalysis and Machine Intelligence, vol.29, pp.824-839,2007.
14. Y. Guo, Y. Shan, H. Sawhney, and R. Kumar,"PEET: Prototype Embedding andEmbedding Transition for Matching Vehicles over Disparate Viewpoints," IEEEConference on Computer Vision and Pattern Recognition, Minneapolis, Minnesota,USA,2007.
15. D. Gray, S. Brennan and H. Tao,"Evaluating Appearance Models for Recognition,Reacquisition, and Tracking," IEEE International Workshop on PerformanceEvaluation for Tracking and Surveillance,2007.
16. J. Huang, S. R. Kumar, M. Mitra, W. J. Zhu and R. Zabih,"Spatial Color Indexing andApplications," International Journal of Computer Vision, vol.35, pp.245–268,1999.
17. J. Huang, S. R. Kumar, M. Mitra, W. J. Zhu and R. Zabih,"Image Indexing UsingColor Correlograms," IEEE Conference on Computer Vision and Pattern Recognition,1997.
18. A. D’Angelo, J. Dugelay,"People re-identifcation in camera networks based onprobabilistic color histograms," in proceedings of the Electronic Imaging,2011.
19. E. D. Cheng, C. Madden, and M. Piccardi,"Mitigating the Effects of VariableIllumination for Tracking across Disjoint Camera Views," IEEE InternationalConference on advanced Video and Signal Based Surveillance, Sydney, NSW,Australia,2006.
20. E. D. Cheng and M. Piccardi,"Disjoint Track Matching Based on a Major ColorSpectrum Histogram Representation," Optical Engineering, vol.46, pp.1-14,2007.
21. C. Madden and M. Piccardi,"Height Measurement as a Session-based Biometric forPeople Matching Across Disjoint Camera Views," in proceedings of the Image andVision Computing, New Zealand,2005.
22. C. Madden, E. D. Cheng, and M. Piccardi,"Tracking People Across Disjoint CameraViews by an Illumination-tolerant Appearance Representation," Machine Vision andApplications, vol.18, pp.233-247,2007.
23. M. Bauml, K. Bernardin, M. Fischer, H. Ekenel and R. Stiefelhagen,"Multi-pose FaceRecognition for Person Retrieval in Camera Networks," IEEE InternationalConference on Advanced Video and Signal Based Surveillance,2010.
24. R. Bowden and P. Kaewtrakulpong,"Towards Automated Wide Area VisualSurveillance: Tracking Objects Between Spatially–separated, Uncalibrated Views,"IEE Proceedings-Vision, Image and Signal Processing, vol.152, pp.213-223,2005.
25. A. Gilbert and R. Bowden,"Incremental Modelling of the Posterior Distribution ofObjects for Inter and Intra Camera Tracking," British Machine Vision Conference,Oxford, UK,2005.
26. A. Gilbert and R. Bowden,"Tracking Objects across Cameras by IncrementallyLearning Inter-camera Colour Calibration and Patterns of Activity," The9th EuropeanConference Computer Vision, Graz, Austria,2006.
27. A. Gilbert and R. Bowden,"Incremental, Scalable Tracking of Objects inter Camera,"Computer Vision and Image Understanding, vol.111(1), pp.43-58,2008.
28. U. Park, A. K. Jain, I. Kitahara, K. Kogure, and N. Hagita,"ViSE: Visual SearchEngine Using Multiple Networked Cameras," The18th International Conference onPattern Recognition, Hong Kong, China,2006.
29. F. Porikli,"Inter-camera Color Calibration Using Cross-correlation Model Function,"IEEE International Conference on Image Processing, Barcelona, Spain,2003.
30. F. Porikli and A. Divakaran,"Multi-Camera Calibration, Object Tracking, and QueryGeneration," International Conference on Multimedia and Expo, Maryland, USA,2003.
31. O. Javed, Z. Rasheed, K. Shafique, and M. Shah,"Tracking Across Multiple CamerasWith Disjoint Views," The9th IEEE International Conference on Computer Vision,Nice, France,2003.
32. O. Javed, K. Shafique, and M. Shah,"Appearance Modeling for Tracking in MultipleNon-overlapping Cameras," IEEE Conference on Computer Vision and PatternRecognition, San Diego, CA, USA,2005.
33. O. Javed, K. Shafique, Z. Rasheed, and M. Shah,"Modeling Inter-camera Space-timeand Appearance Relationships for Tracking Across Non-overlapping Views,"Computer Vision and Image Understanding, vol.109, pp.146-162,2008.
34. K. Jeong and C. Jaynes,"Object Matching in Disjoint Cameras Using a ColorTransfer Approach," Machine Vision and Applications, vol.19(5-6), pp.443-455,2007.
35. Y. Cai, W. Chen, K. Huang, and T. Tan,"Continuously Tracking Objects AcrossMultiple Widely Separated Cameras," The8th Asian Conference on Computer Vision,Tokyo, Japan,2007.
