面向UAV战场感知的目标特征建模与应用研究
|
摘要
对战场空间内高价值目标的感知是无人机（Unmanned Aerial Vehicle，UAV）系统实现自主控制的基础和关键。基于图像特征的目标建模作为目标信息处理的基本环节，在UAV战场感知流程中起着承上启下的作用。然而，由于复杂战场环境中UAV实际获取的目标图像通常存在较大的不确定性，使得建立可靠的目标表示与描述成为一项非常具有挑战性的工作。针对这一问题，论文以UAV战场感知为研究背景，结合目标特征匹配、目标类检测以及目标跟踪三个典型应用开展目标特征建模方法的研究，主要工作及创新点如下：
1）在深入分析和讨论融合上下文信息（contextual information）的目标特征建模理论的基础上，总结提出了三种目标特征建模框架。针对目标特征建模中的特征提取和表达问题，详细比较了不同的局部不变性特征检测与描述方法。同时，重点分析了具有一体化上下文建模优势的条件随机场（Conditional Random Field，CRF）模型，研究了不同扩展形式CRF模型的上下文信息利用能力以及面向目标特征建模应用的关键问题。
2）提出了基于局部特征分组和多目标优化的目标特征匹配方法，通过对特征上下文的利用能够有效克服图像模糊引起的误匹配。首先，使用图像仿射不变区域特征对不变性点特征做出范围约束，并引入特征间的几何定序信息实现了局部特征分组设计；其次，完成了特征匹配的多目标优化问题建模，提出一种新的离散多目标粒子群优化算法实现了局部特征分组的最佳匹配搜索。同不考虑上下文信息的局部特征匹配方法相比，该方法有效提高了目标特征匹配的鲁棒性。
3）提出了一种基于分层上下文表达的扩展CRF模型，实现了显著类内变化条件下单实例目标类的有效检测。针对经典CRF模型在目标特征建模中的不足，基于部件建模理论提出了CHCRF（Contextual Hierarchical Part-Driven CRF）模型，详细设计了模型的图结构、势函数、以及参数估计与模型推断方法。同时，提出了该模型的加权邻域结构形式，解决了邻域节点间依赖程度的表达问题。CHCRF模型的主要优势是能够同时利用目标图像中潜在的部件层上下文和观测层上下文信息，实现目标类及其内部隐含信息的统一建模。
4）针对UAV多实例目标检测问题，提出了基于多任务分解的MFCRF（Multi-task Factorial CRF）模型，解决了模型设计和实现中的关键问题。同单一标记任务的CRF模型相比，MFCRF模型的主要优势是建立了目标多元部件标记任务和二元目标标记任务的融合框架，能够以互补的形式融入不同任务标记间的相关性信息，从而更好地利用标记层上下文。实验结果表明，相比于现有的其它扩展CRF模型，MFCRF模型具有更强的目标建模与检测能力。
5）提出了基于时空上下文CRF模型的目标跟踪算法，有效解决了复杂动态场景中视觉目标跟踪的模型漂移问题。通过将经典CRF模型扩展到时域空间，提出了融入时空上下文信息的三维STCRF（Spatial-Temporal CRF）模型，设计了模型的时域邻域系统。该模型不仅能够借助目标标记的空间邻域相容性应对目标姿态变化和图像模糊，而且可以引入时域平滑约束对目标标记在跟踪中的连续性建模。进一步，设计了基于STCRF模型标记结果的目标跟踪算法和模型更新策略，实现了目标的稳健描述与跟踪。实验结果表明，论文所提算法相比于传统的局部特征匹配跟踪，平均跟踪误差显著降低。
The perception of high-value targets in battle space is a foundational and keyproblem for an unmanned aerial vehicle (UAV) system to achieve autonomous control.As one of the essential contents of object information processing, object featuremodeling plays a connecting role in the process of UAV battlefield awareness. However,due to the high complexity and dynamics of the battlefield environment, the actualimages acquired by UAV usually have large uncertainty, which makes the establishmentof a reliable object model become a very challenging task. Under such a background,this dissertation focuses on the problem of object feature modeling, including threetypical applications, i.e. object feature matching, object category detection, and objecttracking. The main work and contributions of this dissertation are summarized asfollows:
1) On the basis of in-depth analysis and discussion of the object feature modelingtheory with contextual information, the dissertation proposes three object featuremodeling frameworks. Aiming at the problems of feature extraction and expression inobject modeling, different detection methods and description types of local invariantfeatures are discussed in detail. Meanwhile, conditional random field (CRF) model,which has the unified framework for contextual information modeling, is analyzedemphatically. The abilities of using contextual information and key problems in objectfeature modeling for various extended forms of CRF model are studied.
2) A novel feature point matching method that benefits from local-feature-groups(LFGs) and the multi-objective optimization theory is proposed, which can effectivelyreduce the mismatches caused by image ambiguities. Fisrt of all, LFGs are constructedthrough grouping affine invariant point features and regional features. Regional featuresmake a range constraint to point features, and geometrical ordering contextualinformation in each group is introduced to enhance robustness and discrimination ofLFGs. Then, feature point matching is formulated as a multi-objective optimizationproblem, and the optimal search is realized by using a novel discrete multi-objectiveparticle swarm optimization algorithm. Experimental results show that the proposedmethod can effectively improve robustness of object feature matching while comparedwith those without contextual information.
3) In order to overcome the drawbacks of the classical CRF model for objectcategory detection, a contextual hierarchical part-driven CRF (CHCRF) model isproposed in the dissertation, which can effectively detect single-instance object categorywith notable intra-class variations. The graph structure, potential functions, parameterestimation and inference methods of CHCRF model are designed, respectively.Meanwhile, a weighted neighborhood structure is developed to capture the degree of correlation between connected nodes in the model. By using a two-layer hierarchicalformulation of labels, CHCRF model can effectively represent label-level context andobservation-level context simultaneously, and achieve unified modeling of objectcategory and its internal latent context.
4) For multi-instance object detection, the dissertation proposes a multi-taskfactorial CRF (MFCRF) model to tightly combine the task of multiclass part labelingwith the task of binary object labeling. By fusing different types of labels, the MFCRFmodel can make full use of label-level contextual information. Experimental resultsshow that the modeling capability and detection performance of MFCRF model aresuperior to other existing extended forms of CRF model.
5) To solve the drift problem of object model for visual tracking in complexdynamic scenes, a novel CRF model with spatial-temporal contextual information isproposed. By extending the classic CRF model in the time domain, the definition of thetime-domain neighborhood system is developed, and a spatial-temporal CRF (STCRF)model is proposed. The main characteristic of the model is that it can not only use thecompatibility of spatial neighborhood to deal with pose variations and image ambiguity,but also use the time domain smoothness constraint to model the continuity of objectlabels. Furthermore, an object tracking algorithm and a model update strategy based onlabeling results from STCRF model are designed to achieve robust object descriptionand tracking. Experimental results show that the proposed algorithm can significantlyreduce the average tracking error while compared with traditional feature matchingtracking methods.
1）在深入分析和讨论融合上下文信息（contextual information）的目标特征建模理论的基础上，总结提出了三种目标特征建模框架。针对目标特征建模中的特征提取和表达问题，详细比较了不同的局部不变性特征检测与描述方法。同时，重点分析了具有一体化上下文建模优势的条件随机场（Conditional Random Field，CRF）模型，研究了不同扩展形式CRF模型的上下文信息利用能力以及面向目标特征建模应用的关键问题。
2）提出了基于局部特征分组和多目标优化的目标特征匹配方法，通过对特征上下文的利用能够有效克服图像模糊引起的误匹配。首先，使用图像仿射不变区域特征对不变性点特征做出范围约束，并引入特征间的几何定序信息实现了局部特征分组设计；其次，完成了特征匹配的多目标优化问题建模，提出一种新的离散多目标粒子群优化算法实现了局部特征分组的最佳匹配搜索。同不考虑上下文信息的局部特征匹配方法相比，该方法有效提高了目标特征匹配的鲁棒性。
3）提出了一种基于分层上下文表达的扩展CRF模型，实现了显著类内变化条件下单实例目标类的有效检测。针对经典CRF模型在目标特征建模中的不足，基于部件建模理论提出了CHCRF（Contextual Hierarchical Part-Driven CRF）模型，详细设计了模型的图结构、势函数、以及参数估计与模型推断方法。同时，提出了该模型的加权邻域结构形式，解决了邻域节点间依赖程度的表达问题。CHCRF模型的主要优势是能够同时利用目标图像中潜在的部件层上下文和观测层上下文信息，实现目标类及其内部隐含信息的统一建模。
4）针对UAV多实例目标检测问题，提出了基于多任务分解的MFCRF（Multi-task Factorial CRF）模型，解决了模型设计和实现中的关键问题。同单一标记任务的CRF模型相比，MFCRF模型的主要优势是建立了目标多元部件标记任务和二元目标标记任务的融合框架，能够以互补的形式融入不同任务标记间的相关性信息，从而更好地利用标记层上下文。实验结果表明，相比于现有的其它扩展CRF模型，MFCRF模型具有更强的目标建模与检测能力。
5）提出了基于时空上下文CRF模型的目标跟踪算法，有效解决了复杂动态场景中视觉目标跟踪的模型漂移问题。通过将经典CRF模型扩展到时域空间，提出了融入时空上下文信息的三维STCRF（Spatial-Temporal CRF）模型，设计了模型的时域邻域系统。该模型不仅能够借助目标标记的空间邻域相容性应对目标姿态变化和图像模糊，而且可以引入时域平滑约束对目标标记在跟踪中的连续性建模。进一步，设计了基于STCRF模型标记结果的目标跟踪算法和模型更新策略，实现了目标的稳健描述与跟踪。实验结果表明，论文所提算法相比于传统的局部特征匹配跟踪，平均跟踪误差显著降低。
The perception of high-value targets in battle space is a foundational and keyproblem for an unmanned aerial vehicle (UAV) system to achieve autonomous control.As one of the essential contents of object information processing, object featuremodeling plays a connecting role in the process of UAV battlefield awareness. However,due to the high complexity and dynamics of the battlefield environment, the actualimages acquired by UAV usually have large uncertainty, which makes the establishmentof a reliable object model become a very challenging task. Under such a background,this dissertation focuses on the problem of object feature modeling, including threetypical applications, i.e. object feature matching, object category detection, and objecttracking. The main work and contributions of this dissertation are summarized asfollows:
1) On the basis of in-depth analysis and discussion of the object feature modelingtheory with contextual information, the dissertation proposes three object featuremodeling frameworks. Aiming at the problems of feature extraction and expression inobject modeling, different detection methods and description types of local invariantfeatures are discussed in detail. Meanwhile, conditional random field (CRF) model,which has the unified framework for contextual information modeling, is analyzedemphatically. The abilities of using contextual information and key problems in objectfeature modeling for various extended forms of CRF model are studied.
