智能视频监控中目标检测、跟踪和识别方法研究
|
摘要
随着视频监控需求的迅速增长、监控规模的日益扩大，现有技术手段和人力很难保证及时性和有效性，远远不能满足监控要求，因此对智能视频监控系统的需求变得越来越迫切。
智能视频监控是利用计算机视觉和图像处理的方法对将获取的图像序列进行运动检测、运动目标分类、运动目标跟踪以及对监视场景中目标行为进行理解与描述，进而为监控者提供有用的关键信息。目前，智能视频监控已得到国内外学者的广泛关注，并展开了深入研究。但由于智能视频监控涉及的学科广泛、面临问题和应用背景复杂，至今仍处于探索阶段。研究具有鲁棒性、高精度和实时性的智能视频分析算法是构建智能视频监控系统的关键，有着重要的理论意义和很高的实用价值。本文针对智能视频监控中的核心关键技术，包括：图像特征的选择，目标检测、目标跟踪与目标识别等，进行了系统深入的研究，主要工作及创新如下：
（1）针对现有约简算法抗噪性能较差问题，本文提出了一种具有抗噪性能的粗糙集近似约简算法，并将其引入到图像特征描述中。提出的近似约简算法通过放松对约简条件的限制，实现了约简过程中对噪声的抑制，使得约简后的特征更加精简。通过该约简算法，有效的实现了对SIFT特征的约简，去除了SIFT特征中的冗余信息，提高了基于SIFT特征匹配算法的效率和精度。
（2）针对红外视频图像的行人检测，提出了一种基于粗糙集和MB-LBP特征的快速行人检测算法。该算法通过搜索和合并图像中的关键点来分割感兴趣区域，提高了算法的效率；用MB-LBP特征来表示感兴趣区域，通过粗糙集近似约简算法对对MB-LBP特征降维，进一步提高了算法的检测速度和性能，适合实际应用中的快速处理。特别是，该算法对可见光视频图像的行人检测也适用，增强了算法的鲁棒性。
（3）针对视频跟踪中的非刚性特征匹配问题，提出了一种基于几何约束的约简SIFT特征非刚性匹配算法。该算法定义了以SIFT特征之间相似性为基础的匹配评价函数，评价函数中综合考虑了在匹配过程中特征点之间的几何距离约束、薄板样条非刚性几何变换约束以及匹配矩阵的熵值约束。在此基础上，通过把图像特征点集匹配转化为评价函数优化问题，并通过确定性退火的迭代寻优方法对问题进行求解，在每次迭代中直接求解特征之间的匹配与变换关系，获取问题的最优匹配结果。在此匹配算法基础上，提出了基于约简SIFT特征的非刚性目标跟踪方案，通过与目标运动估计的结合，较好地解决了基于特征的跟踪方法中存在的目标特征选择、描述、匹配，以及跟踪过程中目标部分遮挡及短时间完全遮挡问题。
（4）针对智能视频监控中的目标识别问题，提出了一种面向识别的特征集网络目标建模方法。该方法以不变局部特征为基础，首先构建描述目标的目标特征集，然后以目标特征集为网络节点，以特征集之间的相似性为节点连接线建立目标特征集网络。该特征集网络模型有效地描述了在不同状态和成像条件下目标的特征，实现了对同一类训练图像目标进行聚类，进而形成目标特征集网络树；此外，特征集网络模型还能够增量地对新目标进行训练学习，为准确的目标识别提供支持。为解决目标特征集网络训练与识别过程中存在的大规模图像目标检索问题，本文利用基于RSOM聚类树的方法对图像目标特征进行聚类以及增量的学习训练，通过目标特征在聚类树中检索，进而快速地得到与目标特征集匹配的候选目标特征集，实现了大规模图像目标条件下的快速检索与目标识别。
With the rapid growth of video surveillance requirements and the extension ofsurveillance area day by day, current technical method and manpower are difficult toguarantee the promptness and effectiveness of surveillance, and can't meet the needs ofsurveillance. Therefore the demand for intelligent video surveillance system becomesmore and more urgent.
Intelligent video surveillance (IVS) is to use computer vision and image processingtechniques to obtain the image sequence of motion detection, moving targetclassification, moving object tracking and monitoring the scene for the understandingand description of target behavior, and thus provides usefull and key information formonitors. At present, the intelligent video surveillance has been widespread concern ofscholars, and been launched an in-depth study. However, it is still in the phase ofexploration for the wide range of scientific subjects IVS involves, and the comlexproblems and application backgrounds IVS meets.It is a key point of the IVS systemthat researching for robust，precise, real-time and intelligent video content analysisalgorithms, which has important theory significance and application value. In thiscontext, we focus our attention on the key technologies of IVS, such as selection ofimage features, object detection, object tracking and recognition. The main work andinnovation in the thesis are as follows:
(1) Considering the noise in information systems, we propose an approximateattribute reduction algorithms which can be used to deal with noise by loosening theconditions of reduction. The proposed approximate attribute reduction algorithm candelete the Information redundancy in SIFT features, and thus improve the effciency andaccuracy of matching algorithm.
(2) A robust pedestrian detection algorithm in infrared imagery is presented. First,a keypoint sliding window searching strategy is introduced for candidate regionsgeneration, and thus the size of the sliding window searching space is thus reduceddramatically. Second, the multi-block LBP (MB-LBP) feature is used to represent thepedestrians. Considering the drawback of MB-LBP, that is lots of features, theapproximate attribute reduction algorithm is used to ruduct the information redundancyof MB-LBP. Finally, pedestrian detection is performed by SVM classifiers.Experimental results in various scenarios demonstrate the effectiveness and robustnessof the proposed method. Notice that the proposed algothm is also applied to pedestriandetection for visual images.
(3) An object tracking scheme based on reducted SIFT features is presented. Itcan solve the feature selection, description, matching, object part-occlusion and shorttime complete-occlusion problem in the feature-based tracking method. In the scheme, the reduct SIFT features are used to descript the object efficiently. Then, the non-rigidmatching is applied to tracking the moving object. At the same time, object movementestimation method is embed into the feature-based tracking frame to solve the objectpart-occlusion and short time complete-occlusion problem. The paper focus onnon-rigid feature matching problem, and a non-rigid reduct SIFT feature matchingalgorithm based on geometric constraint is proposed. A SIFT features’ similarity basedmatching evaluation function (MEF) is defined. The MEF jointly considers theconstraint about geometric distance between features, thin plate spline transformationbetween the feature sets, and the entropy of the matching matrix. Based on this, thealgorithm turns the non-rigid feature matching problem to a MEF optimization problem,and solves the problem by deterministic annealing iterative frame. In each iterative step,the algorithm directly computes the matching and transformation between the featuresets alternatively, and reaches the optimal matching result iteratively.
(4) An object feature-sets net (OFSN) modeling is proposed for object recognitionin intelligent video surveillance. In the method, local invariant feature based objectfeature-set (OFS) is constructed to describe the detected object in the image. Based onthis, the OFSN is constructed, OFS is the node of OFSN, and the similarity of the OFSsis the connecting line between the nodes. The OFSN model can effectively describe theobject at large imaging condition variety, can cluster training images of the same classautomatically into an OFSN tree, and can incrementally train and study images of thenew classes. These provide strong supports for object recognition. At the same time, wealso studied how to use Recursive Self-Organizing Map (RSOM) clustering tree toincrementally train and study the image object features, which can apply for efficientlarge scale image objects retrieval for OFSN model’s training and recognition. Whilerecognizing an image object, we can quickly find the candidate OFS by feature retrievalin the RSOM clustering tree, which realize recognition in the large scale image dataset.
智能视频监控是利用计算机视觉和图像处理的方法对将获取的图像序列进行运动检测、运动目标分类、运动目标跟踪以及对监视场景中目标行为进行理解与描述，进而为监控者提供有用的关键信息。目前，智能视频监控已得到国内外学者的广泛关注，并展开了深入研究。但由于智能视频监控涉及的学科广泛、面临问题和应用背景复杂，至今仍处于探索阶段。研究具有鲁棒性、高精度和实时性的智能视频分析算法是构建智能视频监控系统的关键，有着重要的理论意义和很高的实用价值。本文针对智能视频监控中的核心关键技术，包括：图像特征的选择，目标检测、目标跟踪与目标识别等，进行了系统深入的研究，主要工作及创新如下：
（1）针对现有约简算法抗噪性能较差问题，本文提出了一种具有抗噪性能的粗糙集近似约简算法，并将其引入到图像特征描述中。提出的近似约简算法通过放松对约简条件的限制，实现了约简过程中对噪声的抑制，使得约简后的特征更加精简。通过该约简算法，有效的实现了对SIFT特征的约简，去除了SIFT特征中的冗余信息，提高了基于SIFT特征匹配算法的效率和精度。
（2）针对红外视频图像的行人检测，提出了一种基于粗糙集和MB-LBP特征的快速行人检测算法。该算法通过搜索和合并图像中的关键点来分割感兴趣区域，提高了算法的效率；用MB-LBP特征来表示感兴趣区域，通过粗糙集近似约简算法对对MB-LBP特征降维，进一步提高了算法的检测速度和性能，适合实际应用中的快速处理。特别是，该算法对可见光视频图像的行人检测也适用，增强了算法的鲁棒性。
（3）针对视频跟踪中的非刚性特征匹配问题，提出了一种基于几何约束的约简SIFT特征非刚性匹配算法。该算法定义了以SIFT特征之间相似性为基础的匹配评价函数，评价函数中综合考虑了在匹配过程中特征点之间的几何距离约束、薄板样条非刚性几何变换约束以及匹配矩阵的熵值约束。在此基础上，通过把图像特征点集匹配转化为评价函数优化问题，并通过确定性退火的迭代寻优方法对问题进行求解，在每次迭代中直接求解特征之间的匹配与变换关系，获取问题的最优匹配结果。在此匹配算法基础上，提出了基于约简SIFT特征的非刚性目标跟踪方案，通过与目标运动估计的结合，较好地解决了基于特征的跟踪方法中存在的目标特征选择、描述、匹配，以及跟踪过程中目标部分遮挡及短时间完全遮挡问题。
（4）针对智能视频监控中的目标识别问题，提出了一种面向识别的特征集网络目标建模方法。该方法以不变局部特征为基础，首先构建描述目标的目标特征集，然后以目标特征集为网络节点，以特征集之间的相似性为节点连接线建立目标特征集网络。该特征集网络模型有效地描述了在不同状态和成像条件下目标的特征，实现了对同一类训练图像目标进行聚类，进而形成目标特征集网络树；此外，特征集网络模型还能够增量地对新目标进行训练学习，为准确的目标识别提供支持。为解决目标特征集网络训练与识别过程中存在的大规模图像目标检索问题，本文利用基于RSOM聚类树的方法对图像目标特征进行聚类以及增量的学习训练，通过目标特征在聚类树中检索，进而快速地得到与目标特征集匹配的候选目标特征集，实现了大规模图像目标条件下的快速检索与目标识别。
With the rapid growth of video surveillance requirements and the extension ofsurveillance area day by day, current technical method and manpower are difficult toguarantee the promptness and effectiveness of surveillance, and can't meet the needs ofsurveillance. Therefore the demand for intelligent video surveillance system becomesmore and more urgent.