36. D. Baltieri, R. Vezzani, and R. Cucchiara,"3D Body Model Construction andMatching for Real Time People Re-identification," Eurographics Italian ChapterConference, pp.65-71,2010.
37. D. Baltieri, R. Vezzani, and R. Cucchiara,"SARC3d: a New3D Body Model forPeople Tracking and Re-identifcation," International Conference on Image Analysisand Processing,2011.
38. W. S. Zheng, S. Gong, T. Xiang,"Person Re-identification by Probabilistic RelativeDistance Comparison," IEEE Conference on Computer Vision and PatternRecognition,2011.
39. N. Gheissari, T. B. Sebastian, P. H. Tu, and J. Rittscher,"Person ReidentificationUsing Spatiotemporal Appearance," IEEE Conference on Computer Vision andPattern Recognition New York, NY, USA,2006.
40. L. F. Teixeira and L. Corte-Real,"Video Object Matching across MultipleIndependent Views Using Local Descriptors and Adaptive Learning," PatternRecognition Letters, vol.30(2), pp.157-167,2009.
41. O. Hamdoun, F. Moutarde, B. Stanciulescu, B. Steux,"Person Re-identifcation inMulti-camera System by Signature Based on Interest Point Descriptors Collected onShort Video Sequences," ACM/IEEE International Conference on Distributed SmartCameras,2008.
42. I. Oliveira and J. Pio,"People Reidentifcation in a Camera Network," IEEEInternational Conference on Dependable, Autonomic and Secure Computing,2009.
43. A. Alahi, P. Vandergheynst, M. Bierlaire and M. Kunt,"Cascade of Descriptors toDetect and Track Objects across any Network of Cameras," Computer Vision andImage Understanding, vol.114, pp.624–640,2010.
44. L. Wang, T. Tan, H. Ning and W. Hu,"Silhouette Analysis-based Gait Recognition forHuman Identifcation," IEEE Transactions on Pattern Analysis and MachineIntelligence, vol.25, pp.1505–1518,2003.
45. L. Havasi, Z. Szlavik and T. Sziranyi,"Eigenwalks: Walk Detection and Biometricsfrom Symmetry Patterns," IEEE International Conference on Image Processing,2005.
46. Y. Yu, D. Harwood, K. Yoon, and L. S. Davis,"Human Appearance Modeling forMatching across Video Sequences," Machine Vision and Applications, vol.18, pp.139-149,2007.
47. K. A. Patwardhan, G. Sapiro, and V. Morellas,"A Graph-based ForegroundRepresentation and ITS Application in Example Based People Matching in Video,"IEEE International Conference on Image Processing, San Antonio, Texas, USA,2007.
48. X. Lv, Q. J. Kong, F. Weng, and Y. Liu,"Analysis of Appearance Features for HumanMatching between Different Fields of View," IEEE International Conference onMultimedia and Expo, pp.670-673,2009.
49.孔庆杰，吕晓威，李雄，刘允才，“不同场景图像中的人体目标匹配算法分析，”第四届和谐人机环境联合学术会议，2008。
50.吕晓威，孔庆杰，刘允才，“无重叠视域摄像机间人目标匹配的特征融合算法，”中国模式识别学术会议，2008。
51.吕晓威，“场景中人体运动跟踪与分析，”上海交通大学硕士学位论文，2009。
52. C. Madden and M. Piccardi,"A Framework for Track Matching Across DisjointCameras using Robust Shape and Appearance Features," IEEE InternationalConference on advanced Video and Signal Based Surveillance, London, U.K.,2007.
53. T. Gandhi and M. M. Trivedi,"Panoramic Appearance Map (PAM) for Multi-CameraBased Person Re-identification," IEEE International Conference on Advanced Videoand Signal based Surveillance, Sydney, NSW, Australia,2006.
54. T. Gandhi and M. M. Trivedi,"Person Tracking and Reidentification: IntroducingPanoramic Appearance Map (PAM) for Feature Representation," Machine Vision andApplications, vol.18, pp.207-220,2007.
55. D. Gray and H. Tao,"Viewpoint Invariant Pedestrian Recognition with an Ensembleof Localized Features," European Conference on Computer Vision,2008.
56. M. Farenzena, L. Bazzani, A. Perina, V. Murino, and M. Cristani,"PersonRe-identifcation by Symmetry-driven Accumulation of Local Features," IEEEConference on Computer Vision and Pattern Recognition,2010.
57. L. Bazzani, M. Cristani and V. Murino,"Symmetry-driven Accumulation of LocalFeatures for Human Characterization and Re-identification," Computer Vision andImage Understanding, accept,2013.
58. C. Motamed and O. Wallart,"A Temporal Fusion Strategy for Cross-camera DataAssociation," Pattern Recognition Letters, vol.28, pp.233-245,2007.
59. T. J. Ellis, D. Makris, and J. Black,"Learning a Multi-camera Topology," Joint IEEEInternational Workshop on VS-PETS, France,2003.
60. D. Makris, T. Ellis,"Automatic Learning of an Activity-based Semantic SceneModel," IEEE International Conference on Advanced Video and Signal BasedSurveillance,2003.