2) A novel feature point matching method that benefits from local-feature-groups(LFGs) and the multi-objective optimization theory is proposed, which can effectivelyreduce the mismatches caused by image ambiguities. Fisrt of all, LFGs are constructedthrough grouping affine invariant point features and regional features. Regional featuresmake a range constraint to point features, and geometrical ordering contextualinformation in each group is introduced to enhance robustness and discrimination ofLFGs. Then, feature point matching is formulated as a multi-objective optimizationproblem, and the optimal search is realized by using a novel discrete multi-objectiveparticle swarm optimization algorithm. Experimental results show that the proposedmethod can effectively improve robustness of object feature matching while comparedwith those without contextual information.
3) In order to overcome the drawbacks of the classical CRF model for objectcategory detection, a contextual hierarchical part-driven CRF (CHCRF) model isproposed in the dissertation, which can effectively detect single-instance object categorywith notable intra-class variations. The graph structure, potential functions, parameterestimation and inference methods of CHCRF model are designed, respectively.Meanwhile, a weighted neighborhood structure is developed to capture the degree of correlation between connected nodes in the model. By using a two-layer hierarchicalformulation of labels, CHCRF model can effectively represent label-level context andobservation-level context simultaneously, and achieve unified modeling of objectcategory and its internal latent context.
4) For multi-instance object detection, the dissertation proposes a multi-taskfactorial CRF (MFCRF) model to tightly combine the task of multiclass part labelingwith the task of binary object labeling. By fusing different types of labels, the MFCRFmodel can make full use of label-level contextual information. Experimental resultsshow that the modeling capability and detection performance of MFCRF model aresuperior to other existing extended forms of CRF model.
5) To solve the drift problem of object model for visual tracking in complexdynamic scenes, a novel CRF model with spatial-temporal contextual information isproposed. By extending the classic CRF model in the time domain, the definition of thetime-domain neighborhood system is developed, and a spatial-temporal CRF (STCRF)model is proposed. The main characteristic of the model is that it can not only use thecompatibility of spatial neighborhood to deal with pose variations and image ambiguity,but also use the time domain smoothness constraint to model the continuity of objectlabels. Furthermore, an object tracking algorithm and a model update strategy based onlabeling results from STCRF model are designed to achieve robust object descriptionand tracking. Experimental results show that the proposed algorithm can significantlyreduce the average tracking error while compared with traditional feature matchingtracking methods.
引文
[1] Fahlstrom P. G., Gleason T. J.(著),吴汉平(译).无人机系统导论[M].北京:电子工业出版社,2003.
[2]沈林成,徐昕,朱华勇,胡天江.移动机器人自主控制理论与技术[M].北京:科学出版社,2011.
[3]沈林成,牛轶峰,朱华勇.多无人机自主协同控制理论与方法[M].北京:国防工业出版社,2013.
[4]朱华勇,牛轶峰,沈林成,张国忠.无人机系统自主控制技术研究现状与发展趋势[J].国防科技大学学报,2010,32(3):115-120.
[5] Department of Defense. Unmanned aircraft systems roadmap2007-2032[R].USA, Washington DC: DoD,2007.
[6]王永明,王贵锦.图像局部不变性特征与描述[M].北京:国防工业出版社,2010.
[7] Parasuraman R, Sheridan T B, and Wickens C.D. A model for types and levels ofhuman interaction with automation [J]. IEEE Transactions on Systems, Man andCybernetics (S1083-4427),2000,30(3):286-297.
[8] B. T. Clough. Unmanned aerial vehicles: autonomous control challenges, aresearcher's perspective [J]. Journal of Aerospace Computing, Information andCommunication (1542-9423),2003,2(8):327-347.
[9] B. T. Clough. Metrics, Schmetrics! How the heck do you determine a UAV’sautonomy anyway [C]. Proceedings of the2002PerMis Workshop, Gaithersburg,MD,2002.
[10] Collins R, Lipton A, Kanade T, et al. A system for video surveillance andmonitoring, VSAM final report[R]. USA: Carnegie Mellon University,2000.
[11] R. P. Higgins. Automatic event recognition for enhanced situation awareness inUAV video [C]. IEEE Military Communication Conference (MILCOM2005),2005.
[12] Kumar R, Sawhney H, Samarasekera S, Hsu S, et al. Aerial video surveillance andexploitation [J]. Proceedings of the IEEE (0018-9219),2001,89(10):1518-1539.
[13] A. Ollero, S. Lacroix, et al. Multiple eyes in the skies: architecture and perceptionissues in the COMETS unmanned air vehicles project [J]. IEEE Robotics andAutomation Magazine (1070-9932),2005,12(2):46-57.
[14] A. Ollero, G. Hommel et al. COMETS: A multiple heterogeneous UAV system[C]. IEEE International Workshop on Safety Security and Rescue Robotics, Bonn,Germany,2004.
[15] Moraver H P. Towards automatic visual obstacle avoidance [C]. Proceedings of5th International Joint Conference on Artificial Intelligence,1977.
[16] C. Harris and M. Stephens. A combined corner and edge detector [C]. AlveyVision Conference, Univ. Manchester,1988.
[17] P. Beaudet. Rotationally invariant image operators [C]. Proceedings of theInternational Joint Conference on Pattern Recognition,1978:579–583.
[18] T. Lindeberg. Feature detection with automatic scale selection [J]. InternationalJournal of Computer Vision,30(2):77–116,1998.
[19] K. Mikolajczyk and C. Schmid. An affine invariant interest point detector [C].Proceedings of the8th International Conference on Computer Vision, Vancouver,Canada,2002.
[20] D. G. Lower. Object recognition from local scale-invariant feature [C].International Conference on Computer Vision, Corfu, Greece,1999.
[21] H. Bay, T. Tuytelaars, and van Gool L. SURF: Speeded up robust features [C].European Conference on Computer Vision,2006.
[22] J. Matas, O. Chum, M. Urban and T. Pajdla. Robust wide baseline stereo frommaximally stable extremal regions [C]. British Machine Vision Conference,2002.
[23] G. Csurka, C. R. Dance, L. Fan, J. Willamowski, and C. Bray. Visualcategorization with bags of keypoints [C]. Workshop on Statistical Learning inComputer Vision, ECCV,2004:1–22.
[24] K. Grauman and T. Darrell. The pyramid match kernel: discriminativeclassification with sets of image features[C]. Proceedings of IEEE InternationalConference on Computer Vision, volume2,2005:1458–1465.
[25] F. Jurie and B. Triggs. Creating efficient codebooks for visual recognition [C].Proceedings of IEEE International Conference on Computer Vision, volume1,2005:604–610.
[26] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramidmatching for recognizing natural scene categories [C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2006:2169–2178.
[27] M. Marsza lek and C. Schmid. Spatial weighting for bag-of-features [C].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,volume2,2006:2118–2125.
[28] E. Nowak, F. Jurie, and B. Triggs. Sampling strategies for bag-of-features imageclassification [C]. Proceedings of European Conference on Computer Vision,2006:490–503.
[29] J. Sivic and A. Zisserman. Video Google: a text retrieval approach to objectmatching in videos [C]. Proceedings of IEEE International Conference onComputer Vision, volume2,2003:1470–1477.
[30] J. C. van Gemert, J. M. Geusebroek, C. J. Veenman, and A. W. M. Smeulders.Kernel codebooks for scene categorization [C]. Proceedings of EuropeanConference on Computer Vision,2008.
[31] J. M. Winn, A. Criminisi, and T. Minka. Object categorization by learneduniversal visual dictionary [C]. Proceedings of IEEE International Conference onComputer Vision, volume2,2005:1800–1807.
[32] L. Yang, R. Jin, R. Sukthankar, and F. Jurie. Unifying discriminative visualcodebook generation with classifier training for object category recognition [C].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2008:1–8.
[33] J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid. Local features and kernelsfor classification of texture and object categories: A comprehensive study [J].International Journal of Computer Vision,2007,73(2):213–238.
[34] J. Goldberger, S. Roweis, G. Hinton, and R. Salakhutdinov. Neighborhoodcomponent analysis [C]. Advances in Neural Information Processing Systems,2004.
[35] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramidmatching for recognizing natural scene categories [C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2006:2169–2178.
[36] M. Fischler and R. Elschlager. The representation and matching of pictorialstructures [J]. IEEE Transactions on Computer,1973, c-22(1):67–92.
[37] S. Agarwal, A. Awan, and D. Roth. Learning to detect objects in images via asparse, part-based representation [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,26(11):1475–1490,2004.
[38] D. Crandall and D. Huttenlocher. Weakly supervised learning of part-based spatialmodels for visual object recognition [C]. Proceedings of European Conference onComputer Vision, pages I:16–29,2006.
[39] D. J. Crandall, P. Felzenszwalb, and D. P. Huttenlocher. Spatial priors forpart-based recognition using statistical models [C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition, volume1, pages10–17,2005.
[40] R. Fergus, P. Perona, and A. Zisserman. Object class recognition by unsupervisedscale-invariant learning [C]. Proceedings of IEEE Conference on ComputerVision and Pattern Recognition, volume2, pages264–271,2003.
[41] L. Leibe, A. Leonardis, and B. Schiele. Combined object categorization andsegmentation with an implicit shape model [C]. ECCV Workshop on StatisticalLearning in Computer Vision,2004.
[42] P. Felzenszwalb, D. McAllester, and D. Ramanan. A discriminatively trained,multiscale, de-formable part model [C]. Proceedings of IEEE Conference onComputer Vision and Pattern Recognition,2008.
[43] M. Weber, M. Welling, and P. Perona. Unsupervised learning of models for objectrecognition [C]. Proceedings of the European Conference on Computer Vision,pages18–32,2000.
[44] S. Lazebnik, C. Schmid, J. Ponde. A maximum entropy framework for part-basedtexture and object recognition [C]. International Conference on Computer Vision,2005.
[45] S. Lazebnik, C. Schmid, J. Ponde. A sparse texture representation using localaffine region [J]. International Transaction on Pattern Analysis and MachineIntelligence,2005,27(8):1265-1278.
[46] M. Weber, M. Welling, P. Perona. Towards automatic discovery of objectcategories [C]. IEEE Conference on Computer Vision and Pattern Recognition,volume2,2000:2101-2109.
[47] R. Fergus, P. Perona, and A. Zisserman. Object class recognition by unsupervisedscale invariant learning [C]. IEEE Conference on Computer Vision and PatternRecognition,2003.
[48] L. Fei-Fei, R. Fergus, and P. Perona. A Bayesian approach to unsupervisedone-shot learning of object categories [C]. Proceedings of IEEE InternationalConference on Computer Vision,2003
[49] R. Fergus, P. Perona, and A. Zisserman. A sparse object category model forefficient learning and exhaustive recognition [C]. Proceedings of the IEEEConference on Computer Vision and Pattern Recognition, volume1,2005:380–397.
[50] D. J. Crandall, P. Felzenszwalb, and D. P. Huttenlocher. Spatial priors forpart-based recognition using statistical models [C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition, volume1,2005:10–17.