Intelligent video surveillance (IVS) is to use computer vision and image processingtechniques to obtain the image sequence of motion detection, moving targetclassification, moving object tracking and monitoring the scene for the understandingand description of target behavior, and thus provides usefull and key information formonitors. At present, the intelligent video surveillance has been widespread concern ofscholars, and been launched an in-depth study. However, it is still in the phase ofexploration for the wide range of scientific subjects IVS involves, and the comlexproblems and application backgrounds IVS meets.It is a key point of the IVS systemthat researching for robust，precise, real-time and intelligent video content analysisalgorithms, which has important theory significance and application value. In thiscontext, we focus our attention on the key technologies of IVS, such as selection ofimage features, object detection, object tracking and recognition. The main work andinnovation in the thesis are as follows:
(1) Considering the noise in information systems, we propose an approximateattribute reduction algorithms which can be used to deal with noise by loosening theconditions of reduction. The proposed approximate attribute reduction algorithm candelete the Information redundancy in SIFT features, and thus improve the effciency andaccuracy of matching algorithm.
(2) A robust pedestrian detection algorithm in infrared imagery is presented. First,a keypoint sliding window searching strategy is introduced for candidate regionsgeneration, and thus the size of the sliding window searching space is thus reduceddramatically. Second, the multi-block LBP (MB-LBP) feature is used to represent thepedestrians. Considering the drawback of MB-LBP, that is lots of features, theapproximate attribute reduction algorithm is used to ruduct the information redundancyof MB-LBP. Finally, pedestrian detection is performed by SVM classifiers.Experimental results in various scenarios demonstrate the effectiveness and robustnessof the proposed method. Notice that the proposed algothm is also applied to pedestriandetection for visual images.
(3) An object tracking scheme based on reducted SIFT features is presented. Itcan solve the feature selection, description, matching, object part-occlusion and shorttime complete-occlusion problem in the feature-based tracking method. In the scheme, the reduct SIFT features are used to descript the object efficiently. Then, the non-rigidmatching is applied to tracking the moving object. At the same time, object movementestimation method is embed into the feature-based tracking frame to solve the objectpart-occlusion and short time complete-occlusion problem. The paper focus onnon-rigid feature matching problem, and a non-rigid reduct SIFT feature matchingalgorithm based on geometric constraint is proposed. A SIFT features’ similarity basedmatching evaluation function (MEF) is defined. The MEF jointly considers theconstraint about geometric distance between features, thin plate spline transformationbetween the feature sets, and the entropy of the matching matrix. Based on this, thealgorithm turns the non-rigid feature matching problem to a MEF optimization problem,and solves the problem by deterministic annealing iterative frame. In each iterative step,the algorithm directly computes the matching and transformation between the featuresets alternatively, and reaches the optimal matching result iteratively.
(4) An object feature-sets net (OFSN) modeling is proposed for object recognitionin intelligent video surveillance. In the method, local invariant feature based objectfeature-set (OFS) is constructed to describe the detected object in the image. Based onthis, the OFSN is constructed, OFS is the node of OFSN, and the similarity of the OFSsis the connecting line between the nodes. The OFSN model can effectively describe theobject at large imaging condition variety, can cluster training images of the same classautomatically into an OFSN tree, and can incrementally train and study images of thenew classes. These provide strong supports for object recognition. At the same time, wealso studied how to use Recursive Self-Organizing Map (RSOM) clustering tree toincrementally train and study the image object features, which can apply for efficientlarge scale image objects retrieval for OFSN model’s training and recognition. Whilerecognizing an image object, we can quickly find the candidate OFS by feature retrievalin the RSOM clustering tree, which realize recognition in the large scale image dataset.
引文
[1] Rumelhart D.E., Hintont G.E, Williams R.J. Learning representations byback-propagating errors[J]. Nature,1986,323(6088):533-536
[2]杨涛,李静,潘泉,等.基于场景模型与统计学习的鲁棒行人检测算法[J].自动化学报,2010:499-508
[3]南京网行通. ATM机/自助银行智能监控系统.
[4] Kreucher, Chris M., Kastella, Keith D., Hero III, Alfred O. Tracking multipletargets using a particle filter representation of the joint multitarget probabilitydensity[A]. Proceedings of SPIE,2003,5204,258-269
[5] Kim J. S., Yeom D. H., Joo Y. H. Fast and robust algorithm of tracking multiplemoving objects for intelligent video surveillance systems[J]. Consumer Electronics,IEEE Transactions on,2011,57(3):1165-1170
[6]万家兵,霍宏.智能视频监控中目标的检测与识别[M].上海:上海交通大学出版社,2010
[7]徐杨,吴成东,陈东岳.基于视频图像的交通事件自动检测算法综述[J].计算机应用研究,2011,28(4):1206-1210
[8]周永红.智能视频监控技术现状,应用及发展趋势的探讨[J].中国安防,2011,(3):38-43
[9]王素玉,沈兰荪.智能视觉监控技术研究进展[J].中国图象图形学报,2007,12(009):1505-1514
[10]梁笃国,张艳霞,郑泽民.网络视频监控技术及应用[M]:人民邮电出版社,2009
[11]罗世伟,左涛,邹开耀.视频监控系统原理及维护[M]:电子工业出版社,2010
[12] Collins R., Lipton A., Kanade T., et al. A system for video surveillance andmonitoring[A]. Citeseer,1999:25-29
[13] Kumar R., Sawhney H., Samarasekera S., et al. Aerial video surveillance andexploitation[J]. Proceedings of the IEEE,2001,89(10):1518-1539
[14] Collins R.T, Gross R., Shi J. Silhouette-based human identification from bodyshape and gait[A]. Published by the IEEE Computer Society,2002,0366
[15] ADVISOR–Annotated Digital Video for Intelligent Surveillance and OptimisedRetrieval. http://www-sop.inria.fr/orion/ADVISOR/
[16] Blauensteiner P., Kampel M. Visual surveillance of an airports apron-an overviewof the AVITRACK project[A]. In Digital imaging in media and education, annualworkshop of AAPR,2004
[17] Behan J. Keeffe D. The Development of an Autonomous Robotic Aid to Assist theDisabled and Elderly[A]. Bioengineering in Ireland, Limerick,2004:146-152
[18]赵旭东,刘鹏,唐降龙,刘家锋.一种适应户外光照变化的背景建模及目标检测方法[J].自动化学报,2011,37(8):915-922
[19] Gelgon M., Bouthemy P., Le Cadre J.P. Recovery of the trajectories of multiplemoving objects in an image sequence with a PMHT approach[J]. Image and VisionComputing,2005,23(1):19-31
[20] Li L., Leung M.K.H. Integrating intensity and texture differences for robust changedetection[J]. IEEE Transactions on Image Processing,2002,11(2):105-112
[21] Hue C., Le Cadre J.P, et al. Sequential Monte Carlo methods for multiple targettracking and data fusion[J]. Signal Processing, IEEE Transactions on,2002,50(2):309-325
[22] Karlsson R., Gustafsson F. Monte Carlo data association for multiple targettracking[A]. IEE,2001,11:13/1-13/5
[23] Iketani A., Kuno Y., Shimada N., et al. Real-time surveillance system detectingpersons in complex scenes[A]. Image Analysis and Processing,1999ProceedingsInternational Conference on,1999:1112-1115
[24] Chris S., Grimson W.E.L. Learning Patterns of Activity Using Real-Time Tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757
[25] Godsill S.J., Doucet A., West M. Monte Carlo smoothing for nonlinear timeseries[J]. Journal of the American Statistical Association,2004,99(465):156-168
[26] Gavrila D.M., Davis L.S.3-D model-based tracking of humans in action: amulti-view approach[A]. IEEE,1995:73-80
[27] Kettnaker V., Zabih R. Counting people from multiple cameras[A]. Published bythe IEEE Computer Society,1999:267-281
[28] Jain R., Nagel H. H. On the analysis of accumulative difference pictures fromimage sequences of real-world scenes[J]. IEEE Transactions Pattern Analysis andMachine Intelligence,1979,1(2):206-214
[29] Song H., Shi F. A real-time algorithm for moving objects detection in videoimages[A]. IEEE,2004,4105:4108-4111
[30] Thakoor N., Gao J. Automatic video object shape extraction and its classificationwith camera in motion[A]. Image Processing,2005ICIP2005IEEE InternationalConference on,2005:III-437-440
[31] Rajagopalan R., Orchard M.T., Brandt R.D. Motion field modeling for videosequences[J]. Image Processing, IEEE Transactions on,1997,6(11):1503-1516
[32]广田.基于视觉的行人检测和跟踪技术的研究[D].上海:上海交通大学,2007
[33]马燕.图像目标跟踪算法研究[D].西安:西安电子科技大学,2011
[34] Lin Z., Davis L.S., Doermann D., et al. Hierarchical part-template matching forhuman detection and segmentation[A].2007IEEE11th International Conferenceon Computer Vision,2007:1-8
[35] Jain A.K., Zhong Y., Lakshmanan S. Object matching using deformabletemplates[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1996,18(3):267-278
[36] Coughlan J., Yuille A., English C., et al. Efficient deformable template detectionand localization without user initialization[J]. Computer Vision and ImageUnderstanding,2000,78(3):303-319
[37]胡正平,杨建秀.稀疏活动轮廓扩展形状脚本模型目标检测算法[J].计算机科学与探索,2011,5(3):280-287
[38] Krattenthaler W., Mayer K.J., Zeiller M. Point correlation: a reduced-cost templatematching technique[A]. IEEE,1994,201:208-212
[39] Baro X., Escalera S., Vitrio J., et al. Traffic sign recognition using evolutionaryadaboost detection and forest-ECOC classification[J]. Intelligent TransportationSystems, IEEE Transactions on,2009,10(1):113-126
[40] Munder S., Gavrila D.M. An experimental study on pedestrian classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006:1863-1868
[41] Khammari A., Nashashibi F., Abramson Y., et al. Vehicle detection combininggradient analysis and AdaBoost classification[A]. Intelligent TransportationSystems,2005Proceedings2005IEEE,2005:66-71
[42] Dalal N., Triggs B., Histograms of oriented gradients for human detection[A].Computer Vision and Pattern Recognition,2005CVPR,2005:1213-1218
[43] Kim D.S., Nguyen H.N., Park J.S. Genetic algorithm to improve SVM basednetwork intrusion detection system[A]. IEEE,2005:1347-1352
[44] Chen W.H., Hsu S.H., Shen H.P. Application of SVM and ANN for intrusiondetection[J]. Computers&Operations Research,2005,32(10):2617-2634
[45] Wu Y., Yu T. A field model for human detection and tracking[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2006:753-765
[46] Wu Y., Yu T., Hua G. A statistical field model for pedestrian detection[A]. IEEE,2005,1021:1023-1030
[47]张秀伟,张艳宁,郭哲,等.可见光-热红外视频运动目标融合检测的研究进展及展望[J].红外与毫米波学报,2011,30(4):354-360