61. D. Makris, T. J. Ellis, and J. Black,"Bridging the Gaps between Cameras," IEEEConference on Computer Vision and Pattern Recognition Washington DC,2004.
62. J. Black, D. Makris, and T. Ellis,"Validation of Blind Region Learning and Tracking,"Joint IEEE International Workshop on VS-PETS, Beijing, China,2005.
63. K. Tieu, G. Dalley, and W. E. L. Grimson,"Inference of Non-Overlapping CameraNetwork Topology by Measuring Statistical Dependence," The10th IEEEInternational Conference on Computer Vision, Beijing, China,2005.
64. C. Niu and E. Grimson,"Recovering Non-overlapping Network Topology UsingFar-field Vehicle Tracking Data," The18th International Conference on PatternRecognition, Hong Kong, China,2006.
65. A. V. D. Hengel, A. Dick, and R. Hill,"Activity Topology Esimation for LargeNetworks of Cameras," IEEE International Conference on Advanced Video and SignalBased Surveillance, Sydney, NSW, Australia,2006.
66. K. W. Chen, C. C. Lai, Y. P. Hung, and C. S. Chen,"An Adaptive Learning Methodfor Target Tracking across Multiple Cameras," IEEE Conference on Computer Visionand Pattern Recognition,2008.
67. C. C. Loy, T. Xiang and S. Gong,"Time-delayed Correlation Analysis forMulti-camera Activity Understanding," International Journal of Computer Vision, vol.90, pp.106–129,2010.
68. C. C. Loy, T. Xiang, and S. Gong,"Multi-camera Activity Correlation Analysis,"IEEE Conference on Computer Vision and Pattern Recognition, pp.1988-1995,2009.
69. T. Huang and S. Russell,"Object Identification in a Bayesian Context," InternationalJoint Conference on Artificial Intelligence, Nagoya, Japan,1997.
70. T. Huang and S. Russell,"Object identification: A Bayesian Analysis with Applicationto Traffic Surveillance," Artificial Intelligence, vol.103, pp.1-17,1998.
71. V. Kettnaker and R. Zabih,"Bayesian Multi-camera Surveillance," IEEE InternationalConference on Computer Vision and Pattern Recognition, Ft. Collins, CO, USA,1999.
72. V. Kettnaker and R. Zabih,"Counting People from Multiple Cameras," InternationalConference on Multimedia Computing and Systems, Florence, Italy,1999.
73. H. Pasula, S. Russell, M. Ostland, and Y. Ritov,"Tracking Many Objects with ManySensors," The16th International Joint Conference on Artificial Intelligence,Stockholm, Sweden,1999.
74. T. Mensink, W. Zajdel, and B. Kruse,"Distributed EM Learning for AppearanceBased Multi-camera Tracking," The First ACM/IEEE International Conference onDistributed Smart Cameras, Vienna, Austria,2007.
75. A. Chilgunde, P. Kumar, S. Ranganath, and W. Huang,"Multi-Camera TargetTracking in Blind Regions of Cameras with Non-overlapping Fields of View," BritishMachine Vision Conference, London, UK,2004.
76. A. R. Dick and M. J. Brooks,"A Stochastic Approach to Tracking Objects acrossMultiple Cameras," The17th Australian Joint Conference on Artificial Intelligence,Cairns, Australia,2004.
77. A. Rahimi, B. Dunagan, and T. Darrell,"Simultaneous Calibration and Tracking witha Network of Non-Overlapping Sensors," IEEE Conference on Computer Vision andPattern Recognition, Washington DC,2004.
78. A. Rahimi, B. Dunagan, and T. Darrell,"Tracking People with a Sparse Network ofBearing Sensors," The8th European Conference on Computer Vision Prague, CzechRepublic,2004.
79. W. Leoputra, T. Tan, and F. L. Lim,"Non-overlapping Distributed Tracking usingParticle Filter," The18th International Conference on Pattern Recognition, HongKong, China,2006.
80. Y. R. Loke, P. Kumar, S. Ranganath, and W. M. Huang,"Object Matching acrossMultiple Non-overlapping Fields of View Using Fuzzy Logic," Acta AutomaticaSinica, vol.32, pp.978-987,2006.
81. B. Song and A. K. Roy-Chowdhury,"Stochastic Adaptive Tracking in a CameraNetwork," IEEE11th International Conference on Computer Vision, Rio de Janeiro,Brazil,2007.
82. E. Zheng, Q. Chen, X. Yang, Y. Liu,"Robust3D Modeling from Silhouette Cues,"IEEE Conference on Acoustics, Speech and Signal Processing,2009.
83. X. Ren and J. Malik,"Learning a Classification Model for Segmentation,"International Conference on Computer Vision,2003.
84. D. Comanicu and P. Meer,"Mean Shift: a Robust Approach toward Feature SpaceAnalysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.24,pp.603-619,2002.
85. A. Hervé and Lynne J. Williams,"Principal Component Analysis," WileyInterdisciplinary Reviews: Computational Statistics, vol.2(4), pp.433-459,2010.