[51] H. Arora, N. Loeff, D.Forsyth, N. Ahuja. An efficient model for automatic objectdetection and segmentation [C]. In IEEE Conference on Computer Vision andPattern Recognition,2007.
[52] N. Loeff, H. Arora, A. Sorokin, D.Forsyth. Efficient unsupervised learning forlocalization and detection in object categories [M]. Advances in NeuralInformation Processing Systems18, Cambrige, MA, USA, MIT Press,2005
[53] S. Z. Li, Markov random field modeling in image analysis [M], Springer-Verlag,2001.
[54] J. M. Hammersley and P. Clifford, Markov field on finite graphs and lattices [Z].Unpublished,1971.
[55] J. Besag, Spatial interaction and the statistical analysis of lattice systems [J].Journal of the Royal Statistical Society B,1974,36:192-236.
[56] U. Grenander, Tutorials in pattern synthesis [Z]. Brown University,1983.
[57] S. Geman and D. Geman, Stochastic relaxation, Gibbs distributions, and theBayesian restoration of images [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,1984,6(6):721-741.
[58]钟平.面向图像标记的随机场模型研究[D].国防科技大学,博士学位论文,2008.
[59] J. Lafferty, A. McCallum, and F. Pereira, Conditional random fields: probabilisticmodels for segmenting and labeling sequence data [C]. International Conferenceon Machine Learning,2001.
[60] S. Kumar and M. Hebert, Discriminative random fields: A discriminativeframework for contextual interaction in classification [C], IEEE InternationalConference on Computer Vision2003:1150-1157.
[61] S. Kumar and M. Hebert. Multiclass discriminative fields for parts-based objectdetection [C]. Snowbird Learning Workshop, Utah, March2004.
[62] A. Quattoni, S. Wang, L.-P. Morency, et al. Hidden conditional random fields [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(10):1848-1853.
[63] A. Kapoor and J. Winn. Located hidden random fields: Learning discriminativeparts for object detection [C]. Proceedings of European Conference on ComputerVision (ECCV’06), Austria, May2006:302-315.
[64] A. Torralba, K. P. Murphy, and W. T. Freeman. Contextual models for objectdetection using boosted random fields [J]. Neural Information Processing Systems.2004.
[65] S. Kumar. Discriminative graphical models for context-based classification [J].Studies in Computational Intelligence,2010,285:109-134.
[66] M. Heikkila, M. Pietikainen, and C. Schmid. Description of interest regions withcenter-symmetric local binary patterns [C]. Proceedings of InternationalConference on Computer Vision,2006:58-69.
[67] Mortensen, E.N., Deng, H.L., Shapiro, L.: A SIFT descriptor with global context[C]. IEEE Computer Society Conference on Computer Vision and PatternRecognition,2005:184-190.
[68] Kim, J., Choi, O., Kweon, I.S. Efficient feature tracking for scene recognitionusing angular and scale constraints [C]. IEEE/RSJ International Conference onIntelligent Robots and Systems,2008:4086-4091.
[69] Choi, O, Kweon, I.S. Robust feature point matching by preserving local geometricconsistency [J]. Computer Vision and Image Understanding.2009,113(6):726-742.
[70] Lindeberg T. Detecting salient blob-like image structures and their scales with ascale-space primal sketch: a method for focus-of-attention [J]. InternationalJournal of Computer Vision,1993,11(3).
[71] Kadir T, Zissserman A, Brady M. An affine invariant salient detector [C].Proceedings of the8th European Conference on Computer Vision, Prague, CzechRepublic,2004.
[72] Lindeberg T. Scalle-space [J]. Encyclopedia of Computer Science andEngineering.2008(6).
[73] Klinger A. Pattern and search statistics [M]. In Rustagi J S, ed. OptimizingMethods in Statistics. NewYork: Academic Press,1971.
[74] Witkin A P. Scale-space filtering [C]. Proceedings of8th International JointConference on Artificial Intelligence. Germany,1983.
[75] J.Koenderink, J. Jan. The structure of images [J]. Biological Cybernetics,1984(50).
[76] Lindeberg T. Scalle-space theory in computer vision [M]. Kluwer AcademicPublisher,1994.
[77] Florack L M, J. ter Haar Romeny, et al. Scale and the differential structure ofimages [J]. Image and Vision Computing.1992,10(6).
[78] Lindeberg T. Principles for automatic scale selection [R]. Technical Report ISRNKTH NA/P-98/14-SE. Sweden,1998.
[79]罗四维.视觉感知系统信息处理理论[M].北京:电子工业出版社,2006.
[80] Heymann S, Mller K, Smolic A, et al. SIFT Implementation and Optimization forgeneral-purpose GPU[C]. Proceedings of the15th International Conference inCentral Europe on Computer Graphics, Visualization and Computer Vision,2007.
[81] Mikolajczyk K, Schmid C. Scale&affine invariant interest point detectors [J].International Journal on Computer Vision,2004,60(1).
[82] Simard P, Bottou L, Haffner P, et al. Boxlets: a fast convolution algorithm forsignal processing and neural networks [J]. Advances in Neural InformationProcessing System,1999.
[83] Viola P, Jones M. Rapid object detection using a boosted cascade of simplefeatures [C]. IEEE Conference on Computer Vision and Pattern Recognition,2001.
[84] Mikolajczyk K, Tuytelaars T, Schmid C, et al. A comparison of affine regiondetectors [J]. International Journal of Computer Vision,2005,65(1/2).
[85] Canny J. A computational approach to edge detection [J]. IEEE Transaction onPattern Analysis and Machine Intelligence,1986, PAMZ-8(6).
[86] Tuytelaars T, Van Gool L. Matching widely separated views based on affineinvariant regions [J]. International Journal of Computer Vision,2004,59(1).
[87] Kadir T. Brady M. Scale, saliency and image description [J]. International Journalof Computer Vision,2001,45(2).
[88] Kadir T. Zisserman A, Brady M. An affine invariant salient region detector [C].Proceedings of the8th European Conference on Computer Vision, Prague, CzechRepublic,2004.
[89] Lowe D G. Distinctive image features from scale-invariant keypoints [J].International Journal of Computer Vision,2004,60(2).
[90] Bay H, Tuytelaars T, van Gool L. Speeded up robust features (SURF)[J].Computer Vision and Image Understanding,2008.
[91] Ye K, Sukthankar R. PCA-SIFT: A more distinctive representation for localimage descriptors [C]. Proceedings of the Conference on Computer Vision andPattern Recognition, Washington, USA,2004:511-517.
[92] Belongie S, Malik J, Puzicha J. Shape matching and object recognition usingshape contexts [J]. IEEE Transaction on Pattern Recognition and MachineIntelligence,2002,2(4).
[93] Johnson A, Herbert M. Using spin images for efficient object recognition incluttered3d scenes [J]. IEEE Transaction on Pattern Recognition and MachineIntelligence,1999,21(5).
[94] S. Lazebnik, C. Schmid, and J. Ponce. Sparse texture representation usingaffine-invariant neighborhoods [C]. Proceedings of IEEE Conference onComputer Vision and Pattern Recognition, volume2,2003:319–324.
[95] S. Lazebnik, C. Schmid, and J. Ponce. A sparse texture representation using localaffine regions [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2005,27(8):1265–1278.
[96] K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors [J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2005,27(10):1615–1630.
[97] Freeman W. and Adelson E. The design and use of steerable filters [J]. IEEETransaction on Pattern Recognition and Machine Intelligence,1991,13(9).
[98] Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets [C].Proceedings of7th European Conference on Computer Vision,2002.
[99] Koenderink J, Van Doorn A. Representation of local geometry in the visualsystem [J]. Biological Cybernetics.1986,55.
[100] Van Gool L, Moons T, Ungureanu D. Affine/Photometric invariants for planarintensity patterns [C]. Proceedings of4th European Conference on ComputerVision,1996.
[101] Whittaker J. Graphical models in applied multivariate statistics [M]. NewYork:JohnWiley and Sons lnc,1990.
[102] Wang Y, Vassileva J. Bayesian network-based trust model [C]. Proceedings ofIEEE International Conference on Web Intelligence, Halifax, Canada,2003:372-378.
[103] Chen J.C, Wang Y.C, Maa C.S, et al. Network-side mobile position location usingfactor graphs [J]. IEEE Transactions on Wireless Communications,2006,5(10):2696-2704.
[104] Pearl J. Probabilistic reasoning in intelligent systems: networks of plausibleinference [M]. California, USA, Morgan Kaufmann Publishers Inc,1988.
[105]李杰.隐马尔可夫模型的研究及其在图像识别中的应用[D].北京:清华大学,2004.
[106] S. Z. Li. Markov random field modeling in image analysis [M], Springer-Verlag,2001.
[107] S. Geman and D. Geman. Stochastic relaxation, Gibbs distributions, and theBayesian restoration of images [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,1984,6(6):721-741.
[108]吕庆文.基于互信息量与马尔可夫随机场的图像分割研究[D].广州:第一军医大学,2007.
[109] S. Kumar. Models for learning spatial interactions in natural images forcontext-based classification [D]. Pittsburgh, Carnegie Mellon University, PhDthesis,2005.
[110] W. Pieczynski and A. N. Tebbache. Pairwise markov random fields andsegmentation of textured images [J]. Machine Graphics&Vision,2000,9(3):705-718.
[111] S. Kumar and M. Hebert. Discriminative fields for modeling spatial dependenciesin natural Images [J]. Neural Information Processing Systems,2003.
[112] S. Kumar and M. Hebert. Approximate parameter learning in discriminative fields[C], Snowbird Learning Workshop,2004.
[113] C. H. Lee, S. Wang, F. Jiao, D. Schuurmans, and R. Greiner, Learning to modelspatial dependency: semi-supervised discriminative random fields [J]. NeuralInformation Processing Systems,2006.
[114] S. Kumar and M. Hebert. Discriminative random fields [J]. International Journalof Computer Vision,2006,68(2):179-201.
[115] M. Szummer and Y. Qi. Contextual recognition of hand-drawn diagrams withconditional random fields [C]. Proceedings of the9th International Workshop onFrontiers in Handwriting Recognition,2004:32-37.
[116] Y. Qi, M. Szummer, and T. P. Minka. Diagram structure recognition by bayesianconditional random fields [C]. IEEE Conference on Computer Vision and PatternRecognition,2005:191-196.
[117] W. Jiang, S. F. Chang, and A. C. Loui. Context-based concept fusion with boostedconditional random fields [C]. IEEE International Conference on Acoustics,Speech and Signal Processing,2007:949-952.
[118] L. Liao, T. Choudhury, D. Fox, and H. Kautz, Training conditional randomfields using virtual evidence boosting [C]. International Joint Conference onArtificial Intelligence2007:2530-2535.
[119] C. Liu, R. Szeliski, S. B. Kang, C. L. Zitnick, and W. T. Freeman. Automaticestimation and removal of noise from a single image [J]. IEEE Transactions onPattern Analysis and Machine Intelligence,2008,30(2):299-314.