[48] E Jacobs C, A Finkelstein, H Salesin D. Fast multiresolution image querying[A].Computer Graphics Proceeding SIGGRAPH'95[A],1995:277-286
[49] Jwu-Sheng Hu, Chung-Wei Juan, Jyun-Ji Wang. A spatial-color mean-shift objecttracking algorithm with scale and orientation estimation[J]，Pattern RecognitionLetters，2008，29：2165-2173
[50] R Picard, A Pentland. Introduction to the special section on digitallibraries: representation and retrieval[J]. IEEE Trans on PAMI,1996:769-770
[51] R Smith J, F Chang S. VisualSEEK: a fully automated content-based image querysystem[A]. Proc ACM Multimedia,1996:87-89
[52] J Swain M, H Ballard B. Color Indexing[J]. International Joural of ComputerVision,1991,7(1):11-32
[53] J Hafer. Efficient Color Histogram for Quadratic Form Distance Functions[J].IEEE Trans on PAMI,1995,10(7):729-736
[54] O Balan A, J Black M. An adaptive appearance model approach for model-basedarticulated object tracking[A]. IEEE Computer Society Conference on CVPR,2006:758-765
[55] X Song, R Nevatia. A model-based vehicle segmentation method for tracking[A].Proc of10th IEEE International Conference on Computer Vision,2005:1124-1131
[56] T Zhao, R Nevatia, F Lv. Segmentation and tracking of multiple humans incomplex situations[A]. Proc of IEEE Computer Society Conference on CVPR,2001:194-201
[57] M Hu, W Hu, T Tan. Tracking people through occlusions[A]. Proc of17th ICPR,2004:724-727
[58] Malik, Jitendra, Russell, Stuart. Traffic Surveillance And Detection TechnologyDevelopment: New Traffic Sensor Technology Final Report,1997:97-102
[59] Wron, C.R., Azarbayejani, A., Darrell, T., et al. Pfinder: Real-time Tracking of theHuman Body[J]. IEEE Trans on PAMI,1997,19:780-785
[60]侯晴宇,张伟,武春风,等．改进的均值移位红外目标跟踪[J]．光学精密工程，2010,18(3):764-770
[61] Artur oza, Lyudmila Mihaylova, David Bull, et al. Structural Similarity-BasedObject Tracking in Multimodality Surveillance Videos[J]. Machine Vision andApplications.2009,20(2):71-83
[62] Isard M., Blake A. CONDENSATION-Conditional density propagation for visualtracking[J]. Intemational Journal of Computer Vision,1998,29(1):52-81
[63] Kilger M. A shadow handler in a video-based real-time traffic monitoringsystem[A]. in Proc of IEEE Workshop Applications of Computer Vision. PalmSprings, CA,1992:11-18
[64] Karaulova I A, Hall P M, Marshall A D. A hierarchical model of dynamics fortracking people with a single video camera[A]. Proceedings of British MachineVision Conference,2000:262-352
[65] Ju S, Black M, Yaccob Y. Cardboard people: a parameterized model of articulatedimage motion[A]. Proceedings of IEEE International Conference on AutomaticFace and Gesture Recognition,1996:38-44
[66] Niyogi S.A, Adelson E.H. Analyzing and recognizing walking figures in XYT[A].Proceedings of IEEE Conference on Computer Vision and PatternRecognition,1994:469-474
[67] YAO A.，WANG G.J.，LIN X.G.，et al．Kernel based articulated objecttracking with scale adaptation and model update[C]， IEEE InternationalConference on Acoustics，Speech and Signal Processing. Las Vegas, USA,2008:945—948
[68] Rohr K. Toward model-based recognition of human movements in imagesequences[J]. Image Understanding,1994:94-115
[69] Wachter S, Nagel H H. Tracking persons in monocular image sequences[J]. Visionand Image Understanding,1999,74(3):174-192
[70] Zhu Z., Xu G., Yang B, et al. VISATRAM:A real-time vision system for automatictraffic monitoring[J]. Image and Vision Computing2000,18(10):781-794
[71] Maggio E，Taj M，Cavallaro A. Efficient multi-target visual tracking usingrandom finite sets[J]. IEEE Transactions on Circuits and Systems for VideoTechnology，2008,18(8):1016-1027
[72] Julier S.J.，Uhlmann J.K. A New Extension of the Kalman Filter to NonlinearSystems[J]. Proceedings of the lth International Symposium on Aerospace/DefenseSensing，Simulation and Controls，1997:182-193
[73] Cortina E, Otero D, Attellis C.E．Maneuvering target tracking using extendedKalman filter[J]. IEEE Transactions on Aerospace and Electronic Systems,1991:155-158
[74] LAO Y, ZHU J, ZHENG Y. Sequential particle generation for visual tracking[J].IEEE Transactions on Circuits and Systems for Video Technology,2009,19(9):1365-1378
[75] PAN P, SCHONFILD D. Dynamic proposal variance and optimal particleallocation in particle filtering for video tracking[J]. IEEE Transaction on Circuitsand Systems for Video Technology,2008,18(9):1268-1279.
[76] BOUAYNAYA N，SCHONFELD D. On the optimality of motion-based particlefiltering[J]. IEEE Transactions on Circuits and Systems for Video Technology，2009,19(7):1068-1072.
[77] IOANNIS P, EDWIN H.R. Coupled prediction classification for robust visualtracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，2010,32(9):1553-1567
[78] SOTO D.A, REGAZZONI M C S. Bayesian tracking for video analytics[J]. IEEESignal Processing Magazine,2010,27(5):46-55
[79] Kass M, Witkin A, Terzopoulous D. Snakes: Active contour models[J].International Journal of Computer Vision,1987,1(4):321-331
[80] Paragios N, Deriche R. Geodesic active contours and level sets for the detectionand tracking of moving objects[J]. IEEE Transaction on PAMI,22:266-280
[81] Peterfreund N. Robust tracking of position and velocity with Kalman snakes[J].IEEE Transaction on PAMI,2000,22:564-569
[82] Isard M, Blake A. Contour tracking by stochastic propagation of conditionaldensity[A]. Proceedings of European Conference on Computer Vision,1996:343-356
[83] Kim W., Lee C.Y., Lee J.J. Tracking moving object using Snake's jump based onimage flow[J]. Mechatronics,2001,11(2):199-226
[84] Chen Q, Sun QS, Heng PA, et al.Two-Stage Object Tracking Method Based onKernel and Active Contour[J]. IEEE Transactions on Circuits and Systems forVideo Technology,2010,20(4):605-609
[85] Vard A R，Moallem P，Nilchi A R N．Texture-Based Parametric ActiveContour for Target Detection and Tracking[J]．International Journal of ImagingSystems and Technology,2009,19(3): l79-186
[86] Spengler M, Schiele B. Towards multi-cue integration for visual tracking[J].Machine Vision and Applications,2003,14(1):50-58
[87] Merwe R, Doucet A, Freitas N, et al. The unscented particle filter, technical reportCUED/F-INFENG/TR380. Engineering Department,Cambridge University,2000.
[88] Segen J, Pingali S. A camera-based system for tracking people in real time[A].Proc of International Conference on Pattern Recognition,1996:63-67
[89] Khan Z.H, Gui Y.H. Joint feature correspondences and appearance similarity forrobust visual object tracking[J]. IEEE Transactions on Information Forensics andSecurity,2010,5(3):591-606
[90] Jang D S, Choi H I. Active models for tracking moving objects[J]. PatternRecognition,2000,33(7):135-146
[91] YANG M, WU Y, HUA G. Context-aware visual tracking[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence,2009,31(7):1195-1209
[92] Cyr C, Kimia B.3D Object Recognition Using Similarity-based Aspect Graph.International Conference on Computer Vision,2001:254-261
[93] van de Sande, K.E.A., Gevers, T., Snoek, C.G.M. Evaluating color descriptors forobject and scene recognition[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence, in press,2010,32(9):1582-1596
[94] Selinger A, Nelson C.R. A Perceptual Grouping Hierarchy for Appearance-based3d Object Recognition[J]. Computer Vision and Image Understanding,1999,76(1):83-92
[95] Lowe D. Distinctive Image Features from Scale-invariant Keypoints[J].International Joural of Computer Vision,2004,60(2):91-110
[96] Mikolajczyk K, Schmid C. An Affine Invariant Interest Point Detector[A].European Conference on Computer Vision,2002:128-142
[97] Obrdzalek S, Matas J. Object Recognition Using Local Affine Frames onDistinguished Regions[A]. BMVC,2002:414-431
[98] Tuyelaars T, Van-Gool L. Wide Baseline Stereo Based on Local, AffinelyInvariant Regions [A], BMVC,2000
[99] Schaffalitzky F, Zisserman A. Automated Scene Maching in Movies. Workshop onContent-Based Image and Video Retrieval,2002:186-197
[100] Mikolajczyk K, Schmid C. Indexing Based on Scale-invariant Interest Points[A].International Conference on Computer Vision,2001:525-531
[101] Mikolajczyk K, Schmid C. Scale and affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86
[102] Csurka G., Dance C., Fan L., et al. Visual categorization with bags ofkeypoints[A]. Citeseer,2004:22-34
[103] L.-J. Guo, J.-Y. Zhao, and R. Zhang. A novel method to construct visualvocabulary based on maximization of mutual information. In Proceedings ofInternational Conference on Artificial Intelligence and ComputationalIntelligence[C],2009,3:123-127.
[104] van Gemert, J.C., Veenman, C.J., Smeulders, A.W.M., et al. Visual wordambiguity[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(7):1271-1283
[105] Weber M., Welling M., Perona P. Unsupervised learning of models forrecognition[J]. Computer Vision-ECCV2000,2000:18-32
[106] Fergus R, Perona P, Zisserman A. Object class recognition by unsupervisedscale-invariant learning[A]. Proceedings of IEEE Conference on ComputerVision and Pattern Recognition,2003:264-271
[107] Crandall D, Huttenlocher D. Weakly supervised learning of part-based spatialmodels for visual object recognition[A]. Proceedings of European Conference onComputer Vision,2006:16-29
[108] Zheng QF, Wen G. Constructing Visual Phrases for Effective and EfficientObject-Based Image Retrieval[J]. ACM Transactions on Multimedia Computing,Communications and Applications,2008,5(1),7:1-19
[109] Crandall D J, Felzenszwalb P, Huttenlocher D P. Spatial priors for part-basedrecognition using statistical models[A]. Proceedings of IEEE Conference onComputer Vision and Pattern Recognition,2005:10-17
[110] Fischler M, Elschlager R. The representation and matching of pictorialstructures[J]. IEEE Trans on Comp, c-22(1):67-92
[111] Burl M, Weber M, Perona P. A probabilistic approach to object recognition usinglocal photometry and global geometry[A]. Proceedings of European Conferenceon Computer Vision,1998:628-641
[112] Mikolajczyk K, Leibe B, Schiele B. Multiple object class detection with agenerative model[A]. Proceedings of IEEE Conference on Computer Vision andPattern Recognition,2006:26-36
[113] Leibe B, Schiele B. Interleaved object categorization and segmentation[A]. Procof British Machine Vision Conference,2003:759-768
[114] Fei-Fei L, Fergus R, Perona P. A bayesian approach to unsupervised one-shotlearning of object categories[A]. Proceedings of IEEE International Conferenceon Computer Vision,2003:1134-1139.
[115] Fergus R., Perona P., Zisserman A. A sparse object category model for efficientlearning and exhaustive recognition[A]. IEEE,2005,381:380-387
[116] Felzenszwalb P, Huttenlocher D. Pictorial structures for object recognition[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2000:2066-2073.