86. I. T. Jolliffe,"Principal Component Analysis," Springer-Verlag, ISBN978-0-387-95442-4,1986.
87. W. Svante, K. Esbensen, and P. Geladi,"Principal Component Analysis,"Chemometrics and intelligent laboratory systems, vol.2(1), pp.37-52,1987.
88. M. E. Tipping and C. M. Bishop,"Probabilistic Principal Component Analysis,"Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol.61(3),pp.611-622.1999.
89. C. J. Burges,"A tutorial on support vector machines for pattern recognition," Datamining and knowledge discovery, vol.2(2), pp.121-167,1998.
90. M. A. Hearst, S. T. Dumais, E. Osman, J. Platt and B. Scholkopf,"Support VectorMachines," Intelligent Systems and their Applications, vol.13(4), pp.18-28,1998.
91. C. C. Chang, and C. J. Lin,"LIBSVM: a Library for Support Vector Machines," ACMTransactions on Intelligent Systems and Technology, vol.2(3), pp.27,2011.
92. P. Viola and M. Jones M,“Fast and Robust Classification Using AsymmetricAdaboost and a Detector Cascade,” in proceedings of the Neural InformationProcessing Systems, pp.1311-1318,2001.
93. R. Polikar,"A Tutorial Article on Ensemble Systems including Pseudocode, BlockDiagrams and Implementation Issues for AdaBoost and Other Ensemble LearningAlgorithms," IEEE Trans. Circuits and Systems Magazine, vol.6(3), pp.21-45,2006.
94. Y. Freund, S. Robert, and N. Abe,"A Short Introduction to Boosting,"Journal-Japanese Society For Artificial Intelligence, vol.14, pp.771-780,1999.
95. D. G. Lowe,"Object Recognition from Local Scale-invariant Features," IEEEInternational Conference on Computer Vision, vol.2, pp.1150-1157,1999.
96. H. Bay, A. Ess, T. Tuytelaars and L. V. Gool,"SURF: Speeded Up Robust Features,"Computer Vision and Image Understanding, vol.110(3), pp.346-359,2008.
97. P. T. Higgins,"An Overview of Biometrics," Retrieved January, vol.2, pp.2006,2003.
98. C. D. Brown and H. T. Davis,"Receiver Operating Characteristics Curves and RelatedDecision Measures: a tutorial," Chemometrics and Intelligent Laboratory Systems, vol.80(1), pp.24-38,2006.
99. K. H. Zou, A. J. O'Malley, and L. Mauri,"Receiver-operating Characteristic Analysisfor Evaluating Diagnostic Tests and Predictive Models," Circulation, vol.115(5), pp.654-657,2007.
100.Z. Zivkovic,"Improved Adaptive Gaussian Mixture Model for BackgroundSubtraction," IEEE International Conference on Pattern Recognition, vol.2, pp.28-31,2004.
101.C. Stauffer, W. E. L Grimson,"Adaptive Background Mixture Models for Real-timeTracking," IEEE Conference on Computer Vision and Pattern Recognition,1999.
102.A. P. Dempster, N. M. Laird, and D. B. Rubin,"Maximum Likelihood fromIncomplete Data via the EM Algorithm," Journal of the Royal Statistical Society.Series B (Methodological), pp.1-38,1977.
103.G. Arthur,"Single-Channel and Multichannel Finite-State Machines," IEEETransactions on Computers, vol.19(11), pp.1073-1078,1970.
104.F. Wagner,"Modeling Software with Finite State Machines: A Practical Approach,"Auerbach Publications, ISBN0-8493-8086-3,2006.
2. M. Valera and S. A. Velastin,"Intelligent Distributed Surveillance Systems: a review,"IEE Proceedings-Vision, Image and Signal Processing, vol.152, pp.192-204,2005.
3.孔庆杰，刘允才，“面向广域视频监控的无重叠视域多摄像机目标跟踪”2007年中国模式识别学术会议
4.徐剑,丁晓青,王生进,"基于目标存在概率场的多视角运动目标检测与对应算法,"自动化学报, vol.34, pp.609-612,2008.
5. F. Fleuret, J. Berclaz, R. Lengagne, and P. Fua,"Multicamera People Tracking with aProbabilistic Occupancy Map," IEEE Transaction on Pattern Analysis and MachineIntelligence, vol.30, pp.267-282,2008.
6. S. Calderara, R. Cucchiara, and A. Prati,"Bayesian-Competitive Consistent Labelingfor People Surveillance," IEEE Transaction on Pattern Analysis and MachineIntelligence, vol.30, pp.354-360,2008.
7. Q. Cai and J. K. Aggarwal,"Tracking Human Motion in Structured Environmentsusing a Distributed Camera System," IEEE Transaction on Pattern Analysis andMachine Intelligence, vol.21, pp.1241-1247,1999.