[120] T. M. T. Do and T. Artières. Polynomial conditional random fields for signalprocessing [J]. Frontiers in Artificial Intelligence and Applications,2006,141:797-798.
[121] J. Yuan, J. Li, and B. Zhang. Exploiting spatial context constraints for automaticimage region annotation [C]. International Conference on Multimedia,2007.
[122] C. H. Lee, M. Schmidt, A. Murtha, et al. Segmenting brain tumors withconditional random fields and support vector machines [J]. Lecture Notes inComputer Science,2005,3765:469-478.
[123] C. H. Lee, R. Greiner, and M. Schmidt. Support vector random fields for spatialclassification [J]. Lecture Notes in Computer Science,2005,3721:121-132.
[124] C. H. Lee, R. Greiner, and O. Za ane. Efficient spatial classification usingdecoupled conditional random fields [J]. Lecture Notes in Computer Science,2006,4213:272-283.
[125] J. Lafferty, X. Zhu, Y. Liu. Kernel conditional random fields: representation andclique selection [C]. International Conference on Machine Learning,2004.
[126] Y. Y. Wang, A. Acero, M. Mahajan, and J. Lee. Combining statistical andknowledge-based spoken language understanding in conditional models [C].Proceedings of the COLING/ACL on Main Conference Poster Sessions,2006:882-889.
[127] Y. H. Sung, C. Boulis, C. Manning, and D. Jurafsky. Regularization, adaptation,and non-independent features improve hidden conditional random fields for phoneclassification [C]. IEEE Workshop on Automatic Speech Recognition andUnderstanding,2007:347-352.
[128] M. Szummer. Learning diagram parts with hidden random fields [C]. InternationalConference on Document Analysis and Recognition,2005:1188-1193.
[129] Quattoni, M. Collins, and T. Darrell. Conditional random fields for objectrecognition [J]. Neural Information Processing Systems,2004.
[130] M. Welling and C. Sutton. Learning in Markov random fields with contrastivefree energies [C]. International Workshop on Artificial Intelligence and Statistics,2005:397-404.
[131] S. Reiter, B. O. Schuller, and G. Rigoll. Hidden conditional random fields formeeting segmentation [C]. IEEE International Conference on Multimedia andExpo,2007:639-642.
[132] S. B. Wang, A. Quattoni, L. P. Morency, D. Demirdjian, and T. Darrell. Hiddenconditional random fields for gesture recognition [C]. IEEE Conference onComputer Vision and Pattern Recognition,2006:1521-1527.
[133] M. Mahajan, A. Gunawardana, and A. A cero. Training algorithms for hiddenconditional random fields [C]. International Conference on Acoustics, Speech,and Signal Processing,2006.
[134] Y. P. Chu., X. Z. Ye, J. Qian, Y. Zhang, and S. Y. Zheng. Adaptive foregroundand shadow segmentation using hidden conditional random fields [J]. Journal ofZhejiang University SCIENCE A,2007,8(4):586-592.
[135] L. P. Morency, A. Quattoni, and T. Da rrell. Latent-dynamic discriminativemodels for continuous gesture recognition [C]. IEEE Conference on ComputerVision and Pattern Recognition,2007.
[136] Quattoni, M. Collins, and T. Darrell. Incorporating semantic constraints into adiscriminative categorization and labelling model [C]. IEEE InternationalConference on Computer Vision,2005:1877-1877.
[137] Y. H. Sung, C. Boulis, and D. Jurafsky. Maximum conditional likelihood linearregression and maximum a posteriori for hidden conditional random fieldsspeaker adaptation [C]. IEEE International Conference on Acoustics, Speech andSignal Processing,2008:4293-4296.
[138]褚一平，张引，叶修梓，张三元.基于隐条件随机场的自适应视频分割算法.自动化学报,2007,33(12):1252-1258.
[139] Kapoor and J. Winn. Located hidden random fields: learning discriminative partsfor object detection [J]. Lecture Notes in Computer Science,2006,3953:302-315.
[140] J. Winn and J. Shotton. The layout consistent random field for recognizing andsegmenting partially occluded objects [C]. IEEE Conference on Computer Visionand Pattern Recognition,2006:37-44.
[141] D. Hoiem, C. Rother, and J. Winn.3D layoutCRF for multi-view object classrecognition and segmentation [C]. IEEE Conference on Computer Vision andPattern Recognition,2007.
[142] C. Sutton and A. McCallum. Composition of conditional random fields fortransfer learning [C]. Proceedings of the Conference on Human LanguageTechnology and Empirical Methods in Natural Language Processing,2005:748-754.
[143] A. McCallum, K. Rohanimanesh, and C. Sutton. Dynamic conditional randomfields for jointly labeling multiple sequences [C]. Neural Information ProcessingSystem Workshop on Syntax, Semantics and Statistics,2003.
[144] C. Sutton, K. Rohanimanesh, and A. McCallum. Dynamic conditional randomfields: factorized probabilistic models for labeling and segmenting sequence data[C]. International Conference on Machine Learning,2004:282-289.
[145] M. Shimosaka, T. Mori, and T. Sato. Robust action recognition and segmentationwith multi-task conditional random fields. IEEE International Conference onRobotics and Automation. Roma,2007:3780-3786.
[146] L. Wang and D. Suter. Recognizing human activities from silhouettes: motionsubspace and factorial discriminative graphical model [C]. IEEE Conference onComputer Vision and Pattern Recognition,2007.
[147] T. Y. Wu, C. C. Lian, and J. Y. J. Hsu. Joint recognition of multiple concurrentactivities using factorial conditional random fields [C]. AAAI Workshop on Plan,Activity, and Intent Recognition,2007.
[148] S. Kumar and M. Hebert. A hierarchical field framework for unifiedcontext-based classification [C]. IEEE International Conference on ComputerVision,2005:1284-1291.
[149] J. Reynolds and K. Murphy. Figure-ground segmentation using a hierarchicalconditional random field [C]. Canadian Conference on Computer and RobotVision2007:175-182.
[150] L. Liao, D. Fox, and H. Kautz. Hierarchical conditional random fields forGPS-based activity recognition [C], Springer Tracts in Advanced Robotics,2007,28:487-506.
[151] L. Liao, D. Fox, and H. Kautz, Extracting places and activities from GPS tracesusing hierarchical conditional random fields [J]. International Journal of RoboticsResearch,2007,26(1):119-134.
[152] T. Cohn and P. Blunsom. Semantic role labelling with tree conditional randomfields [C]. Proceedings CoNLL-2005:9th Conference on Computational NaturalLanguage,2005.
[153] J. Tang, M. Hong, J. Li, and B. Liang. Tree-structured Conditional RandomFields for Semantic Annotation [C] Lecture Notes in Computer Science,2006,4273:640-653.
[154] D. Ramanan and C. Sminchisescu. Training deformable models for localization[C]. IEEE Conference on Computer Vision and Pattern Recognition,2006:206-213.
[155] P. Awasthi, A. Gagrani, and B. Ravindran. Image modeling using tree structuredconditional random fields [C]. International Joint Conferences on ArtificialIntelligence,2007:2060-2065.
[156] C. Sutton, M. Sindelar, and A. McCallum. Reducing weight under training instructured discriminative learning [C]. Conference on Human LanguageTechnology and North American Association for Computational Linguistics,2006:89-95.
[157] T. Kudo, K. Yamamoto, and Y. Matsumoto. Applying conditional random fieldsto Japanese morphological analysis [C]. Conference on Empirical Methods inNatural Language Processing,2004.
[158] T. H. Tsai, W. C. Chou, S. H. Wu, et al. Integrating linguistic knowledge into aconditional random field framework to identify biomedical named entities [J].Expert Systems with Applications,2006,30(1):117-128.
[159] T. L. Wong and W. Lam. Learning to extract and summarize hot item featuresfrom multiple auction web sites [J]. Knowledge and Information Systems,2008,14(2):143-160.
[160] P. Singla and P. Domingos. Object identification with attribute-mediateddependences [C]. Lecture Notes in Computer Science,2005,3721:297-308.
[161] B. Limketkai, D. Fox, and L. Liao. CRF-Filters: discriminative particle filters forsequential state estimation [C]. IEEE International Conference on Robotics andAutomation2007:3142-3147.
[162] T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum. Learning to detect a salientobject [C]. IEEE Conference on Computer Vision and Pattern Recognition,2007.
[163] D. Scharstein and C. Pal. Learning conditional random fields for stereo [C]. IEEEConference on Computer Vision and Pattern Recognition,2007.
[164] A. Mathur and S. Chakrabarti. Accelerating Newton optimization for log-linearmodels through feature redundancy [C]. International Conference on Data Mining,2006:404-413.
[165] I. R. Mansuri and S. Sarawagi. Integrating unstructured data into relationaldatabases [C]. International Conference on Data Engineering,2006.
[166] X. Ren, C. C. Fowlkes, and J. Malik. Figure/Ground assignment in natural images[C]. Lecture Notes in Computer Science,2006,3952:614-627.
[167] L. Stewart, X. He, and R. S. Zemel. Learning flexible features for conditionalrandom fields [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2008,30(8):1415-1426.
[168] H. L. Chieu, W. S. Lee, and L. P. Kaelbling. Activity recognition fromphysiological data using conditional random fields [C]. SMA Symposium,2006.
[169] C. Sun, Y. Guan, X. Wang, and L. Li n. Biomedical named entities recognitionusing conditional random fields model [C]. Lecture Notes in Computer Science,2006,4223:1279-1288.
[170] D. H. Tran, T. H. Pham, K. Satou, and T. B. Ho. Conditional random fields forpredicting and analyzing histone occupancy, acetylation and methylation areas inDNA sequences [C]. Lecture Notes in Computer Science,2006,3907:221-230.
[171] Y. Qiao, J. Liu, and X. Tang. Offline signature verification using onlinehandwriting registration [C]. IEEE Conference on Computer Vision and PatternRecognition,2007.
[172] T. Cohn. Efficient inference in large conditional random fields [C]. Lecture Notesin Computer Science,2006,4212:606-613.
[173] X. H. Phan, L. M. Nguyen, Y. Noguchi, and T.B. Ho. Improving discriminativesequential learning by discovering important association of statistics [J]. ACMTransactions on Asian Language Information Processing,2006,5(4):413-438.
[174] S. Feng, R. Manmatha, and A. McCallum. Exploring the use of conditionalrandom field models and HMMs for historical handwritten document recognition[C]. International Conference on Document Image Analysis for Libraries,2006:30-37.
[175] F. Peng and A. McCallum. Information extraction from research papers usingconditional random fields [J]. Information Processing and Management,2006,42(4):963-979.
[176] G. E. Hinton. Training product of experts by minimizing contrastive divergence[J]. Neural Computation,2002,14:1771–1800.
[177] X. He, R. S. Zemel, and M. A. Carreira-Perpinan. Multiscale conditional randomfields for image labeling [C]. IEEE Conference on Computer Vision and PatternRecognition,2004:695-702.