[117] Bouchard G, Triggs B. Hierarchical part-based visual object categorization[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2005:710-715
[118] Carneiro G, Lowe D G. Sparse flexible models of local features[A]. Proceedingsof European Conference on Computer Vision,2006:29-43
[119]孙浩,王程,王润生.局部不变特征综述[J].中国图象图形学报,2011,16(02):141-151
[120] Mikolajczyk K., Schmid C. A Performance Evaluation of Local Descriptors[J].IEEE Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630
[121]李蓉,周维柏.一种基于不变特征的图像匹配算法[J].华中师范大学学报：自然科学版,2010,44(1):38-42
[122]王鹏,王平,沈振康,等.一种基于sift的仿射不变特征提取新方法[J].信号处理,2011,27(1):88-93
[123] KeY. PCA-SIFT: a more distinctive representation for local image descriptors[J].CVPR,2004,2:506-513
[124]李伟,沈振康.基于KPCA-Sift描述符的图像配准[J].信号处理,2009,25(4):644-647
[125] Pawlak Z., Skowron A. Rudiments of rough sets[J]. Information Sciences,2007,177(1):3-27
[126] Thangavel K., Pethalakshmi A. Dimensionality reduction based on rough settheory: A review[J]. Appl Soft Comput,2009,9(1):1-12
[127] Pawlak Z. Rough Sets: Theoretical Aspects of Reasoning About Data[M]. London:Kluwer Academic Publisher,1991
[128]张文修,吴伟志,梁吉业,等.粗糙集理论与方法[M].北京:科学出版社,2001
[129]滕书华,昝德才,孙即祥,等.基于同可区分度的属性约简算法[J].模式识别与人工智能,2010,23(5):630-638
[130]滕书华.基于粗糙集理论的不确定性度量和属性约简方法研究[D].长沙:国防科学技术大学,2011:182-189
[131]王国胤.粗糙集理论与知识获取.西安:西安交通大学出版社,2001
[132]张文修,梁怡,吴伟志.信息系统与知识发现[M].北京:科学出版社,2003
[133]吴子特,叶东毅.一种可伸缩的快速属性约简算法[J].模式识别与人工智能,2009,22(2):234-239
[134]刘少辉,盛秋戬,吴斌,等. Rough集高效算法的研究[J].计算机学报,2003,26(5):524-529
[135]徐章艳,刘作鹏,杨炳儒,等.一个复杂度为max(O(|C||U|), O(|C|^2|U/C|))的快速属性约简算法[J].计算机学报,2006,29(3):391-399
[136]钱宇华,梁吉业,王锋.面向非完备决策表的正向近似特征选择加速算法[J].计算机学报,2011,34(3):435-442
[137]滕书华,孙即祥,周石琳,等.基于信息观点的约简算法比较[J].计算机科学,2011,38(1):259-263
[138] Li Fei, Yin Yunqiang. Approaches to knowledge reduction of covering decisionsystems based on information theory [J]. Information Sciences,2009,179(11):1694-1704
[139]颜艳,杨慧中.一种基于互信息的粗糙集知识约简算法[J].清华大学学报(自然科学版),2007,47(S2):1903-1906
[140]王国胤,于洪,杨大春.基于条件信息熵的决策表约简[J].计算机学报,2002,25(7):759-766
[141]苗夺谦,王珏.粗糙集理论中概念与运算的信息表示[J].软件学报,1999,10(2):113-116
[142]刘振华,刘三阳,王珏.基于信息量的一种属性约简算法[J].西安电子科技大学学报,2003,30(6):835-838
[143] Luo P., He Q., Shi Z.. Theoretical study on a new information entropy and its usein attribute reduction[J]. Cognitive Informatics,2005(ICCI2005) Fourth IEEEConference on,2005:73-79
[144] Slezak D. Approximate entropy reducts[J]. Fundam Inform,2002,53(3-4):365-390
[145]杨明,杨萍.垂直分布多决策表下基于条件信息熵的近似约简[J].控制与决策,2008,23(10):1103-1108
[146]祁立,刘玉树.基于条件信息量的快速粗集约简算法[J].北京理工大学学报,2007,27(7):604-608
[147]苗夺谦,王国胤,刘清,等.粒计算：过去、现在与展望[M].北京:科学出版社,2007
[148] Zhao Y., Yao Y. Y., Luo F. Data analysis based on discernibility andindiscernibility[J]. Information Sciences,2007,177(22):4959-4976
[149] Susmaga R. Reducts and constructs in attribute reduction[J]. Fundam Inform,2004,61(2):159-181
[150]苗夺谦,王珏.粗糙集理论中知识粗糙性与信息熵关系的讨论[J].模式识别与人工智能,1998,11(001):34-40
[151]杨明.决策表中基于条件信息熵的近似约简[J].电子学报,2007,35(11):2156-2160
[152]陈堂敏.基于区分能力大小的启发式约简算法的研究[J].计算机学报,2006,29(3):480-487
[153] Lindeberg Tony. Scale-Space for Discrete Signals[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1990,12(3):234-254
[154] Linderberg T. Junction Detection with Automatic Selection of Detection Scalesand Localization Scales [C]. IEEE International Conference on Image Processing,1994:924-928
[155] Xia SP, Ren P, Hancock R. Ranking the Local Invariant Features for the RobustVisual Saliencies[A]. International Conference on Pattern Recognition,2008
[156] Wojciech Ziarko. Variable precision rough set model[J]. Journal of Computer andSystem Sciences,1993,46(1):39-59
[157]刘建军,夏胜平,郁文贤.基于SIFT特征的两阶段procrustes迭代匹配算法[J].信号处理,2011,26(6):854-858
[158]孙涛,黄茜,刘军,等.基于局部二元模式特征的行人检测[J].计算机工程与设计,2011,(6):2119-2123
[159] Gandhi T., Trivedi M. M. Pedestrian Protection Systems: Issues, Survey, andChallenges[J]. Intelligent Transportation Systems, IEEE Transactions on,2007,8(3):413-430
[160]许言午,曹先彬,乔红.行人检测系统研究新进展及关键技术展望[J].电子学报,2008,36(5):962-968
[161]贾慧星,章毓晋.车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述[J].自动化学报,2007,33(1):84-90
[162] Enzweiler M., Gavrila D. M. Monocular Pedestrian Detection: Survey andExperiments[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2009,31(12):2179-2195
[163] Sabzmeydani P, Mori G. Detecting pedestrians by learning Shapelet features[C].IEEE Conference on Computer Vision and Pattern Recognition,2007:1-8
[164]李娟,邵春福,杨励雅.基于混合高斯模型的行人检测方法[J].吉林大学学报:工学版,2011,(1):41-45
[165] Wu B, Nevatia R. Detection of multiple partially occluded humans in a singleimage by bayesian combination of edgelet part detectors[C]. IEEE InternationalConference on Computer Vision,2005,1:90–97
[166] Dai C, Zheng Y, Li X. Layered represenation for pedestrian detection andtrakcing in infrared imagery[C]. IEEE Computer Society Conference onComputer Vision and Pattern Recognition,2005,1:13-20
[167] Yasuno M, Ryousuke S, Yasuda N, et al. Pedestrian detection and tracking in farinfrared images[C]. IEEE Conference on Intelligent Transportation Systems,2005:182-187
[168] Sun H, Wang C, Wang BL, et al. Pyramid binary pattern features for real-timepedestrian detection from infrared videos[J]. Neurocomputing,2011,74(5):797-804
[169]田广,戚飞虎.移动摄像机环境下基于特征变换和svm的分级行人检测算法[J].电子学报,2008,36(5):1024-1028
[170]胡春华,钱堃.基于角度泛化的SC模型匹配的行人检测[J].计算机工程,2010:234-241
[171]郭永彩,胡瑞光,高潮.红外图像中的行人检测[J].重庆大学学报：自然科学版,2009,32(9):1070-1073
[172] Liu Y, Chen X, Yao H, et al. Contour-motion feature (CMF): a space-timeapproach for robust pedestrian detection[J]. Pattern Recognition Letters,2009,30:148-156
[173] Gavrila D M. Multi-cue pedestrian detection and tracking from a movingvehicle[J]. International Journal of Computer Vision,2007,73(1):41-59
[174] Xu F, Liu X, Fujimura K. Pedestrian detection and tracking with night vision[J].IEEE Transactions on Intelligent Transportation Systems,2005,6(1):63-71
[175] Toyofuku K, Katsuno T. Night view system with pedestrian detection using nearinfared light[J]. TOYOTA Technical Review,2008,56(1):82-87
[176] Bertozzi M, Broggi A, Caraffi C, et al. Pedestrian detection by means offar-infared stereo vision[J]. Computer Vision and Image Understanding,2007,106:194-204
[177] Heikkil Marko, Pietiknen Matti, Schmid Cordelia. Description of interest regionswith local binary patterns[J]. Pattern Recognition,2009,42(3):425-436
[178] Ojala T., Pietikainen M., Maenpaa T. Multiresolution gray-scale and rotationinvariant texture classification with local binary patterns[J]. Pattern Analysis andMachine Intelligence, IEEE Transactions on,2002,24(7):971-987
[179] Liao Shengcai, Zhu Xiangxin, Lei Zhen, et al. Learning Multi-scale Block LocalBinary Patterns for Face Recognition[A]. Proceedings of IAPR/IEEEInternational Conference on Biometrics (ICB-2007): Springer Berlin/Heidelberg,2007:828-837
[180] O'Malley R., Glavin M., Jones E. A review of automotive infrared pedestriandetection techniques[A]. Proceedings of the IET Irish Signals and SystemsConference: IET,2008:168-173
[181] X.Wang, Han T.X., S.Yan. An HOG-LBP human detector with partial occlusionhandling[A]. Proceedings of the IEEE International Conference on ComputerVision,2009:1-8
[182]田秀霞,彭源,杨姗,等.图像中基于滑动窗口的行人检测框架[J].上海电力学院学报,2011,27(1):79-82
[183] Zhang L., Chu R.F., Xiang S.M., et al. Face detection based on multi-block LBPrepresentation[A]. The2nd International Conference on Biometrics. Seoul, Korea:Springer,2007:11-18
[184]黄非非.基于LBP的人脸识别研究[D].重庆:重庆大学,2009
[185]崔美琳,陈才扣.基于分块局部二元模式的鉴别特征抽取方法及人脸识别[J].江南大学学报：自然科学版,2009,8(6):657-660
[186] Chouchoulas A., Shen Q. Rough set-aided keyword reduction for textcategorisation[J]. Applied Artificial Intelligence,2001,15(9):843-873
[187] Jensen R., Shen Q. Semantics-preserving dimensionality reduction: Rough andfuzzy-rough-based approaches[J]. IEEE Trans Knowl Data Eng,2004,16(12):1457-1471
[188] Jensen R., Shen Q. Fuzzy–rough attribute reduction with application to webcategorization[J]. Fuzzy Sets and Systems,2004,141(3):469-485
[189] Salamó Maria, López-Sánchez Maite. Rough set based approaches to featureselection for Case-Based Reasoning classifiers[J]. Pattern Recognition Letters,2011,32(2):280-292
[190] Vapnik V N. The Nature of Statistical Learning Theory[M]. New York: Springer,1995
[191]孙昀,刘富强,李志鹏.基于空间梯度直方图的行人检测算法[J].中国图象图形学报,2008,13(10):1825-1828
[192] Dalal N, Triggs B. Histogranxs oforiented gradientsfor human detection [A].International Conference on Com puter Vision and Pattern Recognition(CVPR2005),2005:886-893
[193] http://www.csie.ntu.edu.tw/~cjlin/
[194] http://www.cse.ohio-state.edu/otcbvs-bench/
[195]王玮.采用LBP金字塔的人脸描述与识别[J].计算机辅助设计与图形学学报,2009,21(1):94-100,106
[196] Qian X, Hua X, Chen P, et al. PLBP: An effective local binary patterns texturedescriptor with pyramid representation[J]. Pattern Recognition,2011,44(10-11):2502-2515
[197] Yilmaz A, O Javed, M Shah. Object tracking: a survey[J]. ACM ComputingSurveys,2006,38(4):1-45
[198] Xing J, Ai H, Lao S. Multi-object tracking through occlusions by local trackletsfiltering and global tracklets association with detection responses[A].Proceedingsof IEEE Conference on Computer Vision and Pattern Recognition.New Jersey,2009:1-8
[199] Bennett B., Magee D.R., Cohn A.G., et al. Enhanced tracking and recognition ofmoving objects by reasoning about spatio-temporal continuity[J]. Image andVision Computing,2008,26(1):67-81
[200]单勇.复杂条件下视频运动目标检测和跟踪[D]:国防科学技术大学,2006.