8. Y. Shan, H. S. Sawhney, and R. Kumar,"Unsupervised Learning of DiscriminativeEdge Measures for Vehicle Matching between Non-Overlapping Cameras," IEEEInternational Conference on Computer Vision and Pattern Recognition, San Diego,CA, USA,2005.
9. Y. Shan, H. S. Sawhney, and R. Kumar,"Vehicle Identification betweenNon-Overlapping Cameras without Direct Feature Matching," The10th IEEEInternational Conference on Computer Vision, Beijing, China,2005.
10. Y. Shan, H. S. Sawhney, and R. Kumar,"Unsupervised Learning of DiscriminativeEdge Measures for Vehicle Matching between Non-Overlapping Cameras," IEEETransaction on Pattern Analysis and Machine Intelligence, vol.30, pp.700-711,2008.
11. Y. Guo, S. Hsu, Y. Shan, H. Sawhney, and R. Kumar,"Vehicle Fingerprinting forReacquisition&Tracking in Videos," IEEE International Conference on ComputerVision and Pattern Recognition, San Diego, CA, USA,2005.
12. Y. Guo, H. S. Sawhney, R. Kumar, and S. Hsu,"Robust Object Matching forPersistent Tracking with Heterogeneous Features," Joint IEEE International Workshopon VS-PETS,2005.
13. Y. Guo, S. Hsu, H. S. Sawhney, R. Kumar, and Y. Shan,"Robust Object Matching forPersistent Tracking with Heterogeneous Features," IEEE Transaction on PatternAnalysis and Machine Intelligence, vol.29, pp.824-839,2007.
14. Y. Guo, Y. Shan, H. Sawhney, and R. Kumar,"PEET: Prototype Embedding andEmbedding Transition for Matching Vehicles over Disparate Viewpoints," IEEEConference on Computer Vision and Pattern Recognition, Minneapolis, Minnesota,USA,2007.
15. D. Gray, S. Brennan and H. Tao,"Evaluating Appearance Models for Recognition,Reacquisition, and Tracking," IEEE International Workshop on PerformanceEvaluation for Tracking and Surveillance,2007.
16. J. Huang, S. R. Kumar, M. Mitra, W. J. Zhu and R. Zabih,"Spatial Color Indexing andApplications," International Journal of Computer Vision, vol.35, pp.245–268,1999.
17. J. Huang, S. R. Kumar, M. Mitra, W. J. Zhu and R. Zabih,"Image Indexing UsingColor Correlograms," IEEE Conference on Computer Vision and Pattern Recognition,1997.
18. A. D’Angelo, J. Dugelay,"People re-identifcation in camera networks based onprobabilistic color histograms," in proceedings of the Electronic Imaging,2011.
19. E. D. Cheng, C. Madden, and M. Piccardi,"Mitigating the Effects of VariableIllumination for Tracking across Disjoint Camera Views," IEEE InternationalConference on advanced Video and Signal Based Surveillance, Sydney, NSW,Australia,2006.
20. E. D. Cheng and M. Piccardi,"Disjoint Track Matching Based on a Major ColorSpectrum Histogram Representation," Optical Engineering, vol.46, pp.1-14,2007.
21. C. Madden and M. Piccardi,"Height Measurement as a Session-based Biometric forPeople Matching Across Disjoint Camera Views," in proceedings of the Image andVision Computing, New Zealand,2005.
22. C. Madden, E. D. Cheng, and M. Piccardi,"Tracking People Across Disjoint CameraViews by an Illumination-tolerant Appearance Representation," Machine Vision andApplications, vol.18, pp.233-247,2007.
23. M. Bauml, K. Bernardin, M. Fischer, H. Ekenel and R. Stiefelhagen,"Multi-pose FaceRecognition for Person Retrieval in Camera Networks," IEEE InternationalConference on Advanced Video and Signal Based Surveillance,2010.
24. R. Bowden and P. Kaewtrakulpong,"Towards Automated Wide Area VisualSurveillance: Tracking Objects Between Spatially–separated, Uncalibrated Views,"IEE Proceedings-Vision, Image and Signal Processing, vol.152, pp.213-223,2005.
25. A. Gilbert and R. Bowden,"Incremental Modelling of the Posterior Distribution ofObjects for Inter and Intra Camera Tracking," British Machine Vision Conference,Oxford, UK,2005.
26. A. Gilbert and R. Bowden,"Tracking Objects across Cameras by IncrementallyLearning Inter-camera Colour Calibration and Patterns of Activity," The9th EuropeanConference Computer Vision, Graz, Austria,2006.
27. A. Gilbert and R. Bowden,"Incremental, Scalable Tracking of Objects inter Camera,"Computer Vision and Image Understanding, vol.111(1), pp.43-58,2008.
28. U. Park, A. K. Jain, I. Kitahara, K. Kogure, and N. Hagita,"ViSE: Visual SearchEngine Using Multiple Networked Cameras," The18th International Conference onPattern Recognition, Hong Kong, China,2006.
29. F. Porikli,"Inter-camera Color Calibration Using Cross-correlation Model Function,"IEEE International Conference on Image Processing, Barcelona, Spain,2003.