[178] D. Geiger and F. Girosi. Parallel and deterministic algorithms from MRFs:Surface reconstruction [J]. IEEE Transaction on Pattern Analysis and MachineIntelligence,1991,5(5):401–412.
[179] C. Peterson and J. Anderson. A mean-field theory learning algorithm for neuralnetworks [J].Complex Systems,1987,1:995–1019.
[180] H. Arora, N. Loeff, D. Forsyth, and N. Ahuja. Unsupervised segmentation ofobjects using efficient learning [C]. IEEE Conference on Computer Vision andPattern Recognition,2007.
[181] C. Sminchisescu, A. Kanaujia, and D. Metaxas. Conditional models for contextualhuman motion recognition [J]. Computer Vision and Image Understanding,2006,104(2-3):210-220.
[182] Y. Wang and S. Gong. Refining image annotation using contextual relationsbetween words [C]. ACM International Conference on Image and Video Retrieval,2007:425-432.
[183] B. Douillard, D. Fox, and F. Ramos. A spatio-temporal probabilistic model formulti-sensor object recognition [C]. IEEE/RSJ International Conference onIntelligent Robots and Systems,2007:2402-2408.
[184] J. Weinman, A. Hanson, and A. McCallum. Sign detection in natural images withconditional random fields [C]. IEEE International Workshop on MachineLearning for Signal Processing,2004:549-558.
[185] J. Snoek, J. Hoey, L. Stewart, and R. S. Zemel. Automated detection of unusualevents on stairs [C]. Proceedings of the3rd Canadian Conference on Computerand Robot Vision,2006.
[186] T. Wang, J. Li, W. Hu, X. Tong, Y. Zhang, and C. Dulong. Event detectionmodels using2d-BN and CRFs [C]. Lecture Notes in Computer Science,2007,4352:83-93.
[187] S. Nicolas, J. Dardenne, T. Paquet, and L. Heutte. Document image segmentationusing a2D conditional random field model [C]. International Conference onDocument Analysis and Recognition,2007:407-411.
[188] F. Ramos, D. Fox, and H. Durrant-Whyte. CRF-Matching: conditional randomfields for feature-based scan matching [J]. Robotics: Science and Systems,2007.
[189] X. Ren, C. C. Fowlkes, and J. Malik. Scale-Invariant contour completion usingconditional random fields [C]. IEEE International Conference on ComputerVision,2005:1214-1221.
[190] J. Shotton, JohnWinn, C. Rother, and A. Criminisi. TextonBoost: jointappearance, shape and context modeling for multi-class object recognition andsegmentation [C]. Lecture Notes in Computer Science,2006,3951:1-15.
[191] N. Komodakis and G. Tziritas. Approximate labeling via graph cuts based onlinear programming [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(8):1436-1453.
[192]高琳,唐鹏,盛鹏,左航.复杂条件下基于条件随机场的视觉目标跟踪[J].光学学报,2010,30(6):1721-1728.
[193]罗荣华,闵华清,林盛峰.基于联合条件随机场的移动机器人多目标跟踪[J].机器人.2011,33(3):279-286.
[194] Luo Ronghua, Min Huaqing. Joint conditional random field filter for multi-objecttracking [J]. International Journal of Advanced Robotic Systems,2011,8(1):76-84.
[195]陶霖密,王奇凡,邸慧军.视觉信息处理中的马尔可夫随机场[J].中国图象图形学报.2009,14(9):1705-1711.
[196] Li, C., Ma, L. A new framework for feature descriptor based on SIFT [J]. PatternRecognition Letters.2009,30(5),544-557.
[197] Carneiro, G., Jepson, A.D. Flexible spatial configuration of local Image features[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence.2007,29(12):2089-2014.
[198] Coello Coello, Carlos A. Recent trend in evolutionary multiobjectiveoptimization [A]. Evolutionary Multiobjective Optimization: TheoreticalAdvances and Applications [C]. Springer-Verlag, London,2005:7-32.
[199]牛轶峰.面向AUAV自主控制的图像融合方法研究[D].国防科技大学,博士学位论文,2007.
[200] Pulido G T. On the use of self-adaptation and elitism for multiobjective particleswarm optimization [D]. Ph.D. Dissertation, Electrical Engineering Department,CINVESTAV-IPN, Mexico,2005.
[201] Knowles J D, Corne D W. Approximating the nondominated front using thePareto archived evolution strategy [J]. Evolutionary Computation,2000,8(2):149-172.
[202] Zitzler E, Laumanns M,Thiele L. SPEA2: Improving the strength paretoevolutionary algorithm [R].Technical Report103, Gloriastrasse35, CH-8092Zurieh, Switzerland,2001.
[203] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective geneticalgorithm: NSGA-II [J]. IEEE Transactions on Evolutionary Computation,2002,6(2):182-197.
[204]张勇德,黄莎白.多目标优化问题的蚁群算法研究[J].控制与决策,2005,20(2):170-174.
[205] Coello Coello C A, Pulido G T, Lechuga M S. Handling multiple objectives withparticle swarm optimization [J]. IEEE Transactions on Evolutionary Computation,2004,8(3):256-279.
[206] Kennedy J., Eberhart R. C. Particle swarm optimization [C]. IEEE InternationalConference on Neural Networks. Perth, Australia,1995,1942-1948.
[207]霍霄华.多UCAV动态协同任务规划建模与滚动优化方法研究[D].国防科技大学,博士学位论文,2007.
[208]刘锦峰.图像模板匹配快速算法研究[D].中南大学,硕士学位论文,2007.
[209] S. Gu, Y. Zheng, C.Tomasi. Critical nets and beta-stable features for imagematching [C]. Lecture Notes in Computer Science,2010, part3:663-676.
[210] Leonid Taycher, Leonid Taycher, Gregory Shakhnarovich, et al. Conditionalrandom people: tracking humans with CRFs and grid filters[C]. In IEEEConference on Computer Vision and Pattern Recognition,2006:222-229.
[211] Hai Tao, Harpreet S., Rakesh Kumar. Object tracking with bayesian estimation ofdynamic layer representations [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,2002,24(1):75-89.
[212]章毓晋.图像工程[M].北京:清华大学出版社,2007.
[213] Ji Z, Liao H L, Wang Y W, et al. A novel intelligent particle optimizer for globaloptimization of multimodal functions [C]. IEEE Congress on EvolutionaryComputation, Singapore,2007:3272-3275.
[214] Kass M, Witkinm A, Terzopoulos D. Snakes: Active Contour Models [J].International Journal of Computer Vision,1988, l(4):321-331.
[215] George H. Dunteman(著),吴晓刚(主编).广义线性模型[M].上海:人民出版社,2011.
[2]沈林成,徐昕,朱华勇,胡天江.移动机器人自主控制理论与技术[M].北京:科学出版社,2011.
[3]沈林成,牛轶峰,朱华勇.多无人机自主协同控制理论与方法[M].北京:国防工业出版社,2013.
[4]朱华勇,牛轶峰,沈林成,张国忠.无人机系统自主控制技术研究现状与发展趋势[J].国防科技大学学报,2010,32(3):115-120.
[5] Department of Defense. Unmanned aircraft systems roadmap2007-2032[R].USA, Washington DC: DoD,2007.
[6]王永明,王贵锦.图像局部不变性特征与描述[M].北京:国防工业出版社,2010.
[7] Parasuraman R, Sheridan T B, and Wickens C.D. A model for types and levels ofhuman interaction with automation [J]. IEEE Transactions on Systems, Man andCybernetics (S1083-4427),2000,30(3):286-297.
[8] B. T. Clough. Unmanned aerial vehicles: autonomous control challenges, aresearcher's perspective [J]. Journal of Aerospace Computing, Information andCommunication (1542-9423),2003,2(8):327-347.
[9] B. T. Clough. Metrics, Schmetrics! How the heck do you determine a UAV’sautonomy anyway [C]. Proceedings of the2002PerMis Workshop, Gaithersburg,MD,2002.
[10] Collins R, Lipton A, Kanade T, et al. A system for video surveillance andmonitoring, VSAM final report[R]. USA: Carnegie Mellon University,2000.
[11] R. P. Higgins. Automatic event recognition for enhanced situation awareness inUAV video [C]. IEEE Military Communication Conference (MILCOM2005),2005.
[12] Kumar R, Sawhney H, Samarasekera S, Hsu S, et al. Aerial video surveillance andexploitation [J]. Proceedings of the IEEE (0018-9219),2001,89(10):1518-1539.
[13] A. Ollero, S. Lacroix, et al. Multiple eyes in the skies: architecture and perceptionissues in the COMETS unmanned air vehicles project [J]. IEEE Robotics andAutomation Magazine (1070-9932),2005,12(2):46-57.
[14] A. Ollero, G. Hommel et al. COMETS: A multiple heterogeneous UAV system[C]. IEEE International Workshop on Safety Security and Rescue Robotics, Bonn,Germany,2004.
[15] Moraver H P. Towards automatic visual obstacle avoidance [C]. Proceedings of5th International Joint Conference on Artificial Intelligence,1977.
[16] C. Harris and M. Stephens. A combined corner and edge detector [C]. AlveyVision Conference, Univ. Manchester,1988.
[17] P. Beaudet. Rotationally invariant image operators [C]. Proceedings of theInternational Joint Conference on Pattern Recognition,1978:579–583.
[18] T. Lindeberg. Feature detection with automatic scale selection [J]. InternationalJournal of Computer Vision,30(2):77–116,1998.
[19] K. Mikolajczyk and C. Schmid. An affine invariant interest point detector [C].Proceedings of the8th International Conference on Computer Vision, Vancouver,Canada,2002.
[20] D. G. Lower. Object recognition from local scale-invariant feature [C].International Conference on Computer Vision, Corfu, Greece,1999.
[21] H. Bay, T. Tuytelaars, and van Gool L. SURF: Speeded up robust features [C].European Conference on Computer Vision,2006.
[22] J. Matas, O. Chum, M. Urban and T. Pajdla. Robust wide baseline stereo frommaximally stable extremal regions [C]. British Machine Vision Conference,2002.
[23] G. Csurka, C. R. Dance, L. Fan, J. Willamowski, and C. Bray. Visualcategorization with bags of keypoints [C]. Workshop on Statistical Learning inComputer Vision, ECCV,2004:1–22.
[24] K. Grauman and T. Darrell. The pyramid match kernel: discriminativeclassification with sets of image features[C]. Proceedings of IEEE InternationalConference on Computer Vision, volume2,2005:1458–1465.
[25] F. Jurie and B. Triggs. Creating efficient codebooks for visual recognition [C].Proceedings of IEEE International Conference on Computer Vision, volume1,2005:604–610.
[26] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramidmatching for recognizing natural scene categories [C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2006:2169–2178.
[27] M. Marsza lek and C. Schmid. Spatial weighting for bag-of-features [C].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,volume2,2006:2118–2125.