[201] Donoho D L, Johnstone L M. Ideal spatial adaptation via wavelet shrinkage[J].Biometrika,1994,81:425-455
[202] Oliva A, Torralba A. Modeling the Shape of the Scene: A Holistic Representationof the Spatial Envelope[J]. IJCV,2001,42(3):145-175
[203] Kadir T, Brady M. Scale, saliency and image description[J]. International Journalof Computer Vision,2001,45:83-105
[204] Xia S, Hancock Edwin R.3D Object Recognition using Hyper-Graphs andRanked Local Invariant Features[A]. SSPR&SPR2008,2008:117-126
[205] Xia S, Yu H, Liu J, et al. A Framework for Large Scale Object Indexing andRetrieval[J]. Journal of Information&Computational Science,2009,6(3):869~877
[206] Ke Y., Sukthankar R. PCA-SIFT: A more distinctive representation for localimage descriptors[A].2004IEEE Computer Society Conference on ComputerVision and Pattern Recognition,2004:506-513
[207]谭志国,刘滕冲,孙即祥,等.一种非刚性医学图像点匹配方法[J].武汉大学学报：理学版,2007,53(6):759-764
[208] Zheng Y. F., Doermann D. Robust point matching for two-dimensional nonrigidshapes[A]. Tenth IEEE International Conference on Computer Vision,2005:1561-1566
[209] Kosowsky J. J., Yuille A. L. The invisible hand algorithm: solving the assignmentproblem with statistical physics[J]. Neural Networks,1994,7(3):477-490
[210] Powell M. J. D. The uniform convergence of thin plate spline interpolation in twodimensions[J]. Numerische Mathematik,1994,68:107-128
[211]谭志国.点模式匹配及应用[D]:国防科技大学,2008
[212] Bilbro G., Mann R., Miller T. K., et al. Optimization by mean field annealing[J].Advances in neural information processing systems1table of contents,1989:91-98
[213] Bilbro G. L., Snyder W. E., Garnier S. J., et al. Mean field annealing: a formalismfor constructing GNC-likealgorithms[J]. Neural Networks, IEEE Transactions on,1992,3(1):131-138
[214] Peterson C., Soderberg B. A new method for mapping optimization problems ontoneural networks[J]. International Journal of Neural Systems,1989,1(1):3-22
[215] Yuille A. L., Kosowsky J. J. Statistical physics algorithms that converge[J].Neural Computation,1994,6(3):341-356
[216] Chui Haili, Rangarajan A. A new algorithm for non-rigid point matching[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2000:44-51
[217] Zheng Y. F., Doermann D. Robust point matching for nonrigid shapes bypreserving local neighborhood structures[J]. IEEE Transactions on PatternAnalysis and Machine Intelligence,2006,28(4):643-649
[218] Belongie S., Malik J., Puzicha J. Shape matching and object recognition usingshape contexts[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2002,24(4):509-522
[219]吴月娥,王小喜,哈章,等.基于薄板样条和形状内容的医学图像非刚性配准方法研究[J].航天医学与医学工程,2007,20(1):43-46
[220] Bookstein F. L. Principal Warps-Thin-Plate Splines and the Decomposition ofDeformations[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1989,11(6):567-585
[221] NieX, Zhao R, Zhang C, et al. an Improved Radial Basis Function Based MethodFor Image Warpping[J]. Journal of Electronics(China),2005,22(4):422-426
[222] Chui H, Lawrence Win, Robert Schultz, et al. A Unified Non-rigid FeatureRegistration Method For Brain Mapping[J]. Medical Image Analysis,2003,(7):113-130
[223] Sinkhorn R. A relationship between arbitrary positive matrices and doublystochastic[J]. Ann Math Stat,1964,35:876-879
[224] Gold S., Rangarajan A. A graduated assignment algorithm for graph matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(4):377-388
[225] Rangarajan A., Gold S., Mjolsness E. A novel optimizing network architecturewith applications[J]. Neural Computation,1996,8(5):1041-1060
[226]刘建军.基于图像局部不变特征的类属超图模型构建与目标识别技术研究
[D]:国防科学技术大学,2011
[227]李志华.智能视频监控系统目标跟踪与分类算法研究[D]:浙江大学,2008
[228] BebisG, Georgiopoulos M, Lobo N. Learning Geometric Hashing Functions forModel-based Object Recognition[A]. International Conference on ComputerVision,1995:543-548
[229] Li F, Perona P. A Bayesian Hierarchical model for Learning Natural SceneCategories. International Conference on Computer Vision and PatternRecognition,2005:524-531
[230] Torralba A, Fergus R, Weiss Y. Small Codes and Large Image Databases forRecognition[A], International Conference on Computer Vision,2008
[231] Nowak E. Sampling Strategies for Bag-of-Features Image Classification.European Conference on Computer Vision,2006:490-503
[232] PhilbinJ, Sivic J, Zisserman A. Geometric Latent Dirichlet Allocation (gLDA)Model for Unsupervised Particular Object Discovery in Unordered ImageCollections [A]. BMVC,2008
[233] KadirT, Brady M, Zisserman A. An Invariant Method for Selecting SalientRegions in Images. European Conference on Computer Vision,2004:345-457
[234]张仁彦,赵洪亮,卢晓,等.基于相似性传播聚类的灰度图像分割[J].海军工程大学学报,2009,(3):33-37
[235] Frey B, Dueck D. Mixture Modeling by Affinity Propagation[J]. NeuralInformation Processing Systems,2006:379-386
[236] Frey B, Dueck D. Clustering by Passing Messages between Data Points[J].Science,2007,315(5814):972-976
[237]孙即祥.现代模式识别[M].长沙:国防科学技术大学出版社,2002.
[238] Alahakoon D, Halgamuge S K. Dynamie seIf-organizing maps with controlledgrowth for knowledge diseovery[J]. IEEETrans on NeuralNetworks,2000,12(1):153-158
[239]夏胜平,刘建军,袁振涛,等.基于集群的增量分布式RSOM聚类方法[J].电子学报,2007,(3):385-391
[240]张乐锋,虞华,夏胜平,等. RSOM算法及其应用研究[J].复旦学报（自然科学版）,2004,(5):704-709
[241]夏东，李吉成，沈振康.基于粗糙集近似约简和SIFT特征的图像匹配算法[J].信号处理,2011,27(12):1872-1877
[2]杨涛,李静,潘泉,等.基于场景模型与统计学习的鲁棒行人检测算法[J].自动化学报,2010:499-508
[3]南京网行通. ATM机/自助银行智能监控系统.
[4] Kreucher, Chris M., Kastella, Keith D., Hero III, Alfred O. Tracking multipletargets using a particle filter representation of the joint multitarget probabilitydensity[A]. Proceedings of SPIE,2003,5204,258-269
[5] Kim J. S., Yeom D. H., Joo Y. H. Fast and robust algorithm of tracking multiplemoving objects for intelligent video surveillance systems[J]. Consumer Electronics,IEEE Transactions on,2011,57(3):1165-1170
[6]万家兵,霍宏.智能视频监控中目标的检测与识别[M].上海:上海交通大学出版社,2010
[7]徐杨,吴成东,陈东岳.基于视频图像的交通事件自动检测算法综述[J].计算机应用研究,2011,28(4):1206-1210
[8]周永红.智能视频监控技术现状,应用及发展趋势的探讨[J].中国安防,2011,(3):38-43
[9]王素玉,沈兰荪.智能视觉监控技术研究进展[J].中国图象图形学报,2007,12(009):1505-1514
[10]梁笃国,张艳霞,郑泽民.网络视频监控技术及应用[M]:人民邮电出版社,2009
[11]罗世伟,左涛,邹开耀.视频监控系统原理及维护[M]:电子工业出版社,2010
[12] Collins R., Lipton A., Kanade T., et al. A system for video surveillance andmonitoring[A]. Citeseer,1999:25-29
[13] Kumar R., Sawhney H., Samarasekera S., et al. Aerial video surveillance andexploitation[J]. Proceedings of the IEEE,2001,89(10):1518-1539
[14] Collins R.T, Gross R., Shi J. Silhouette-based human identification from bodyshape and gait[A]. Published by the IEEE Computer Society,2002,0366
[15] ADVISOR–Annotated Digital Video for Intelligent Surveillance and OptimisedRetrieval. http://www-sop.inria.fr/orion/ADVISOR/
[16] Blauensteiner P., Kampel M. Visual surveillance of an airports apron-an overviewof the AVITRACK project[A]. In Digital imaging in media and education, annualworkshop of AAPR,2004
[17] Behan J. Keeffe D. The Development of an Autonomous Robotic Aid to Assist theDisabled and Elderly[A]. Bioengineering in Ireland, Limerick,2004:146-152
[18]赵旭东,刘鹏,唐降龙,刘家锋.一种适应户外光照变化的背景建模及目标检测方法[J].自动化学报,2011,37(8):915-922
[19] Gelgon M., Bouthemy P., Le Cadre J.P. Recovery of the trajectories of multiplemoving objects in an image sequence with a PMHT approach[J]. Image and VisionComputing,2005,23(1):19-31
[20] Li L., Leung M.K.H. Integrating intensity and texture differences for robust changedetection[J]. IEEE Transactions on Image Processing,2002,11(2):105-112
[21] Hue C., Le Cadre J.P, et al. Sequential Monte Carlo methods for multiple targettracking and data fusion[J]. Signal Processing, IEEE Transactions on,2002,50(2):309-325
[22] Karlsson R., Gustafsson F. Monte Carlo data association for multiple targettracking[A]. IEE,2001,11:13/1-13/5
[23] Iketani A., Kuno Y., Shimada N., et al. Real-time surveillance system detectingpersons in complex scenes[A]. Image Analysis and Processing,1999ProceedingsInternational Conference on,1999:1112-1115
[24] Chris S., Grimson W.E.L. Learning Patterns of Activity Using Real-Time Tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757
[25] Godsill S.J., Doucet A., West M. Monte Carlo smoothing for nonlinear timeseries[J]. Journal of the American Statistical Association,2004,99(465):156-168
[26] Gavrila D.M., Davis L.S.3-D model-based tracking of humans in action: amulti-view approach[A]. IEEE,1995:73-80
[27] Kettnaker V., Zabih R. Counting people from multiple cameras[A]. Published bythe IEEE Computer Society,1999:267-281
[28] Jain R., Nagel H. H. On the analysis of accumulative difference pictures fromimage sequences of real-world scenes[J]. IEEE Transactions Pattern Analysis andMachine Intelligence,1979,1(2):206-214
[29] Song H., Shi F. A real-time algorithm for moving objects detection in videoimages[A]. IEEE,2004,4105:4108-4111
[30] Thakoor N., Gao J. Automatic video object shape extraction and its classificationwith camera in motion[A]. Image Processing,2005ICIP2005IEEE InternationalConference on,2005:III-437-440
[31] Rajagopalan R., Orchard M.T., Brandt R.D. Motion field modeling for videosequences[J]. Image Processing, IEEE Transactions on,1997,6(11):1503-1516
[32]广田.基于视觉的行人检测和跟踪技术的研究[D].上海:上海交通大学,2007
[33]马燕.图像目标跟踪算法研究[D].西安:西安电子科技大学,2011
[34] Lin Z., Davis L.S., Doermann D., et al. Hierarchical part-template matching forhuman detection and segmentation[A].2007IEEE11th International Conferenceon Computer Vision,2007:1-8
[35] Jain A.K., Zhong Y., Lakshmanan S. Object matching using deformabletemplates[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1996,18(3):267-278
[36] Coughlan J., Yuille A., English C., et al. Efficient deformable template detectionand localization without user initialization[J]. Computer Vision and ImageUnderstanding,2000,78(3):303-319
[37]胡正平,杨建秀.稀疏活动轮廓扩展形状脚本模型目标检测算法[J].计算机科学与探索,2011,5(3):280-287
[38] Krattenthaler W., Mayer K.J., Zeiller M. Point correlation: a reduced-cost templatematching technique[A]. IEEE,1994,201:208-212
[39] Baro X., Escalera S., Vitrio J., et al. Traffic sign recognition using evolutionaryadaboost detection and forest-ECOC classification[J]. Intelligent TransportationSystems, IEEE Transactions on,2009,10(1):113-126
[40] Munder S., Gavrila D.M. An experimental study on pedestrian classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006:1863-1868
[41] Khammari A., Nashashibi F., Abramson Y., et al. Vehicle detection combininggradient analysis and AdaBoost classification[A]. Intelligent TransportationSystems,2005Proceedings2005IEEE,2005:66-71
[42] Dalal N., Triggs B., Histograms of oriented gradients for human detection[A].Computer Vision and Pattern Recognition,2005CVPR,2005:1213-1218
[43] Kim D.S., Nguyen H.N., Park J.S. Genetic algorithm to improve SVM basednetwork intrusion detection system[A]. IEEE,2005:1347-1352
[44] Chen W.H., Hsu S.H., Shen H.P. Application of SVM and ANN for intrusiondetection[J]. Computers&Operations Research,2005,32(10):2617-2634
[45] Wu Y., Yu T. A field model for human detection and tracking[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2006:753-765
[46] Wu Y., Yu T., Hua G. A statistical field model for pedestrian detection[A]. IEEE,2005,1021:1023-1030
[47]张秀伟,张艳宁,郭哲,等.可见光-热红外视频运动目标融合检测的研究进展及展望[J].红外与毫米波学报,2011,30(4):354-360
[48] E Jacobs C, A Finkelstein, H Salesin D. Fast multiresolution image querying[A].Computer Graphics Proceeding SIGGRAPH'95[A],1995:277-286
[49] Jwu-Sheng Hu, Chung-Wei Juan, Jyun-Ji Wang. A spatial-color mean-shift objecttracking algorithm with scale and orientation estimation[J]，Pattern RecognitionLetters，2008，29：2165-2173
[50] R Picard, A Pentland. Introduction to the special section on digitallibraries: representation and retrieval[J]. IEEE Trans on PAMI,1996:769-770
[51] R Smith J, F Chang S. VisualSEEK: a fully automated content-based image querysystem[A]. Proc ACM Multimedia,1996:87-89
[52] J Swain M, H Ballard B. Color Indexing[J]. International Joural of ComputerVision,1991,7(1):11-32
[53] J Hafer. Efficient Color Histogram for Quadratic Form Distance Functions[J].IEEE Trans on PAMI,1995,10(7):729-736
[54] O Balan A, J Black M. An adaptive appearance model approach for model-basedarticulated object tracking[A]. IEEE Computer Society Conference on CVPR,2006:758-765
[55] X Song, R Nevatia. A model-based vehicle segmentation method for tracking[A].Proc of10th IEEE International Conference on Computer Vision,2005:1124-1131
[56] T Zhao, R Nevatia, F Lv. Segmentation and tracking of multiple humans incomplex situations[A]. Proc of IEEE Computer Society Conference on CVPR,2001:194-201
[57] M Hu, W Hu, T Tan. Tracking people through occlusions[A]. Proc of17th ICPR,2004:724-727
[58] Malik, Jitendra, Russell, Stuart. Traffic Surveillance And Detection TechnologyDevelopment: New Traffic Sensor Technology Final Report,1997:97-102
[59] Wron, C.R., Azarbayejani, A., Darrell, T., et al. Pfinder: Real-time Tracking of theHuman Body[J]. IEEE Trans on PAMI,1997,19:780-785
[60]侯晴宇,张伟,武春风,等．改进的均值移位红外目标跟踪[J]．光学精密工程，2010,18(3):764-770
[61] Artur oza, Lyudmila Mihaylova, David Bull, et al. Structural Similarity-BasedObject Tracking in Multimodality Surveillance Videos[J]. Machine Vision andApplications.2009,20(2):71-83
[62] Isard M., Blake A. CONDENSATION-Conditional density propagation for visualtracking[J]. Intemational Journal of Computer Vision,1998,29(1):52-81
[63] Kilger M. A shadow handler in a video-based real-time traffic monitoringsystem[A]. in Proc of IEEE Workshop Applications of Computer Vision. PalmSprings, CA,1992:11-18
[64] Karaulova I A, Hall P M, Marshall A D. A hierarchical model of dynamics fortracking people with a single video camera[A]. Proceedings of British MachineVision Conference,2000:262-352
[65] Ju S, Black M, Yaccob Y. Cardboard people: a parameterized model of articulatedimage motion[A]. Proceedings of IEEE International Conference on AutomaticFace and Gesture Recognition,1996:38-44
[66] Niyogi S.A, Adelson E.H. Analyzing and recognizing walking figures in XYT[A].Proceedings of IEEE Conference on Computer Vision and PatternRecognition,1994:469-474
[67] YAO A.，WANG G.J.，LIN X.G.，et al．Kernel based articulated objecttracking with scale adaptation and model update[C]， IEEE InternationalConference on Acoustics，Speech and Signal Processing. Las Vegas, USA,2008:945—948
[68] Rohr K. Toward model-based recognition of human movements in imagesequences[J]. Image Understanding,1994:94-115
[69] Wachter S, Nagel H H. Tracking persons in monocular image sequences[J]. Visionand Image Understanding,1999,74(3):174-192
[70] Zhu Z., Xu G., Yang B, et al. VISATRAM:A real-time vision system for automatictraffic monitoring[J]. Image and Vision Computing2000,18(10):781-794
[71] Maggio E，Taj M，Cavallaro A. Efficient multi-target visual tracking usingrandom finite sets[J]. IEEE Transactions on Circuits and Systems for VideoTechnology，2008,18(8):1016-1027
[72] Julier S.J.，Uhlmann J.K. A New Extension of the Kalman Filter to NonlinearSystems[J]. Proceedings of the lth International Symposium on Aerospace/DefenseSensing，Simulation and Controls，1997:182-193
[73] Cortina E, Otero D, Attellis C.E．Maneuvering target tracking using extendedKalman filter[J]. IEEE Transactions on Aerospace and Electronic Systems,1991:155-158
[74] LAO Y, ZHU J, ZHENG Y. Sequential particle generation for visual tracking[J].IEEE Transactions on Circuits and Systems for Video Technology,2009,19(9):1365-1378
[75] PAN P, SCHONFILD D. Dynamic proposal variance and optimal particleallocation in particle filtering for video tracking[J]. IEEE Transaction on Circuitsand Systems for Video Technology,2008,18(9):1268-1279.
[76] BOUAYNAYA N，SCHONFELD D. On the optimality of motion-based particlefiltering[J]. IEEE Transactions on Circuits and Systems for Video Technology，2009,19(7):1068-1072.
[77] IOANNIS P, EDWIN H.R. Coupled prediction classification for robust visualtracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，2010,32(9):1553-1567
[78] SOTO D.A, REGAZZONI M C S. Bayesian tracking for video analytics[J]. IEEESignal Processing Magazine,2010,27(5):46-55
[79] Kass M, Witkin A, Terzopoulous D. Snakes: Active contour models[J].International Journal of Computer Vision,1987,1(4):321-331
[80] Paragios N, Deriche R. Geodesic active contours and level sets for the detectionand tracking of moving objects[J]. IEEE Transaction on PAMI,22:266-280
[81] Peterfreund N. Robust tracking of position and velocity with Kalman snakes[J].IEEE Transaction on PAMI,2000,22:564-569
[82] Isard M, Blake A. Contour tracking by stochastic propagation of conditionaldensity[A]. Proceedings of European Conference on Computer Vision,1996:343-356
[83] Kim W., Lee C.Y., Lee J.J. Tracking moving object using Snake's jump based onimage flow[J]. Mechatronics,2001,11(2):199-226
[84] Chen Q, Sun QS, Heng PA, et al.Two-Stage Object Tracking Method Based onKernel and Active Contour[J]. IEEE Transactions on Circuits and Systems forVideo Technology,2010,20(4):605-609
[85] Vard A R，Moallem P，Nilchi A R N．Texture-Based Parametric ActiveContour for Target Detection and Tracking[J]．International Journal of ImagingSystems and Technology,2009,19(3): l79-186
[86] Spengler M, Schiele B. Towards multi-cue integration for visual tracking[J].Machine Vision and Applications,2003,14(1):50-58
[87] Merwe R, Doucet A, Freitas N, et al. The unscented particle filter, technical reportCUED/F-INFENG/TR380. Engineering Department,Cambridge University,2000.
[88] Segen J, Pingali S. A camera-based system for tracking people in real time[A].Proc of International Conference on Pattern Recognition,1996:63-67
[89] Khan Z.H, Gui Y.H. Joint feature correspondences and appearance similarity forrobust visual object tracking[J]. IEEE Transactions on Information Forensics andSecurity,2010,5(3):591-606
[90] Jang D S, Choi H I. Active models for tracking moving objects[J]. PatternRecognition,2000,33(7):135-146
[91] YANG M, WU Y, HUA G. Context-aware visual tracking[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence,2009,31(7):1195-1209
[92] Cyr C, Kimia B.3D Object Recognition Using Similarity-based Aspect Graph.International Conference on Computer Vision,2001:254-261
[93] van de Sande, K.E.A., Gevers, T., Snoek, C.G.M. Evaluating color descriptors forobject and scene recognition[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence, in press,2010,32(9):1582-1596
[94] Selinger A, Nelson C.R. A Perceptual Grouping Hierarchy for Appearance-based3d Object Recognition[J]. Computer Vision and Image Understanding,1999,76(1):83-92
[95] Lowe D. Distinctive Image Features from Scale-invariant Keypoints[J].International Joural of Computer Vision,2004,60(2):91-110
[96] Mikolajczyk K, Schmid C. An Affine Invariant Interest Point Detector[A].European Conference on Computer Vision,2002:128-142
[97] Obrdzalek S, Matas J. Object Recognition Using Local Affine Frames onDistinguished Regions[A]. BMVC,2002:414-431
[98] Tuyelaars T, Van-Gool L. Wide Baseline Stereo Based on Local, AffinelyInvariant Regions [A], BMVC,2000
[99] Schaffalitzky F, Zisserman A. Automated Scene Maching in Movies. Workshop onContent-Based Image and Video Retrieval,2002:186-197
[100] Mikolajczyk K, Schmid C. Indexing Based on Scale-invariant Interest Points[A].International Conference on Computer Vision,2001:525-531
[101] Mikolajczyk K, Schmid C. Scale and affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86
[102] Csurka G., Dance C., Fan L., et al. Visual categorization with bags ofkeypoints[A]. Citeseer,2004:22-34
[103] L.-J. Guo, J.-Y. Zhao, and R. Zhang. A novel method to construct visualvocabulary based on maximization of mutual information. In Proceedings ofInternational Conference on Artificial Intelligence and ComputationalIntelligence[C],2009,3:123-127.
[104] van Gemert, J.C., Veenman, C.J., Smeulders, A.W.M., et al. Visual wordambiguity[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(7):1271-1283
[105] Weber M., Welling M., Perona P. Unsupervised learning of models forrecognition[J]. Computer Vision-ECCV2000,2000:18-32
[106] Fergus R, Perona P, Zisserman A. Object class recognition by unsupervisedscale-invariant learning[A]. Proceedings of IEEE Conference on ComputerVision and Pattern Recognition,2003:264-271
[107] Crandall D, Huttenlocher D. Weakly supervised learning of part-based spatialmodels for visual object recognition[A]. Proceedings of European Conference onComputer Vision,2006:16-29
[108] Zheng QF, Wen G. Constructing Visual Phrases for Effective and EfficientObject-Based Image Retrieval[J]. ACM Transactions on Multimedia Computing,Communications and Applications,2008,5(1),7:1-19
[109] Crandall D J, Felzenszwalb P, Huttenlocher D P. Spatial priors for part-basedrecognition using statistical models[A]. Proceedings of IEEE Conference onComputer Vision and Pattern Recognition,2005:10-17
[110] Fischler M, Elschlager R. The representation and matching of pictorialstructures[J]. IEEE Trans on Comp, c-22(1):67-92
[111] Burl M, Weber M, Perona P. A probabilistic approach to object recognition usinglocal photometry and global geometry[A]. Proceedings of European Conferenceon Computer Vision,1998:628-641
[112] Mikolajczyk K, Leibe B, Schiele B. Multiple object class detection with agenerative model[A]. Proceedings of IEEE Conference on Computer Vision andPattern Recognition,2006:26-36
[113] Leibe B, Schiele B. Interleaved object categorization and segmentation[A]. Procof British Machine Vision Conference,2003:759-768
[114] Fei-Fei L, Fergus R, Perona P. A bayesian approach to unsupervised one-shotlearning of object categories[A]. Proceedings of IEEE International Conferenceon Computer Vision,2003:1134-1139.
[115] Fergus R., Perona P., Zisserman A. A sparse object category model for efficientlearning and exhaustive recognition[A]. IEEE,2005,381:380-387
[116] Felzenszwalb P, Huttenlocher D. Pictorial structures for object recognition[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2000:2066-2073.
[117] Bouchard G, Triggs B. Hierarchical part-based visual object categorization[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2005:710-715
[118] Carneiro G, Lowe D G. Sparse flexible models of local features[A]. Proceedingsof European Conference on Computer Vision,2006:29-43
[119]孙浩,王程,王润生.局部不变特征综述[J].中国图象图形学报,2011,16(02):141-151
[120] Mikolajczyk K., Schmid C. A Performance Evaluation of Local Descriptors[J].IEEE Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630
[121]李蓉,周维柏.一种基于不变特征的图像匹配算法[J].华中师范大学学报：自然科学版,2010,44(1):38-42
[122]王鹏,王平,沈振康,等.一种基于sift的仿射不变特征提取新方法[J].信号处理,2011,27(1):88-93
[123] KeY. PCA-SIFT: a more distinctive representation for local image descriptors[J].CVPR,2004,2:506-513
[124]李伟,沈振康.基于KPCA-Sift描述符的图像配准[J].信号处理,2009,25(4):644-647
[125] Pawlak Z., Skowron A. Rudiments of rough sets[J]. Information Sciences,2007,177(1):3-27
[126] Thangavel K., Pethalakshmi A. Dimensionality reduction based on rough settheory: A review[J]. Appl Soft Comput,2009,9(1):1-12
[127] Pawlak Z. Rough Sets: Theoretical Aspects of Reasoning About Data[M]. London:Kluwer Academic Publisher,1991
[128]张文修,吴伟志,梁吉业,等.粗糙集理论与方法[M].北京:科学出版社,2001
[129]滕书华,昝德才,孙即祥,等.基于同可区分度的属性约简算法[J].模式识别与人工智能,2010,23(5):630-638
[130]滕书华.基于粗糙集理论的不确定性度量和属性约简方法研究[D].长沙:国防科学技术大学,2011:182-189
[131]王国胤.粗糙集理论与知识获取.西安:西安交通大学出版社,2001
[132]张文修,梁怡,吴伟志.信息系统与知识发现[M].北京:科学出版社,2003
[133]吴子特,叶东毅.一种可伸缩的快速属性约简算法[J].模式识别与人工智能,2009,22(2):234-239
[134]刘少辉,盛秋戬,吴斌,等. Rough集高效算法的研究[J].计算机学报,2003,26(5):524-529
[135]徐章艳,刘作鹏,杨炳儒,等.一个复杂度为max(O(|C||U|), O(|C|^2|U/C|))的快速属性约简算法[J].计算机学报,2006,29(3):391-399
[136]钱宇华,梁吉业,王锋.面向非完备决策表的正向近似特征选择加速算法[J].计算机学报,2011,34(3):435-442
[137]滕书华,孙即祥,周石琳,等.基于信息观点的约简算法比较[J].计算机科学,2011,38(1):259-263
[138] Li Fei, Yin Yunqiang. Approaches to knowledge reduction of covering decisionsystems based on information theory [J]. Information Sciences,2009,179(11):1694-1704
[139]颜艳,杨慧中.一种基于互信息的粗糙集知识约简算法[J].清华大学学报(自然科学版),2007,47(S2):1903-1906
[140]王国胤,于洪,杨大春.基于条件信息熵的决策表约简[J].计算机学报,2002,25(7):759-766
[141]苗夺谦,王珏.粗糙集理论中概念与运算的信息表示[J].软件学报,1999,10(2):113-116
[142]刘振华,刘三阳,王珏.基于信息量的一种属性约简算法[J].西安电子科技大学学报,2003,30(6):835-838
[143] Luo P., He Q., Shi Z.. Theoretical study on a new information entropy and its usein attribute reduction[J]. Cognitive Informatics,2005(ICCI2005) Fourth IEEEConference on,2005:73-79
[144] Slezak D. Approximate entropy reducts[J]. Fundam Inform,2002,53(3-4):365-390
[145]杨明,杨萍.垂直分布多决策表下基于条件信息熵的近似约简[J].控制与决策,2008,23(10):1103-1108
[146]祁立,刘玉树.基于条件信息量的快速粗集约简算法[J].北京理工大学学报,2007,27(7):604-608
[147]苗夺谦,王国胤,刘清,等.粒计算：过去、现在与展望[M].北京:科学出版社,2007
[148] Zhao Y., Yao Y. Y., Luo F. Data analysis based on discernibility andindiscernibility[J]. Information Sciences,2007,177(22):4959-4976
[149] Susmaga R. Reducts and constructs in attribute reduction[J]. Fundam Inform,2004,61(2):159-181
[150]苗夺谦,王珏.粗糙集理论中知识粗糙性与信息熵关系的讨论[J].模式识别与人工智能,1998,11(001):34-40
[151]杨明.决策表中基于条件信息熵的近似约简[J].电子学报,2007,35(11):2156-2160
[152]陈堂敏.基于区分能力大小的启发式约简算法的研究[J].计算机学报,2006,29(3):480-487
[153] Lindeberg Tony. Scale-Space for Discrete Signals[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1990,12(3):234-254
[154] Linderberg T. Junction Detection with Automatic Selection of Detection Scalesand Localization Scales [C]. IEEE International Conference on Image Processing,1994:924-928
[155] Xia SP, Ren P, Hancock R. Ranking the Local Invariant Features for the RobustVisual Saliencies[A]. International Conference on Pattern Recognition,2008
[156] Wojciech Ziarko. Variable precision rough set model[J]. Journal of Computer andSystem Sciences,1993,46(1):39-59
[157]刘建军,夏胜平,郁文贤.基于SIFT特征的两阶段procrustes迭代匹配算法[J].信号处理,2011,26(6):854-858
[158]孙涛,黄茜,刘军,等.基于局部二元模式特征的行人检测[J].计算机工程与设计,2011,(6):2119-2123
[159] Gandhi T., Trivedi M. M. Pedestrian Protection Systems: Issues, Survey, andChallenges[J]. Intelligent Transportation Systems, IEEE Transactions on,2007,8(3):413-430
[160]许言午,曹先彬,乔红.行人检测系统研究新进展及关键技术展望[J].电子学报,2008,36(5):962-968
[161]贾慧星,章毓晋.车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述[J].自动化学报,2007,33(1):84-90
[162] Enzweiler M., Gavrila D. M. Monocular Pedestrian Detection: Survey andExperiments[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2009,31(12):2179-2195
[163] Sabzmeydani P, Mori G. Detecting pedestrians by learning Shapelet features[C].IEEE Conference on Computer Vision and Pattern Recognition,2007:1-8
[164]李娟,邵春福,杨励雅.基于混合高斯模型的行人检测方法[J].吉林大学学报:工学版,2011,(1):41-45
[165] Wu B, Nevatia R. Detection of multiple partially occluded humans in a singleimage by bayesian combination of edgelet part detectors[C]. IEEE InternationalConference on Computer Vision,2005,1:90–97
[166] Dai C, Zheng Y, Li X. Layered represenation for pedestrian detection andtrakcing in infrared imagery[C]. IEEE Computer Society Conference onComputer Vision and Pattern Recognition,2005,1:13-20
[167] Yasuno M, Ryousuke S, Yasuda N, et al. Pedestrian detection and tracking in farinfrared images[C]. IEEE Conference on Intelligent Transportation Systems,2005:182-187
[168] Sun H, Wang C, Wang BL, et al. Pyramid binary pattern features for real-timepedestrian detection from infrared videos[J]. Neurocomputing,2011,74(5):797-804
[169]田广,戚飞虎.移动摄像机环境下基于特征变换和svm的分级行人检测算法[J].电子学报,2008,36(5):1024-1028
[170]胡春华,钱堃.基于角度泛化的SC模型匹配的行人检测[J].计算机工程,2010:234-241
[171]郭永彩,胡瑞光,高潮.红外图像中的行人检测[J].重庆大学学报：自然科学版,2009,32(9):1070-1073
[172] Liu Y, Chen X, Yao H, et al. Contour-motion feature (CMF): a space-timeapproach for robust pedestrian detection[J]. Pattern Recognition Letters,2009,30:148-156
[173] Gavrila D M. Multi-cue pedestrian detection and tracking from a movingvehicle[J]. International Journal of Computer Vision,2007,73(1):41-59
[174] Xu F, Liu X, Fujimura K. Pedestrian detection and tracking with night vision[J].IEEE Transactions on Intelligent Transportation Systems,2005,6(1):63-71
[175] Toyofuku K, Katsuno T. Night view system with pedestrian detection using nearinfared light[J]. TOYOTA Technical Review,2008,56(1):82-87
[176] Bertozzi M, Broggi A, Caraffi C, et al. Pedestrian detection by means offar-infared stereo vision[J]. Computer Vision and Image Understanding,2007,106:194-204
[177] Heikkil Marko, Pietiknen Matti, Schmid Cordelia. Description of interest regionswith local binary patterns[J]. Pattern Recognition,2009,42(3):425-436
[178] Ojala T., Pietikainen M., Maenpaa T. Multiresolution gray-scale and rotationinvariant texture classification with local binary patterns[J]. Pattern Analysis andMachine Intelligence, IEEE Transactions on,2002,24(7):971-987
[179] Liao Shengcai, Zhu Xiangxin, Lei Zhen, et al. Learning Multi-scale Block LocalBinary Patterns for Face Recognition[A]. Proceedings of IAPR/IEEEInternational Conference on Biometrics (ICB-2007): Springer Berlin/Heidelberg,2007:828-837
[180] O'Malley R., Glavin M., Jones E. A review of automotive infrared pedestriandetection techniques[A]. Proceedings of the IET Irish Signals and SystemsConference: IET,2008:168-173
[181] X.Wang, Han T.X., S.Yan. An HOG-LBP human detector with partial occlusionhandling[A]. Proceedings of the IEEE International Conference on ComputerVision,2009:1-8
[182]田秀霞,彭源,杨姗,等.图像中基于滑动窗口的行人检测框架[J].上海电力学院学报,2011,27(1):79-82
[183] Zhang L., Chu R.F., Xiang S.M., et al. Face detection based on multi-block LBPrepresentation[A]. The2nd International Conference on Biometrics. Seoul, Korea:Springer,2007:11-18
[184]黄非非.基于LBP的人脸识别研究[D].重庆:重庆大学,2009
[185]崔美琳,陈才扣.基于分块局部二元模式的鉴别特征抽取方法及人脸识别[J].江南大学学报：自然科学版,2009,8(6):657-660
[186] Chouchoulas A., Shen Q. Rough set-aided keyword reduction for textcategorisation[J]. Applied Artificial Intelligence,2001,15(9):843-873
[187] Jensen R., Shen Q. Semantics-preserving dimensionality reduction: Rough andfuzzy-rough-based approaches[J]. IEEE Trans Knowl Data Eng,2004,16(12):1457-1471
[188] Jensen R., Shen Q. Fuzzy–rough attribute reduction with application to webcategorization[J]. Fuzzy Sets and Systems,2004,141(3):469-485
[189] Salamó Maria, López-Sánchez Maite. Rough set based approaches to featureselection for Case-Based Reasoning classifiers[J]. Pattern Recognition Letters,2011,32(2):280-292
[190] Vapnik V N. The Nature of Statistical Learning Theory[M]. New York: Springer,1995
[191]孙昀,刘富强,李志鹏.基于空间梯度直方图的行人检测算法[J].中国图象图形学报,2008,13(10):1825-1828
[192] Dalal N, Triggs B. Histogranxs oforiented gradientsfor human detection [A].International Conference on Com puter Vision and Pattern Recognition(CVPR2005),2005:886-893
[193] http://www.csie.ntu.edu.tw/~cjlin/
[194] http://www.cse.ohio-state.edu/otcbvs-bench/
[195]王玮.采用LBP金字塔的人脸描述与识别[J].计算机辅助设计与图形学学报,2009,21(1):94-100,106
[196] Qian X, Hua X, Chen P, et al. PLBP: An effective local binary patterns texturedescriptor with pyramid representation[J]. Pattern Recognition,2011,44(10-11):2502-2515
[197] Yilmaz A, O Javed, M Shah. Object tracking: a survey[J]. ACM ComputingSurveys,2006,38(4):1-45
[198] Xing J, Ai H, Lao S. Multi-object tracking through occlusions by local trackletsfiltering and global tracklets association with detection responses[A].Proceedingsof IEEE Conference on Computer Vision and Pattern Recognition.New Jersey,2009:1-8
[199] Bennett B., Magee D.R., Cohn A.G., et al. Enhanced tracking and recognition ofmoving objects by reasoning about spatio-temporal continuity[J]. Image andVision Computing,2008,26(1):67-81
[200]单勇.复杂条件下视频运动目标检测和跟踪[D]:国防科学技术大学,2006.
[201] Donoho D L, Johnstone L M. Ideal spatial adaptation via wavelet shrinkage[J].Biometrika,1994,81:425-455
[202] Oliva A, Torralba A. Modeling the Shape of the Scene: A Holistic Representationof the Spatial Envelope[J]. IJCV,2001,42(3):145-175
[203] Kadir T, Brady M. Scale, saliency and image description[J]. International Journalof Computer Vision,2001,45:83-105
[204] Xia S, Hancock Edwin R.3D Object Recognition using Hyper-Graphs andRanked Local Invariant Features[A]. SSPR&SPR2008,2008:117-126
[205] Xia S, Yu H, Liu J, et al. A Framework for Large Scale Object Indexing andRetrieval[J]. Journal of Information&Computational Science,2009,6(3):869~877
[206] Ke Y., Sukthankar R. PCA-SIFT: A more distinctive representation for localimage descriptors[A].2004IEEE Computer Society Conference on ComputerVision and Pattern Recognition,2004:506-513
[207]谭志国,刘滕冲,孙即祥,等.一种非刚性医学图像点匹配方法[J].武汉大学学报：理学版,2007,53(6):759-764
[208] Zheng Y. F., Doermann D. Robust point matching for two-dimensional nonrigidshapes[A]. Tenth IEEE International Conference on Computer Vision,2005:1561-1566
[209] Kosowsky J. J., Yuille A. L. The invisible hand algorithm: solving the assignmentproblem with statistical physics[J]. Neural Networks,1994,7(3):477-490
[210] Powell M. J. D. The uniform convergence of thin plate spline interpolation in twodimensions[J]. Numerische Mathematik,1994,68:107-128
[211]谭志国.点模式匹配及应用[D]:国防科技大学,2008
[212] Bilbro G., Mann R., Miller T. K., et al. Optimization by mean field annealing[J].Advances in neural information processing systems1table of contents,1989:91-98
[213] Bilbro G. L., Snyder W. E., Garnier S. J., et al. Mean field annealing: a formalismfor constructing GNC-likealgorithms[J]. Neural Networks, IEEE Transactions on,1992,3(1):131-138
[214] Peterson C., Soderberg B. A new method for mapping optimization problems ontoneural networks[J]. International Journal of Neural Systems,1989,1(1):3-22
[215] Yuille A. L., Kosowsky J. J. Statistical physics algorithms that converge[J].Neural Computation,1994,6(3):341-356
[216] Chui Haili, Rangarajan A. A new algorithm for non-rigid point matching[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2000:44-51
[217] Zheng Y. F., Doermann D. Robust point matching for nonrigid shapes bypreserving local neighborhood structures[J]. IEEE Transactions on PatternAnalysis and Machine Intelligence,2006,28(4):643-649
[218] Belongie S., Malik J., Puzicha J. Shape matching and object recognition usingshape contexts[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2002,24(4):509-522
[219]吴月娥,王小喜,哈章,等.基于薄板样条和形状内容的医学图像非刚性配准方法研究[J].航天医学与医学工程,2007,20(1):43-46
[220] Bookstein F. L. Principal Warps-Thin-Plate Splines and the Decomposition ofDeformations[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1989,11(6):567-585
[221] NieX, Zhao R, Zhang C, et al. an Improved Radial Basis Function Based MethodFor Image Warpping[J]. Journal of Electronics(China),2005,22(4):422-426
[222] Chui H, Lawrence Win, Robert Schultz, et al. A Unified Non-rigid FeatureRegistration Method For Brain Mapping[J]. Medical Image Analysis,2003,(7):113-130
[223] Sinkhorn R. A relationship between arbitrary positive matrices and doublystochastic[J]. Ann Math Stat,1964,35:876-879
[224] Gold S., Rangarajan A. A graduated assignment algorithm for graph matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(4):377-388
[225] Rangarajan A., Gold S., Mjolsness E. A novel optimizing network architecturewith applications[J]. Neural Computation,1996,8(5):1041-1060
[226]刘建军.基于图像局部不变特征的类属超图模型构建与目标识别技术研究
[D]:国防科学技术大学,2011
[227]李志华.智能视频监控系统目标跟踪与分类算法研究[D]:浙江大学,2008
[228] BebisG, Georgiopoulos M, Lobo N. Learning Geometric Hashing Functions forModel-based Object Recognition[A]. International Conference on ComputerVision,1995:543-548
[229] Li F, Perona P. A Bayesian Hierarchical model for Learning Natural SceneCategories. International Conference on Computer Vision and PatternRecognition,2005:524-531
[230] Torralba A, Fergus R, Weiss Y. Small Codes and Large Image Databases forRecognition[A], International Conference on Computer Vision,2008
[231] Nowak E. Sampling Strategies for Bag-of-Features Image Classification.European Conference on Computer Vision,2006:490-503
[232] PhilbinJ, Sivic J, Zisserman A. Geometric Latent Dirichlet Allocation (gLDA)Model for Unsupervised Particular Object Discovery in Unordered ImageCollections [A]. BMVC,2008
[233] KadirT, Brady M, Zisserman A. An Invariant Method for Selecting SalientRegions in Images. European Conference on Computer Vision,2004:345-457
[234]张仁彦,赵洪亮,卢晓,等.基于相似性传播聚类的灰度图像分割[J].海军工程大学学报,2009,(3):33-37
[235] Frey B, Dueck D. Mixture Modeling by Affinity Propagation[J]. NeuralInformation Processing Systems,2006:379-386
[236] Frey B, Dueck D. Clustering by Passing Messages between Data Points[J].Science,2007,315(5814):972-976
[237]孙即祥.现代模式识别[M].长沙:国防科学技术大学出版社,2002.
[238] Alahakoon D, Halgamuge S K. Dynamie seIf-organizing maps with controlledgrowth for knowledge diseovery[J]. IEEETrans on NeuralNetworks,2000,12(1):153-158
[239]夏胜平,刘建军,袁振涛,等.基于集群的增量分布式RSOM聚类方法[J].电子学报,2007,(3):385-391
[240]张乐锋,虞华,夏胜平,等. RSOM算法及其应用研究[J].复旦学报（自然科学版）,2004,(5):704-709
[241]夏东，李吉成，沈振康.基于粗糙集近似约简和SIFT特征的图像匹配算法[J].信号处理,2011,27(12):1872-1877
© 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 |