30. F. Porikli and A. Divakaran,"Multi-Camera Calibration, Object Tracking, and QueryGeneration," International Conference on Multimedia and Expo, Maryland, USA,2003.
31. O. Javed, Z. Rasheed, K. Shafique, and M. Shah,"Tracking Across Multiple CamerasWith Disjoint Views," The9th IEEE International Conference on Computer Vision,Nice, France,2003.
32. O. Javed, K. Shafique, and M. Shah,"Appearance Modeling for Tracking in MultipleNon-overlapping Cameras," IEEE Conference on Computer Vision and PatternRecognition, San Diego, CA, USA,2005.
33. O. Javed, K. Shafique, Z. Rasheed, and M. Shah,"Modeling Inter-camera Space-timeand Appearance Relationships for Tracking Across Non-overlapping Views,"Computer Vision and Image Understanding, vol.109, pp.146-162,2008.
34. K. Jeong and C. Jaynes,"Object Matching in Disjoint Cameras Using a ColorTransfer Approach," Machine Vision and Applications, vol.19(5-6), pp.443-455,2007.
35. Y. Cai, W. Chen, K. Huang, and T. Tan,"Continuously Tracking Objects AcrossMultiple Widely Separated Cameras," The8th Asian Conference on Computer Vision,Tokyo, Japan,2007.
36. D. Baltieri, R. Vezzani, and R. Cucchiara,"3D Body Model Construction andMatching for Real Time People Re-identification," Eurographics Italian ChapterConference, pp.65-71,2010.
37. D. Baltieri, R. Vezzani, and R. Cucchiara,"SARC3d: a New3D Body Model forPeople Tracking and Re-identifcation," International Conference on Image Analysisand Processing,2011.
38. W. S. Zheng, S. Gong, T. Xiang,"Person Re-identification by Probabilistic RelativeDistance Comparison," IEEE Conference on Computer Vision and PatternRecognition,2011.
39. N. Gheissari, T. B. Sebastian, P. H. Tu, and J. Rittscher,"Person ReidentificationUsing Spatiotemporal Appearance," IEEE Conference on Computer Vision andPattern Recognition New York, NY, USA,2006.
40. L. F. Teixeira and L. Corte-Real,"Video Object Matching across MultipleIndependent Views Using Local Descriptors and Adaptive Learning," PatternRecognition Letters, vol.30(2), pp.157-167,2009.
41. O. Hamdoun, F. Moutarde, B. Stanciulescu, B. Steux,"Person Re-identifcation inMulti-camera System by Signature Based on Interest Point Descriptors Collected onShort Video Sequences," ACM/IEEE International Conference on Distributed SmartCameras,2008.
42. I. Oliveira and J. Pio,"People Reidentifcation in a Camera Network," IEEEInternational Conference on Dependable, Autonomic and Secure Computing,2009.
43. A. Alahi, P. Vandergheynst, M. Bierlaire and M. Kunt,"Cascade of Descriptors toDetect and Track Objects across any Network of Cameras," Computer Vision andImage Understanding, vol.114, pp.624–640,2010.
44. L. Wang, T. Tan, H. Ning and W. Hu,"Silhouette Analysis-based Gait Recognition forHuman Identifcation," IEEE Transactions on Pattern Analysis and MachineIntelligence, vol.25, pp.1505–1518,2003.
45. L. Havasi, Z. Szlavik and T. Sziranyi,"Eigenwalks: Walk Detection and Biometricsfrom Symmetry Patterns," IEEE International Conference on Image Processing,2005.
46. Y. Yu, D. Harwood, K. Yoon, and L. S. Davis,"Human Appearance Modeling forMatching across Video Sequences," Machine Vision and Applications, vol.18, pp.139-149,2007.
47. K. A. Patwardhan, G. Sapiro, and V. Morellas,"A Graph-based ForegroundRepresentation and ITS Application in Example Based People Matching in Video,"IEEE International Conference on Image Processing, San Antonio, Texas, USA,2007.
48. X. Lv, Q. J. Kong, F. Weng, and Y. Liu,"Analysis of Appearance Features for HumanMatching between Different Fields of View," IEEE International Conference onMultimedia and Expo, pp.670-673,2009.
49.孔庆杰，吕晓威，李雄，刘允才，“不同场景图像中的人体目标匹配算法分析，”第四届和谐人机环境联合学术会议，2008。
50.吕晓威，孔庆杰，刘允才，“无重叠视域摄像机间人目标匹配的特征融合算法，”中国模式识别学术会议，2008。
51.吕晓威，“场景中人体运动跟踪与分析，”上海交通大学硕士学位论文，2009。
52. C. Madden and M. Piccardi,"A Framework for Track Matching Across DisjointCameras using Robust Shape and Appearance Features," IEEE InternationalConference on advanced Video and Signal Based Surveillance, London, U.K.,2007.
53. T. Gandhi and M. M. Trivedi,"Panoramic Appearance Map (PAM) for Multi-CameraBased Person Re-identification," IEEE International Conference on Advanced Videoand Signal based Surveillance, Sydney, NSW, Australia,2006.