[28] E. Nowak, F. Jurie, and B. Triggs. Sampling strategies for bag-of-features imageclassification [C]. Proceedings of European Conference on Computer Vision,2006:490–503.
[29] J. Sivic and A. Zisserman. Video Google: a text retrieval approach to objectmatching in videos [C]. Proceedings of IEEE International Conference onComputer Vision, volume2,2003:1470–1477.
[30] J. C. van Gemert, J. M. Geusebroek, C. J. Veenman, and A. W. M. Smeulders.Kernel codebooks for scene categorization [C]. Proceedings of EuropeanConference on Computer Vision,2008.
[31] J. M. Winn, A. Criminisi, and T. Minka. Object categorization by learneduniversal visual dictionary [C]. Proceedings of IEEE International Conference onComputer Vision, volume2,2005:1800–1807.
[32] L. Yang, R. Jin, R. Sukthankar, and F. Jurie. Unifying discriminative visualcodebook generation with classifier training for object category recognition [C].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2008:1–8.
[33] J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid. Local features and kernelsfor classification of texture and object categories: A comprehensive study [J].International Journal of Computer Vision,2007,73(2):213–238.
[34] J. Goldberger, S. Roweis, G. Hinton, and R. Salakhutdinov. Neighborhoodcomponent analysis [C]. Advances in Neural Information Processing Systems,2004.
[35] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramidmatching for recognizing natural scene categories [C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2006:2169–2178.
[36] M. Fischler and R. Elschlager. The representation and matching of pictorialstructures [J]. IEEE Transactions on Computer,1973, c-22(1):67–92.
[37] S. Agarwal, A. Awan, and D. Roth. Learning to detect objects in images via asparse, part-based representation [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,26(11):1475–1490,2004.
[38] D. Crandall and D. Huttenlocher. Weakly supervised learning of part-based spatialmodels for visual object recognition [C]. Proceedings of European Conference onComputer Vision, pages I:16–29,2006.
[39] D. J. Crandall, P. Felzenszwalb, and D. P. Huttenlocher. Spatial priors forpart-based recognition using statistical models [C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition, volume1, pages10–17,2005.
[40] R. Fergus, P. Perona, and A. Zisserman. Object class recognition by unsupervisedscale-invariant learning [C]. Proceedings of IEEE Conference on ComputerVision and Pattern Recognition, volume2, pages264–271,2003.
[41] L. Leibe, A. Leonardis, and B. Schiele. Combined object categorization andsegmentation with an implicit shape model [C]. ECCV Workshop on StatisticalLearning in Computer Vision,2004.
[42] P. Felzenszwalb, D. McAllester, and D. Ramanan. A discriminatively trained,multiscale, de-formable part model [C]. Proceedings of IEEE Conference onComputer Vision and Pattern Recognition,2008.
[43] M. Weber, M. Welling, and P. Perona. Unsupervised learning of models for objectrecognition [C]. Proceedings of the European Conference on Computer Vision,pages18–32,2000.
[44] S. Lazebnik, C. Schmid, J. Ponde. A maximum entropy framework for part-basedtexture and object recognition [C]. International Conference on Computer Vision,2005.
[45] S. Lazebnik, C. Schmid, J. Ponde. A sparse texture representation using localaffine region [J]. International Transaction on Pattern Analysis and MachineIntelligence,2005,27(8):1265-1278.
[46] M. Weber, M. Welling, P. Perona. Towards automatic discovery of objectcategories [C]. IEEE Conference on Computer Vision and Pattern Recognition,volume2,2000:2101-2109.
[47] R. Fergus, P. Perona, and A. Zisserman. Object class recognition by unsupervisedscale invariant learning [C]. IEEE Conference on Computer Vision and PatternRecognition,2003.
[48] L. Fei-Fei, R. Fergus, and P. Perona. A Bayesian approach to unsupervisedone-shot learning of object categories [C]. Proceedings of IEEE InternationalConference on Computer Vision,2003
[49] R. Fergus, P. Perona, and A. Zisserman. A sparse object category model forefficient learning and exhaustive recognition [C]. Proceedings of the IEEEConference on Computer Vision and Pattern Recognition, volume1,2005:380–397.
[50] D. J. Crandall, P. Felzenszwalb, and D. P. Huttenlocher. Spatial priors forpart-based recognition using statistical models [C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition, volume1,2005:10–17.
[51] H. Arora, N. Loeff, D.Forsyth, N. Ahuja. An efficient model for automatic objectdetection and segmentation [C]. In IEEE Conference on Computer Vision andPattern Recognition,2007.
[52] N. Loeff, H. Arora, A. Sorokin, D.Forsyth. Efficient unsupervised learning forlocalization and detection in object categories [M]. Advances in NeuralInformation Processing Systems18, Cambrige, MA, USA, MIT Press,2005
[53] S. Z. Li, Markov random field modeling in image analysis [M], Springer-Verlag,2001.
[54] J. M. Hammersley and P. Clifford, Markov field on finite graphs and lattices [Z].Unpublished,1971.
[55] J. Besag, Spatial interaction and the statistical analysis of lattice systems [J].Journal of the Royal Statistical Society B,1974,36:192-236.
[56] U. Grenander, Tutorials in pattern synthesis [Z]. Brown University,1983.
[57] S. Geman and D. Geman, Stochastic relaxation, Gibbs distributions, and theBayesian restoration of images [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,1984,6(6):721-741.
[58]钟平.面向图像标记的随机场模型研究[D].国防科技大学,博士学位论文,2008.
[59] J. Lafferty, A. McCallum, and F. Pereira, Conditional random fields: probabilisticmodels for segmenting and labeling sequence data [C]. International Conferenceon Machine Learning,2001.
[60] S. Kumar and M. Hebert, Discriminative random fields: A discriminativeframework for contextual interaction in classification [C], IEEE InternationalConference on Computer Vision2003:1150-1157.
[61] S. Kumar and M. Hebert. Multiclass discriminative fields for parts-based objectdetection [C]. Snowbird Learning Workshop, Utah, March2004.
[62] A. Quattoni, S. Wang, L.-P. Morency, et al. Hidden conditional random fields [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(10):1848-1853.
[63] A. Kapoor and J. Winn. Located hidden random fields: Learning discriminativeparts for object detection [C]. Proceedings of European Conference on ComputerVision (ECCV’06), Austria, May2006:302-315.
[64] A. Torralba, K. P. Murphy, and W. T. Freeman. Contextual models for objectdetection using boosted random fields [J]. Neural Information Processing Systems.2004.
[65] S. Kumar. Discriminative graphical models for context-based classification [J].Studies in Computational Intelligence,2010,285:109-134.
[66] M. Heikkila, M. Pietikainen, and C. Schmid. Description of interest regions withcenter-symmetric local binary patterns [C]. Proceedings of InternationalConference on Computer Vision,2006:58-69.
[67] Mortensen, E.N., Deng, H.L., Shapiro, L.: A SIFT descriptor with global context[C]. IEEE Computer Society Conference on Computer Vision and PatternRecognition,2005:184-190.
[68] Kim, J., Choi, O., Kweon, I.S. Efficient feature tracking for scene recognitionusing angular and scale constraints [C]. IEEE/RSJ International Conference onIntelligent Robots and Systems,2008:4086-4091.
[69] Choi, O, Kweon, I.S. Robust feature point matching by preserving local geometricconsistency [J]. Computer Vision and Image Understanding.2009,113(6):726-742.
[70] Lindeberg T. Detecting salient blob-like image structures and their scales with ascale-space primal sketch: a method for focus-of-attention [J]. InternationalJournal of Computer Vision,1993,11(3).
[71] Kadir T, Zissserman A, Brady M. An affine invariant salient detector [C].Proceedings of the8th European Conference on Computer Vision, Prague, CzechRepublic,2004.
[72] Lindeberg T. Scalle-space [J]. Encyclopedia of Computer Science andEngineering.2008(6).
[73] Klinger A. Pattern and search statistics [M]. In Rustagi J S, ed. OptimizingMethods in Statistics. NewYork: Academic Press,1971.
[74] Witkin A P. Scale-space filtering [C]. Proceedings of8th International JointConference on Artificial Intelligence. Germany,1983.
[75] J.Koenderink, J. Jan. The structure of images [J]. Biological Cybernetics,1984(50).
[76] Lindeberg T. Scalle-space theory in computer vision [M]. Kluwer AcademicPublisher,1994.
[77] Florack L M, J. ter Haar Romeny, et al. Scale and the differential structure ofimages [J]. Image and Vision Computing.1992,10(6).
[78] Lindeberg T. Principles for automatic scale selection [R]. Technical Report ISRNKTH NA/P-98/14-SE. Sweden,1998.
[79]罗四维.视觉感知系统信息处理理论[M].北京:电子工业出版社,2006.
[80] Heymann S, Mller K, Smolic A, et al. SIFT Implementation and Optimization forgeneral-purpose GPU[C]. Proceedings of the15th International Conference inCentral Europe on Computer Graphics, Visualization and Computer Vision,2007.
[81] Mikolajczyk K, Schmid C. Scale&affine invariant interest point detectors [J].International Journal on Computer Vision,2004,60(1).
[82] Simard P, Bottou L, Haffner P, et al. Boxlets: a fast convolution algorithm forsignal processing and neural networks [J]. Advances in Neural InformationProcessing System,1999.
[83] Viola P, Jones M. Rapid object detection using a boosted cascade of simplefeatures [C]. IEEE Conference on Computer Vision and Pattern Recognition,2001.
[84] Mikolajczyk K, Tuytelaars T, Schmid C, et al. A comparison of affine regiondetectors [J]. International Journal of Computer Vision,2005,65(1/2).
[85] Canny J. A computational approach to edge detection [J]. IEEE Transaction onPattern Analysis and Machine Intelligence,1986, PAMZ-8(6).
[86] Tuytelaars T, Van Gool L. Matching widely separated views based on affineinvariant regions [J]. International Journal of Computer Vision,2004,59(1).
[87] Kadir T. Brady M. Scale, saliency and image description [J]. International Journalof Computer Vision,2001,45(2).
[88] Kadir T. Zisserman A, Brady M. An affine invariant salient region detector [C].Proceedings of the8th European Conference on Computer Vision, Prague, CzechRepublic,2004.
[89] Lowe D G. Distinctive image features from scale-invariant keypoints [J].International Journal of Computer Vision,2004,60(2).
[90] Bay H, Tuytelaars T, van Gool L. Speeded up robust features (SURF)[J].Computer Vision and Image Understanding,2008.
[91] Ye K, Sukthankar R. PCA-SIFT: A more distinctive representation for localimage descriptors [C]. Proceedings of the Conference on Computer Vision andPattern Recognition, Washington, USA,2004:511-517.
[92] Belongie S, Malik J, Puzicha J. Shape matching and object recognition usingshape contexts [J]. IEEE Transaction on Pattern Recognition and MachineIntelligence,2002,2(4).
[93] Johnson A, Herbert M. Using spin images for efficient object recognition incluttered3d scenes [J]. IEEE Transaction on Pattern Recognition and MachineIntelligence,1999,21(5).
[94] S. Lazebnik, C. Schmid, and J. Ponce. Sparse texture representation usingaffine-invariant neighborhoods [C]. Proceedings of IEEE Conference onComputer Vision and Pattern Recognition, volume2,2003:319–324.
[95] S. Lazebnik, C. Schmid, and J. Ponce. A sparse texture representation using localaffine regions [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2005,27(8):1265–1278.
[96] K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors [J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2005,27(10):1615–1630.
[97] Freeman W. and Adelson E. The design and use of steerable filters [J]. IEEETransaction on Pattern Recognition and Machine Intelligence,1991,13(9).
[98] Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets [C].Proceedings of7th European Conference on Computer Vision,2002.
[99] Koenderink J, Van Doorn A. Representation of local geometry in the visualsystem [J]. Biological Cybernetics.1986,55.
[100] Van Gool L, Moons T, Ungureanu D. Affine/Photometric invariants for planarintensity patterns [C]. Proceedings of4th European Conference on ComputerVision,1996.
[101] Whittaker J. Graphical models in applied multivariate statistics [M]. NewYork:JohnWiley and Sons lnc,1990.
[102] Wang Y, Vassileva J. Bayesian network-based trust model [C]. Proceedings ofIEEE International Conference on Web Intelligence, Halifax, Canada,2003:372-378.
[103] Chen J.C, Wang Y.C, Maa C.S, et al. Network-side mobile position location usingfactor graphs [J]. IEEE Transactions on Wireless Communications,2006,5(10):2696-2704.
[104] Pearl J. Probabilistic reasoning in intelligent systems: networks of plausibleinference [M]. California, USA, Morgan Kaufmann Publishers Inc,1988.
[105]李杰.隐马尔可夫模型的研究及其在图像识别中的应用[D].北京:清华大学,2004.
[106] S. Z. Li. Markov random field modeling in image analysis [M], Springer-Verlag,2001.
[107] S. Geman and D. Geman. Stochastic relaxation, Gibbs distributions, and theBayesian restoration of images [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,1984,6(6):721-741.
[108]吕庆文.基于互信息量与马尔可夫随机场的图像分割研究[D].广州:第一军医大学,2007.
[109] S. Kumar. Models for learning spatial interactions in natural images forcontext-based classification [D]. Pittsburgh, Carnegie Mellon University, PhDthesis,2005.
[110] W. Pieczynski and A. N. Tebbache. Pairwise markov random fields andsegmentation of textured images [J]. Machine Graphics&Vision,2000,9(3):705-718.
[111] S. Kumar and M. Hebert. Discriminative fields for modeling spatial dependenciesin natural Images [J]. Neural Information Processing Systems,2003.
[112] S. Kumar and M. Hebert. Approximate parameter learning in discriminative fields[C], Snowbird Learning Workshop,2004.
[113] C. H. Lee, S. Wang, F. Jiao, D. Schuurmans, and R. Greiner, Learning to modelspatial dependency: semi-supervised discriminative random fields [J]. NeuralInformation Processing Systems,2006.
[114] S. Kumar and M. Hebert. Discriminative random fields [J]. International Journalof Computer Vision,2006,68(2):179-201.
[115] M. Szummer and Y. Qi. Contextual recognition of hand-drawn diagrams withconditional random fields [C]. Proceedings of the9th International Workshop onFrontiers in Handwriting Recognition,2004:32-37.
[116] Y. Qi, M. Szummer, and T. P. Minka. Diagram structure recognition by bayesianconditional random fields [C]. IEEE Conference on Computer Vision and PatternRecognition,2005:191-196.
[117] W. Jiang, S. F. Chang, and A. C. Loui. Context-based concept fusion with boostedconditional random fields [C]. IEEE International Conference on Acoustics,Speech and Signal Processing,2007:949-952.
[118] L. Liao, T. Choudhury, D. Fox, and H. Kautz, Training conditional randomfields using virtual evidence boosting [C]. International Joint Conference onArtificial Intelligence2007:2530-2535.
[119] C. Liu, R. Szeliski, S. B. Kang, C. L. Zitnick, and W. T. Freeman. Automaticestimation and removal of noise from a single image [J]. IEEE Transactions onPattern Analysis and Machine Intelligence,2008,30(2):299-314.
[120] T. M. T. Do and T. Artières. Polynomial conditional random fields for signalprocessing [J]. Frontiers in Artificial Intelligence and Applications,2006,141:797-798.
[121] J. Yuan, J. Li, and B. Zhang. Exploiting spatial context constraints for automaticimage region annotation [C]. International Conference on Multimedia,2007.
[122] C. H. Lee, M. Schmidt, A. Murtha, et al. Segmenting brain tumors withconditional random fields and support vector machines [J]. Lecture Notes inComputer Science,2005,3765:469-478.
[123] C. H. Lee, R. Greiner, and M. Schmidt. Support vector random fields for spatialclassification [J]. Lecture Notes in Computer Science,2005,3721:121-132.
[124] C. H. Lee, R. Greiner, and O. Za ane. Efficient spatial classification usingdecoupled conditional random fields [J]. Lecture Notes in Computer Science,2006,4213:272-283.
[125] J. Lafferty, X. Zhu, Y. Liu. Kernel conditional random fields: representation andclique selection [C]. International Conference on Machine Learning,2004.
[126] Y. Y. Wang, A. Acero, M. Mahajan, and J. Lee. Combining statistical andknowledge-based spoken language understanding in conditional models [C].Proceedings of the COLING/ACL on Main Conference Poster Sessions,2006:882-889.
[127] Y. H. Sung, C. Boulis, C. Manning, and D. Jurafsky. Regularization, adaptation,and non-independent features improve hidden conditional random fields for phoneclassification [C]. IEEE Workshop on Automatic Speech Recognition andUnderstanding,2007:347-352.
[128] M. Szummer. Learning diagram parts with hidden random fields [C]. InternationalConference on Document Analysis and Recognition,2005:1188-1193.
[129] Quattoni, M. Collins, and T. Darrell. Conditional random fields for objectrecognition [J]. Neural Information Processing Systems,2004.
[130] M. Welling and C. Sutton. Learning in Markov random fields with contrastivefree energies [C]. International Workshop on Artificial Intelligence and Statistics,2005:397-404.
[131] S. Reiter, B. O. Schuller, and G. Rigoll. Hidden conditional random fields formeeting segmentation [C]. IEEE International Conference on Multimedia andExpo,2007:639-642.
[132] S. B. Wang, A. Quattoni, L. P. Morency, D. Demirdjian, and T. Darrell. Hiddenconditional random fields for gesture recognition [C]. IEEE Conference onComputer Vision and Pattern Recognition,2006:1521-1527.
[133] M. Mahajan, A. Gunawardana, and A. A cero. Training algorithms for hiddenconditional random fields [C]. International Conference on Acoustics, Speech,and Signal Processing,2006.
[134] Y. P. Chu., X. Z. Ye, J. Qian, Y. Zhang, and S. Y. Zheng. Adaptive foregroundand shadow segmentation using hidden conditional random fields [J]. Journal ofZhejiang University SCIENCE A,2007,8(4):586-592.
[135] L. P. Morency, A. Quattoni, and T. Da rrell. Latent-dynamic discriminativemodels for continuous gesture recognition [C]. IEEE Conference on ComputerVision and Pattern Recognition,2007.
[136] Quattoni, M. Collins, and T. Darrell. Incorporating semantic constraints into adiscriminative categorization and labelling model [C]. IEEE InternationalConference on Computer Vision,2005:1877-1877.
[137] Y. H. Sung, C. Boulis, and D. Jurafsky. Maximum conditional likelihood linearregression and maximum a posteriori for hidden conditional random fieldsspeaker adaptation [C]. IEEE International Conference on Acoustics, Speech andSignal Processing,2008:4293-4296.
[138]褚一平，张引，叶修梓，张三元.基于隐条件随机场的自适应视频分割算法.自动化学报,2007,33(12):1252-1258.
[139] Kapoor and J. Winn. Located hidden random fields: learning discriminative partsfor object detection [J]. Lecture Notes in Computer Science,2006,3953:302-315.
[140] J. Winn and J. Shotton. The layout consistent random field for recognizing andsegmenting partially occluded objects [C]. IEEE Conference on Computer Visionand Pattern Recognition,2006:37-44.
[141] D. Hoiem, C. Rother, and J. Winn.3D layoutCRF for multi-view object classrecognition and segmentation [C]. IEEE Conference on Computer Vision andPattern Recognition,2007.
[142] C. Sutton and A. McCallum. Composition of conditional random fields fortransfer learning [C]. Proceedings of the Conference on Human LanguageTechnology and Empirical Methods in Natural Language Processing,2005:748-754.
[143] A. McCallum, K. Rohanimanesh, and C. Sutton. Dynamic conditional randomfields for jointly labeling multiple sequences [C]. Neural Information ProcessingSystem Workshop on Syntax, Semantics and Statistics,2003.
[144] C. Sutton, K. Rohanimanesh, and A. McCallum. Dynamic conditional randomfields: factorized probabilistic models for labeling and segmenting sequence data[C]. International Conference on Machine Learning,2004:282-289.
[145] M. Shimosaka, T. Mori, and T. Sato. Robust action recognition and segmentationwith multi-task conditional random fields. IEEE International Conference onRobotics and Automation. Roma,2007:3780-3786.
[146] L. Wang and D. Suter. Recognizing human activities from silhouettes: motionsubspace and factorial discriminative graphical model [C]. IEEE Conference onComputer Vision and Pattern Recognition,2007.
[147] T. Y. Wu, C. C. Lian, and J. Y. J. Hsu. Joint recognition of multiple concurrentactivities using factorial conditional random fields [C]. AAAI Workshop on Plan,Activity, and Intent Recognition,2007.
[148] S. Kumar and M. Hebert. A hierarchical field framework for unifiedcontext-based classification [C]. IEEE International Conference on ComputerVision,2005:1284-1291.
[149] J. Reynolds and K. Murphy. Figure-ground segmentation using a hierarchicalconditional random field [C]. Canadian Conference on Computer and RobotVision2007:175-182.
[150] L. Liao, D. Fox, and H. Kautz. Hierarchical conditional random fields forGPS-based activity recognition [C], Springer Tracts in Advanced Robotics,2007,28:487-506.
[151] L. Liao, D. Fox, and H. Kautz, Extracting places and activities from GPS tracesusing hierarchical conditional random fields [J]. International Journal of RoboticsResearch,2007,26(1):119-134.
[152] T. Cohn and P. Blunsom. Semantic role labelling with tree conditional randomfields [C]. Proceedings CoNLL-2005:9th Conference on Computational NaturalLanguage,2005.
[153] J. Tang, M. Hong, J. Li, and B. Liang. Tree-structured Conditional RandomFields for Semantic Annotation [C] Lecture Notes in Computer Science,2006,4273:640-653.
[154] D. Ramanan and C. Sminchisescu. Training deformable models for localization[C]. IEEE Conference on Computer Vision and Pattern Recognition,2006:206-213.
[155] P. Awasthi, A. Gagrani, and B. Ravindran. Image modeling using tree structuredconditional random fields [C]. International Joint Conferences on ArtificialIntelligence,2007:2060-2065.
[156] C. Sutton, M. Sindelar, and A. McCallum. Reducing weight under training instructured discriminative learning [C]. Conference on Human LanguageTechnology and North American Association for Computational Linguistics,2006:89-95.
[157] T. Kudo, K. Yamamoto, and Y. Matsumoto. Applying conditional random fieldsto Japanese morphological analysis [C]. Conference on Empirical Methods inNatural Language Processing,2004.
[158] T. H. Tsai, W. C. Chou, S. H. Wu, et al. Integrating linguistic knowledge into aconditional random field framework to identify biomedical named entities [J].Expert Systems with Applications,2006,30(1):117-128.
[159] T. L. Wong and W. Lam. Learning to extract and summarize hot item featuresfrom multiple auction web sites [J]. Knowledge and Information Systems,2008,14(2):143-160.
[160] P. Singla and P. Domingos. Object identification with attribute-mediateddependences [C]. Lecture Notes in Computer Science,2005,3721:297-308.
[161] B. Limketkai, D. Fox, and L. Liao. CRF-Filters: discriminative particle filters forsequential state estimation [C]. IEEE International Conference on Robotics andAutomation2007:3142-3147.
[162] T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum. Learning to detect a salientobject [C]. IEEE Conference on Computer Vision and Pattern Recognition,2007.
[163] D. Scharstein and C. Pal. Learning conditional random fields for stereo [C]. IEEEConference on Computer Vision and Pattern Recognition,2007.
[164] A. Mathur and S. Chakrabarti. Accelerating Newton optimization for log-linearmodels through feature redundancy [C]. International Conference on Data Mining,2006:404-413.
[165] I. R. Mansuri and S. Sarawagi. Integrating unstructured data into relationaldatabases [C]. International Conference on Data Engineering,2006.
[166] X. Ren, C. C. Fowlkes, and J. Malik. Figure/Ground assignment in natural images[C]. Lecture Notes in Computer Science,2006,3952:614-627.
[167] L. Stewart, X. He, and R. S. Zemel. Learning flexible features for conditionalrandom fields [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2008,30(8):1415-1426.
[168] H. L. Chieu, W. S. Lee, and L. P. Kaelbling. Activity recognition fromphysiological data using conditional random fields [C]. SMA Symposium,2006.
[169] C. Sun, Y. Guan, X. Wang, and L. Li n. Biomedical named entities recognitionusing conditional random fields model [C]. Lecture Notes in Computer Science,2006,4223:1279-1288.
[170] D. H. Tran, T. H. Pham, K. Satou, and T. B. Ho. Conditional random fields forpredicting and analyzing histone occupancy, acetylation and methylation areas inDNA sequences [C]. Lecture Notes in Computer Science,2006,3907:221-230.
[171] Y. Qiao, J. Liu, and X. Tang. Offline signature verification using onlinehandwriting registration [C]. IEEE Conference on Computer Vision and PatternRecognition,2007.
[172] T. Cohn. Efficient inference in large conditional random fields [C]. Lecture Notesin Computer Science,2006,4212:606-613.
[173] X. H. Phan, L. M. Nguyen, Y. Noguchi, and T.B. Ho. Improving discriminativesequential learning by discovering important association of statistics [J]. ACMTransactions on Asian Language Information Processing,2006,5(4):413-438.
[174] S. Feng, R. Manmatha, and A. McCallum. Exploring the use of conditionalrandom field models and HMMs for historical handwritten document recognition[C]. International Conference on Document Image Analysis for Libraries,2006:30-37.
[175] F. Peng and A. McCallum. Information extraction from research papers usingconditional random fields [J]. Information Processing and Management,2006,42(4):963-979.
[176] G. E. Hinton. Training product of experts by minimizing contrastive divergence[J]. Neural Computation,2002,14:1771–1800.
[177] X. He, R. S. Zemel, and M. A. Carreira-Perpinan. Multiscale conditional randomfields for image labeling [C]. IEEE Conference on Computer Vision and PatternRecognition,2004:695-702.
[178] D. Geiger and F. Girosi. Parallel and deterministic algorithms from MRFs:Surface reconstruction [J]. IEEE Transaction on Pattern Analysis and MachineIntelligence,1991,5(5):401–412.
[179] C. Peterson and J. Anderson. A mean-field theory learning algorithm for neuralnetworks [J].Complex Systems,1987,1:995–1019.
[180] H. Arora, N. Loeff, D. Forsyth, and N. Ahuja. Unsupervised segmentation ofobjects using efficient learning [C]. IEEE Conference on Computer Vision andPattern Recognition,2007.
[181] C. Sminchisescu, A. Kanaujia, and D. Metaxas. Conditional models for contextualhuman motion recognition [J]. Computer Vision and Image Understanding,2006,104(2-3):210-220.
[182] Y. Wang and S. Gong. Refining image annotation using contextual relationsbetween words [C]. ACM International Conference on Image and Video Retrieval,2007:425-432.
[183] B. Douillard, D. Fox, and F. Ramos. A spatio-temporal probabilistic model formulti-sensor object recognition [C]. IEEE/RSJ International Conference onIntelligent Robots and Systems,2007:2402-2408.
[184] J. Weinman, A. Hanson, and A. McCallum. Sign detection in natural images withconditional random fields [C]. IEEE International Workshop on MachineLearning for Signal Processing,2004:549-558.
[185] J. Snoek, J. Hoey, L. Stewart, and R. S. Zemel. Automated detection of unusualevents on stairs [C]. Proceedings of the3rd Canadian Conference on Computerand Robot Vision,2006.
[186] T. Wang, J. Li, W. Hu, X. Tong, Y. Zhang, and C. Dulong. Event detectionmodels using2d-BN and CRFs [C]. Lecture Notes in Computer Science,2007,4352:83-93.
[187] S. Nicolas, J. Dardenne, T. Paquet, and L. Heutte. Document image segmentationusing a2D conditional random field model [C]. International Conference onDocument Analysis and Recognition,2007:407-411.
[188] F. Ramos, D. Fox, and H. Durrant-Whyte. CRF-Matching: conditional randomfields for feature-based scan matching [J]. Robotics: Science and Systems,2007.
[189] X. Ren, C. C. Fowlkes, and J. Malik. Scale-Invariant contour completion usingconditional random fields [C]. IEEE International Conference on ComputerVision,2005:1214-1221.
[190] J. Shotton, JohnWinn, C. Rother, and A. Criminisi. TextonBoost: jointappearance, shape and context modeling for multi-class object recognition andsegmentation [C]. Lecture Notes in Computer Science,2006,3951:1-15.
[191] N. Komodakis and G. Tziritas. Approximate labeling via graph cuts based onlinear programming [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(8):1436-1453.
[192]高琳,唐鹏,盛鹏,左航.复杂条件下基于条件随机场的视觉目标跟踪[J].光学学报,2010,30(6):1721-1728.
[193]罗荣华,闵华清,林盛峰.基于联合条件随机场的移动机器人多目标跟踪[J].机器人.2011,33(3):279-286.
[194] Luo Ronghua, Min Huaqing. Joint conditional random field filter for multi-objecttracking [J]. International Journal of Advanced Robotic Systems,2011,8(1):76-84.
[195]陶霖密,王奇凡,邸慧军.视觉信息处理中的马尔可夫随机场[J].中国图象图形学报.2009,14(9):1705-1711.
[196] Li, C., Ma, L. A new framework for feature descriptor based on SIFT [J]. PatternRecognition Letters.2009,30(5),544-557.
[197] Carneiro, G., Jepson, A.D. Flexible spatial configuration of local Image features[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence.2007,29(12):2089-2014.
[198] Coello Coello, Carlos A. Recent trend in evolutionary multiobjectiveoptimization [A]. Evolutionary Multiobjective Optimization: TheoreticalAdvances and Applications [C]. Springer-Verlag, London,2005:7-32.
[199]牛轶峰.面向AUAV自主控制的图像融合方法研究[D].国防科技大学,博士学位论文,2007.
[200] Pulido G T. On the use of self-adaptation and elitism for multiobjective particleswarm optimization [D]. Ph.D. Dissertation, Electrical Engineering Department,CINVESTAV-IPN, Mexico,2005.
[201] Knowles J D, Corne D W. Approximating the nondominated front using thePareto archived evolution strategy [J]. Evolutionary Computation,2000,8(2):149-172.
[202] Zitzler E, Laumanns M,Thiele L. SPEA2: Improving the strength paretoevolutionary algorithm [R].Technical Report103, Gloriastrasse35, CH-8092Zurieh, Switzerland,2001.
[203] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective geneticalgorithm: NSGA-II [J]. IEEE Transactions on Evolutionary Computation,2002,6(2):182-197.
[204]张勇德,黄莎白.多目标优化问题的蚁群算法研究[J].控制与决策,2005,20(2):170-174.
[205] Coello Coello C A, Pulido G T, Lechuga M S. Handling multiple objectives withparticle swarm optimization [J]. IEEE Transactions on Evolutionary Computation,2004,8(3):256-279.
[206] Kennedy J., Eberhart R. C. Particle swarm optimization [C]. IEEE InternationalConference on Neural Networks. Perth, Australia,1995,1942-1948.
[207]霍霄华.多UCAV动态协同任务规划建模与滚动优化方法研究[D].国防科技大学,博士学位论文,2007.
[208]刘锦峰.图像模板匹配快速算法研究[D].中南大学,硕士学位论文,2007.
[209] S. Gu, Y. Zheng, C.Tomasi. Critical nets and beta-stable features for imagematching [C]. Lecture Notes in Computer Science,2010, part3:663-676.
[210] Leonid Taycher, Leonid Taycher, Gregory Shakhnarovich, et al. Conditionalrandom people: tracking humans with CRFs and grid filters[C]. In IEEEConference on Computer Vision and Pattern Recognition,2006:222-229.
[211] Hai Tao, Harpreet S., Rakesh Kumar. Object tracking with bayesian estimation ofdynamic layer representations [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,2002,24(1):75-89.
[212]章毓晋.图像工程[M].北京:清华大学出版社,2007.
[213] Ji Z, Liao H L, Wang Y W, et al. A novel intelligent particle optimizer for globaloptimization of multimodal functions [C]. IEEE Congress on EvolutionaryComputation, Singapore,2007:3272-3275.
[214] Kass M, Witkinm A, Terzopoulos D. Snakes: Active Contour Models [J].International Journal of Computer Vision,1988, l(4):321-331.
[215] George H. Dunteman(著),吴晓刚(主编).广义线性模型[M].上海:人民出版社,2011.
© 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 |