54. T. Gandhi and M. M. Trivedi,"Person Tracking and Reidentification: IntroducingPanoramic Appearance Map (PAM) for Feature Representation," Machine Vision andApplications, vol.18, pp.207-220,2007.
55. D. Gray and H. Tao,"Viewpoint Invariant Pedestrian Recognition with an Ensembleof Localized Features," European Conference on Computer Vision,2008.
56. M. Farenzena, L. Bazzani, A. Perina, V. Murino, and M. Cristani,"PersonRe-identifcation by Symmetry-driven Accumulation of Local Features," IEEEConference on Computer Vision and Pattern Recognition,2010.
57. L. Bazzani, M. Cristani and V. Murino,"Symmetry-driven Accumulation of LocalFeatures for Human Characterization and Re-identification," Computer Vision andImage Understanding, accept,2013.
58. C. Motamed and O. Wallart,"A Temporal Fusion Strategy for Cross-camera DataAssociation," Pattern Recognition Letters, vol.28, pp.233-245,2007.
59. T. J. Ellis, D. Makris, and J. Black,"Learning a Multi-camera Topology," Joint IEEEInternational Workshop on VS-PETS, France,2003.
60. D. Makris, T. Ellis,"Automatic Learning of an Activity-based Semantic SceneModel," IEEE International Conference on Advanced Video and Signal BasedSurveillance,2003.
61. D. Makris, T. J. Ellis, and J. Black,"Bridging the Gaps between Cameras," IEEEConference on Computer Vision and Pattern Recognition Washington DC,2004.
62. J. Black, D. Makris, and T. Ellis,"Validation of Blind Region Learning and Tracking,"Joint IEEE International Workshop on VS-PETS, Beijing, China,2005.
63. K. Tieu, G. Dalley, and W. E. L. Grimson,"Inference of Non-Overlapping CameraNetwork Topology by Measuring Statistical Dependence," The10th IEEEInternational Conference on Computer Vision, Beijing, China,2005.
64. C. Niu and E. Grimson,"Recovering Non-overlapping Network Topology UsingFar-field Vehicle Tracking Data," The18th International Conference on PatternRecognition, Hong Kong, China,2006.
65. A. V. D. Hengel, A. Dick, and R. Hill,"Activity Topology Esimation for LargeNetworks of Cameras," IEEE International Conference on Advanced Video and SignalBased Surveillance, Sydney, NSW, Australia,2006.
66. K. W. Chen, C. C. Lai, Y. P. Hung, and C. S. Chen,"An Adaptive Learning Methodfor Target Tracking across Multiple Cameras," IEEE Conference on Computer Visionand Pattern Recognition,2008.
67. C. C. Loy, T. Xiang and S. Gong,"Time-delayed Correlation Analysis forMulti-camera Activity Understanding," International Journal of Computer Vision, vol.90, pp.106–129,2010.
68. C. C. Loy, T. Xiang, and S. Gong,"Multi-camera Activity Correlation Analysis,"IEEE Conference on Computer Vision and Pattern Recognition, pp.1988-1995,2009.
69. T. Huang and S. Russell,"Object Identification in a Bayesian Context," InternationalJoint Conference on Artificial Intelligence, Nagoya, Japan,1997.
70. T. Huang and S. Russell,"Object identification: A Bayesian Analysis with Applicationto Traffic Surveillance," Artificial Intelligence, vol.103, pp.1-17,1998.
71. V. Kettnaker and R. Zabih,"Bayesian Multi-camera Surveillance," IEEE InternationalConference on Computer Vision and Pattern Recognition, Ft. Collins, CO, USA,1999.
72. V. Kettnaker and R. Zabih,"Counting People from Multiple Cameras," InternationalConference on Multimedia Computing and Systems, Florence, Italy,1999.
73. H. Pasula, S. Russell, M. Ostland, and Y. Ritov,"Tracking Many Objects with ManySensors," The16th International Joint Conference on Artificial Intelligence,Stockholm, Sweden,1999.
74. T. Mensink, W. Zajdel, and B. Kruse,"Distributed EM Learning for AppearanceBased Multi-camera Tracking," The First ACM/IEEE International Conference onDistributed Smart Cameras, Vienna, Austria,2007.
75. A. Chilgunde, P. Kumar, S. Ranganath, and W. Huang,"Multi-Camera TargetTracking in Blind Regions of Cameras with Non-overlapping Fields of View," BritishMachine Vision Conference, London, UK,2004.
76. A. R. Dick and M. J. Brooks,"A Stochastic Approach to Tracking Objects acrossMultiple Cameras," The17th Australian Joint Conference on Artificial Intelligence,Cairns, Australia,2004.
77. A. Rahimi, B. Dunagan, and T. Darrell,"Simultaneous Calibration and Tracking witha Network of Non-Overlapping Sensors," IEEE Conference on Computer Vision andPattern Recognition, Washington DC,2004.
78. A. Rahimi, B. Dunagan, and T. Darrell,"Tracking People with a Sparse Network ofBearing Sensors," The8th European Conference on Computer Vision Prague, CzechRepublic,2004.
79. W. Leoputra, T. Tan, and F. L. Lim,"Non-overlapping Distributed Tracking usingParticle Filter," The18th International Conference on Pattern Recognition, HongKong, China,2006.
80. Y. R. Loke, P. Kumar, S. Ranganath, and W. M. Huang,"Object Matching acrossMultiple Non-overlapping Fields of View Using Fuzzy Logic," Acta AutomaticaSinica, vol.32, pp.978-987,2006.
81. B. Song and A. K. Roy-Chowdhury,"Stochastic Adaptive Tracking in a CameraNetwork," IEEE11th International Conference on Computer Vision, Rio de Janeiro,Brazil,2007.
82. E. Zheng, Q. Chen, X. Yang, Y. Liu,"Robust3D Modeling from Silhouette Cues,"IEEE Conference on Acoustics, Speech and Signal Processing,2009.
83. X. Ren and J. Malik,"Learning a Classification Model for Segmentation,"International Conference on Computer Vision,2003.
84. D. Comanicu and P. Meer,"Mean Shift: a Robust Approach toward Feature SpaceAnalysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.24,pp.603-619,2002.
85. A. Hervé and Lynne J. Williams,"Principal Component Analysis," WileyInterdisciplinary Reviews: Computational Statistics, vol.2(4), pp.433-459,2010.
86. I. T. Jolliffe,"Principal Component Analysis," Springer-Verlag, ISBN978-0-387-95442-4,1986.
87. W. Svante, K. Esbensen, and P. Geladi,"Principal Component Analysis,"Chemometrics and intelligent laboratory systems, vol.2(1), pp.37-52,1987.
88. M. E. Tipping and C. M. Bishop,"Probabilistic Principal Component Analysis,"Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol.61(3),pp.611-622.1999.
89. C. J. Burges,"A tutorial on support vector machines for pattern recognition," Datamining and knowledge discovery, vol.2(2), pp.121-167,1998.
90. M. A. Hearst, S. T. Dumais, E. Osman, J. Platt and B. Scholkopf,"Support VectorMachines," Intelligent Systems and their Applications, vol.13(4), pp.18-28,1998.
91. C. C. Chang, and C. J. Lin,"LIBSVM: a Library for Support Vector Machines," ACMTransactions on Intelligent Systems and Technology, vol.2(3), pp.27,2011.
92. P. Viola and M. Jones M,“Fast and Robust Classification Using AsymmetricAdaboost and a Detector Cascade,” in proceedings of the Neural InformationProcessing Systems, pp.1311-1318,2001.
93. R. Polikar,"A Tutorial Article on Ensemble Systems including Pseudocode, BlockDiagrams and Implementation Issues for AdaBoost and Other Ensemble LearningAlgorithms," IEEE Trans. Circuits and Systems Magazine, vol.6(3), pp.21-45,2006.
94. Y. Freund, S. Robert, and N. Abe,"A Short Introduction to Boosting,"Journal-Japanese Society For Artificial Intelligence, vol.14, pp.771-780,1999.
95. D. G. Lowe,"Object Recognition from Local Scale-invariant Features," IEEEInternational Conference on Computer Vision, vol.2, pp.1150-1157,1999.
96. H. Bay, A. Ess, T. Tuytelaars and L. V. Gool,"SURF: Speeded Up Robust Features,"Computer Vision and Image Understanding, vol.110(3), pp.346-359,2008.
97. P. T. Higgins,"An Overview of Biometrics," Retrieved January, vol.2, pp.2006,2003.
98. C. D. Brown and H. T. Davis,"Receiver Operating Characteristics Curves and RelatedDecision Measures: a tutorial," Chemometrics and Intelligent Laboratory Systems, vol.80(1), pp.24-38,2006.
99. K. H. Zou, A. J. O'Malley, and L. Mauri,"Receiver-operating Characteristic Analysisfor Evaluating Diagnostic Tests and Predictive Models," Circulation, vol.115(5), pp.654-657,2007.
100.Z. Zivkovic,"Improved Adaptive Gaussian Mixture Model for BackgroundSubtraction," IEEE International Conference on Pattern Recognition, vol.2, pp.28-31,2004.
101.C. Stauffer, W. E. L Grimson,"Adaptive Background Mixture Models for Real-timeTracking," IEEE Conference on Computer Vision and Pattern Recognition,1999.
102.A. P. Dempster, N. M. Laird, and D. B. Rubin,"Maximum Likelihood fromIncomplete Data via the EM Algorithm," Journal of the Royal Statistical Society.Series B (Methodological), pp.1-38,1977.
103.G. Arthur,"Single-Channel and Multichannel Finite-State Machines," IEEETransactions on Computers, vol.19(11), pp.1073-1078,1970.
104.F. Wagner,"Modeling Software with Finite State Machines: A Practical Approach,"Auerbach Publications, ISBN0-8493-8086-3,2006.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |