面向遥感影像的建筑物区域理解方法研究
|
摘要
遥感影像作为人类现代科技的重大成果，在人类社会的工业、农业、政治、经济、军事等领域的决策过程中都扮演了非常重要的角色。然而，随着高分辨率遥感卫星的不断升空，目前的遥感影像以每天TB级的速度不断增长。面对浩如烟海的遥感影像数据，依靠传统的、人工判读的方法从遥感影像中提取有用信息已经变得不再可行。如何利用计算机自动或者半自动的对遥感影像进行理解，成为了测绘、决策、计算机视觉等领域一个炙手可热的研究课题。图像理解这一试图将图像中包含的目标和场景解释为一系列有意义的，人们可理解的实体的研究，与遥感影像的解译不谋而合。本文以图像理解的理论和方法为指导，结合遥感影像，特别是高分辨率遥感影像的特点，针对人们普遍关心的遥感影像中的建筑区域的目标识别和场景理解问题，展开了遥感影像建筑区域的分割、建筑目标的提取、建筑目标的识别、建筑区域的分类以及建筑区域的理解等几个方面的研究，以期达成对遥感影像建筑区域中的目标进行识别并对有这些目标构成的场景进行理解的目标。论文的研究工作及贡献主要包括以下几个方面：
在高分辨率遥感影像建筑区域的分割研究中，在阐述图像中的上下文信息在图像分割中重要性，并讨论CRF利用上下文信息的能力后，通过修改该CRF中的势函数，提出了一种改进的，面向遥感影像建筑区域分割的CRF模型。由于CRF模型同时具有融合多特征进行分割的能力，在对遥感影像建筑区域的特点进行分析后，提出将多尺度的纹理特征和梯度模、梯度方向的尺度内及尺度间的多种特征引入到CRF模型中，更好地完成遥感影像建筑区域的分割任务。提出的模型除了能够很好的利用标记图像中的上下文信息外，还能很好的利用观测图像中各个层次、各种形式的上下文信息，且在针对性提取的特征的帮助下产生了比传统的分割算法更为准确的分割结果。
在遥感影像建筑物目标检测和提取的研究中，提出了一种能够产生闭合曲线目标提取结果的多先验形状约束的水平集方法。为了解决传统水平集方法在进行目标提取时由于图像低层信息的缺失造成的提取异常问题，提出通过构建建筑物的先验形状库，并将多个先验形状竞争模型引入水平集方法中，在标记函数的指导下，利用先验形状能量来约束曲线的演化，完成建筑物目标的检测和提取，且先验形状的引入也保证了最终提取的结果为有意义的逻辑实体。而标记函数的引入，则加强了先验形状与待提取目标之间的匹配关系。同时提出的模型具有先验形状的旋转、缩放和平移不变性。
目标的表示与描述是目标识别的前提和基础。针对遥感影像建筑物目标，特别是典型目标的识别问题，提出了一种局部描述算法规格化像素点分布直方图局部描述子。利用前文目标提取获得的目标边缘，将目标边缘上每一像素点依次作为坐标原点构建“对数-极坐标”坐标系，并规格化所有像素点的像素值，利用当前坐标原点以外的目标边缘上像素点的分布来构建局部描述子。并在此基础上对图像中的待识别目标利用提出的描述算法进行描述后与模板库中的典型目标进行匹配，匹配时采取分步匹配的策略，在提高匹配效果的同时，降低计算复杂度。若匹配结果高于某一阈值则待识别目标继承模板库中目标的属性和概念，完成目标识别。提出的算法在降低计算复杂度的前提下，在多种变换图像中取得了类似或优于SIFT方法的性能。
针对遥感影像的目标区域的分类问题，提出了一种利用图像特征空间信息的核函数层次对数极坐标匹配核，来对遥感图像中的建筑区域进行分类。首先对图像提取特征，并将特征映射到已聚类好的“码本”中，量化为有限个类别。将图像由粗到细地划分为多个层次的对数极坐标系下的“子区域（单元格）”。通过比对落入同一层次、同一“子区域（单元格）”的每类特征的直方图交集，建立加权的多尺度的直方图，将多个特征多尺度直方图合并得到最终的核函数，利用“一对多”的SVM完成最后的分类。提出的方法没有构建显式的目标模型，而是通过图像中全局的上下文关系间接地表示了要分类的对象，且提出的方法在一定程度上利用了被传统的基于特征包的方法忽略的特征间的空间关系来构建更为鲁棒的核函数，取得了较好的分类结果。
为了对遥感影像中的建筑物区域所展现的场景进行理解，提出了一种面向建筑区域理解的基于城市实体区域空间配置和建筑实体类局部语义关系的语义贝叶斯网络模型（SBN），在对常见的城市实体类和城市实体区域的概念、组成及空间配置进行总结后，将城市实体区域中建筑实体类的局部语义以及其空间配置关系在统一的概率框架进行了描述。通过建筑实体类在城市实体区域中出现的概率表示城市实体区域的局部语义信息；通过确定具有代表性的建筑实体类及其邻域，近似的表示城市实体区域的空间配置信息；通过训练图像学习贝叶斯网络的参数，随后利用贝叶斯网络的推理能力对测试图像进行概率分类，即通过对一幅城市实体区域影像属于何种类型的概率判断，完成了遥感影像中城市实体区域的理解。实验结果表明，在采用同样的区域特征的前提下，较传统场景分类方法有着更好的分类性能，能够满足遥感影像中的城市实体区域的理解需求。
Asoneofthegreatachievementsofhuman’smodernscienceandtechnology, remotesensing has been playing a very important role during the decision-making of industry,agriculture, politics, economy and military, et al. With the launching of high-resolutionremote sensing satellites, remote sensing images is increasing with the speed of TB leveleveryday. To extract useful information from the trillions of remote sensing images withconventional, manual interpretation method, is a mission impossible. Therefor, the re-search of automatically or semi-automatic interpreting remote sensing images becomesa hot topic. Image understanding, which trying to interpret the scene and the objects inthe scene to some meaningful, understandable entities, happens to hold the same viewwith remote sensing image interpretation. In this thesis, some remote sensing image, es-pecially high-resolution remote sensing image oriented topics are studied with the imageunderstanding theory and methods, such as: building area segmentation, building objectsdetection&extraction,buildingrecognition,buildingareaclassificationandbuildingareaunderstanding, etal. Thegoalistorecognizethebuildingsandunderstandthescenescon-structed by the buildings. The contributions including:
After Elaborating the importance of context in image segmentation and discussingthe ability of using context of CRF, by modifying the potential function of CRF, an im-proved building area segmentation oriented CRF is proposed. As CRF has the advantageof fusion multi-features to segment, after analyze the characteristics of building area inremote sensing images, we propose to introduce the multi-scale texture features and the”in scale”, together with the”between scale” gradient features into CRF, to perform abetter segmentation.the proposed method has the ability of using the context in the labelimages, also, it can make good use of various context in the observed images. And withthe chosen features, the proposed method has a better segmentation result.
In the section of building objects detection and extraction, A novel variational levelset model for multiple-building extraction from a single remote image which can generateclosed curves, is proposed. The object extraction could be fail due to the lost of low-levelinformation, in this thesis, we proposed to solve the problem by construct a buildings’prior-shape database, and consider multi-competing shapes together with the level setmodel. The curve evolution is constrained by the prior shape knowledge and the label function which dynamically indicates the region with which the prior shape should becompared. The building extraction is addressed through a level set image segmentationapproach that involves the use of the label function as well as the prior shape knowledge.The introduction of prior-shapes can guarantee that the extracted objects are meaningfullogical entities. In addition, the proposed model permits translation, scaling, and rotationof the prior shapes.
Representation and description of the objects is the basis for object recognition. Inthis section, a local feature description algorithm for building objects, especially typicalsensitive objects, which is called the normalized pixel distribution histogram local de-scriptor (NPDHLD), is proposed. With the edge extracted by the method discussed in lastsection, a’log-polar’ coordinate is established by using every edge points as the coordi-nate origin. Normalize every pixel value, the local descriptor is constructed by capturingthedistributionoftheobjectedgepixelpointswhicharesituatedbeyondthecurrentoriginpoint. The objects are described with the proposed local description algorithm to build aobjectsfeaturedatabase. thelocalfeaturesextractingfromtheobjectstoberecognizedarematched with the ones in the object database under a’two-step matching’ strategy. Objectrecognition is completed after matching. The’two-step matching’ strategy improved thematching result, also reduced the computational complexity. The proposed recognitionmethod has a better result than SIFT under the same context.
A kernel function—Hierarchical Log-Polar Matching Kernel which making use ofthe feature spatial in-formation, is proposed for building classification in remote sensingimages in this section. Image local features are extracted at first, and then traditionalclustering methods are used to quantize all feature vectors into several different types.Partition-ing the image into multi-level increasingly fine log-polar“sub-regions (bins)”. Bycomputinghistogramsoflocalfeaturesfoundinsideeachsub-regionineachlevel,theweighted multi-scale histograms is formulated, sum all weighted multi-level histogramsof each feature vectors, the final hierarchical log-polar kernel is established. The buildingclassification is done with a SVM trained using the“one-versus-all”rule. There is noexplicit object model in the proposed method, but represent the image by the overall con-text. Meanwhile, the proposed method, as mentioned before, take advantage of the spacerelationship between features which is ignored by conventional bag-of-feature methods,therefor, has a better classify result.
Inordertounderstandthescenepresentedbythebuildingarea,abuildingareaunder-standing oriented semantic bayes network(SBN) which based on the city entities’ spaceconfiguration and semantic relationship, is proposed. After summarize the concept, com-position, and space configuration of the building entities class, as well as the city entityarea, the local semantic and space configuration of building entities are described undera unified probabilistic framework. The local semantic information of city entity area isexpressed by the building entity occurrence probability in the very city entity area; Thespace configuration of city entity area is expressed approximatively by verify the’Repre-sentative building entity class’ and their neighbors; The structure and parameters of SBNisderivedbydomainknowledgeandtrainingimages, andclassifythetestimageswiththeinference of the SBN, in other words, the understanding of the city entity area is achievedby the class probability of the city entity area. The experimental results shows that theproposed method has a better performance than traditional area classification methods.
在高分辨率遥感影像建筑区域的分割研究中，在阐述图像中的上下文信息在图像分割中重要性，并讨论CRF利用上下文信息的能力后，通过修改该CRF中的势函数，提出了一种改进的，面向遥感影像建筑区域分割的CRF模型。由于CRF模型同时具有融合多特征进行分割的能力，在对遥感影像建筑区域的特点进行分析后，提出将多尺度的纹理特征和梯度模、梯度方向的尺度内及尺度间的多种特征引入到CRF模型中，更好地完成遥感影像建筑区域的分割任务。提出的模型除了能够很好的利用标记图像中的上下文信息外，还能很好的利用观测图像中各个层次、各种形式的上下文信息，且在针对性提取的特征的帮助下产生了比传统的分割算法更为准确的分割结果。
在遥感影像建筑物目标检测和提取的研究中，提出了一种能够产生闭合曲线目标提取结果的多先验形状约束的水平集方法。为了解决传统水平集方法在进行目标提取时由于图像低层信息的缺失造成的提取异常问题，提出通过构建建筑物的先验形状库，并将多个先验形状竞争模型引入水平集方法中，在标记函数的指导下，利用先验形状能量来约束曲线的演化，完成建筑物目标的检测和提取，且先验形状的引入也保证了最终提取的结果为有意义的逻辑实体。而标记函数的引入，则加强了先验形状与待提取目标之间的匹配关系。同时提出的模型具有先验形状的旋转、缩放和平移不变性。
目标的表示与描述是目标识别的前提和基础。针对遥感影像建筑物目标，特别是典型目标的识别问题，提出了一种局部描述算法规格化像素点分布直方图局部描述子。利用前文目标提取获得的目标边缘，将目标边缘上每一像素点依次作为坐标原点构建“对数-极坐标”坐标系，并规格化所有像素点的像素值，利用当前坐标原点以外的目标边缘上像素点的分布来构建局部描述子。并在此基础上对图像中的待识别目标利用提出的描述算法进行描述后与模板库中的典型目标进行匹配，匹配时采取分步匹配的策略，在提高匹配效果的同时，降低计算复杂度。若匹配结果高于某一阈值则待识别目标继承模板库中目标的属性和概念，完成目标识别。提出的算法在降低计算复杂度的前提下，在多种变换图像中取得了类似或优于SIFT方法的性能。
针对遥感影像的目标区域的分类问题，提出了一种利用图像特征空间信息的核函数层次对数极坐标匹配核，来对遥感图像中的建筑区域进行分类。首先对图像提取特征，并将特征映射到已聚类好的“码本”中，量化为有限个类别。将图像由粗到细地划分为多个层次的对数极坐标系下的“子区域（单元格）”。通过比对落入同一层次、同一“子区域（单元格）”的每类特征的直方图交集，建立加权的多尺度的直方图，将多个特征多尺度直方图合并得到最终的核函数，利用“一对多”的SVM完成最后的分类。提出的方法没有构建显式的目标模型，而是通过图像中全局的上下文关系间接地表示了要分类的对象，且提出的方法在一定程度上利用了被传统的基于特征包的方法忽略的特征间的空间关系来构建更为鲁棒的核函数，取得了较好的分类结果。
为了对遥感影像中的建筑物区域所展现的场景进行理解，提出了一种面向建筑区域理解的基于城市实体区域空间配置和建筑实体类局部语义关系的语义贝叶斯网络模型（SBN），在对常见的城市实体类和城市实体区域的概念、组成及空间配置进行总结后，将城市实体区域中建筑实体类的局部语义以及其空间配置关系在统一的概率框架进行了描述。通过建筑实体类在城市实体区域中出现的概率表示城市实体区域的局部语义信息；通过确定具有代表性的建筑实体类及其邻域，近似的表示城市实体区域的空间配置信息；通过训练图像学习贝叶斯网络的参数，随后利用贝叶斯网络的推理能力对测试图像进行概率分类，即通过对一幅城市实体区域影像属于何种类型的概率判断，完成了遥感影像中城市实体区域的理解。实验结果表明，在采用同样的区域特征的前提下，较传统场景分类方法有着更好的分类性能，能够满足遥感影像中的城市实体区域的理解需求。
Asoneofthegreatachievementsofhuman’smodernscienceandtechnology, remotesensing has been playing a very important role during the decision-making of industry,agriculture, politics, economy and military, et al. With the launching of high-resolutionremote sensing satellites, remote sensing images is increasing with the speed of TB leveleveryday. To extract useful information from the trillions of remote sensing images withconventional, manual interpretation method, is a mission impossible. Therefor, the re-search of automatically or semi-automatic interpreting remote sensing images becomesa hot topic. Image understanding, which trying to interpret the scene and the objects inthe scene to some meaningful, understandable entities, happens to hold the same viewwith remote sensing image interpretation. In this thesis, some remote sensing image, es-pecially high-resolution remote sensing image oriented topics are studied with the imageunderstanding theory and methods, such as: building area segmentation, building objectsdetection&extraction,buildingrecognition,buildingareaclassificationandbuildingareaunderstanding, etal. Thegoalistorecognizethebuildingsandunderstandthescenescon-structed by the buildings. The contributions including:
After Elaborating the importance of context in image segmentation and discussingthe ability of using context of CRF, by modifying the potential function of CRF, an im-proved building area segmentation oriented CRF is proposed. As CRF has the advantageof fusion multi-features to segment, after analyze the characteristics of building area inremote sensing images, we propose to introduce the multi-scale texture features and the”in scale”, together with the”between scale” gradient features into CRF, to perform abetter segmentation.the proposed method has the ability of using the context in the labelimages, also, it can make good use of various context in the observed images. And withthe chosen features, the proposed method has a better segmentation result.
In the section of building objects detection and extraction, A novel variational levelset model for multiple-building extraction from a single remote image which can generateclosed curves, is proposed. The object extraction could be fail due to the lost of low-levelinformation, in this thesis, we proposed to solve the problem by construct a buildings’prior-shape database, and consider multi-competing shapes together with the level setmodel. The curve evolution is constrained by the prior shape knowledge and the label function which dynamically indicates the region with which the prior shape should becompared. The building extraction is addressed through a level set image segmentationapproach that involves the use of the label function as well as the prior shape knowledge.The introduction of prior-shapes can guarantee that the extracted objects are meaningfullogical entities. In addition, the proposed model permits translation, scaling, and rotationof the prior shapes.
Representation and description of the objects is the basis for object recognition. Inthis section, a local feature description algorithm for building objects, especially typicalsensitive objects, which is called the normalized pixel distribution histogram local de-scriptor (NPDHLD), is proposed. With the edge extracted by the method discussed in lastsection, a’log-polar’ coordinate is established by using every edge points as the coordi-nate origin. Normalize every pixel value, the local descriptor is constructed by capturingthedistributionoftheobjectedgepixelpointswhicharesituatedbeyondthecurrentoriginpoint. The objects are described with the proposed local description algorithm to build aobjectsfeaturedatabase. thelocalfeaturesextractingfromtheobjectstoberecognizedarematched with the ones in the object database under a’two-step matching’ strategy. Objectrecognition is completed after matching. The’two-step matching’ strategy improved thematching result, also reduced the computational complexity. The proposed recognitionmethod has a better result than SIFT under the same context.
A kernel function—Hierarchical Log-Polar Matching Kernel which making use ofthe feature spatial in-formation, is proposed for building classification in remote sensingimages in this section. Image local features are extracted at first, and then traditionalclustering methods are used to quantize all feature vectors into several different types.Partition-ing the image into multi-level increasingly fine log-polar“sub-regions (bins)”. Bycomputinghistogramsoflocalfeaturesfoundinsideeachsub-regionineachlevel,theweighted multi-scale histograms is formulated, sum all weighted multi-level histogramsof each feature vectors, the final hierarchical log-polar kernel is established. The buildingclassification is done with a SVM trained using the“one-versus-all”rule. There is noexplicit object model in the proposed method, but represent the image by the overall con-text. Meanwhile, the proposed method, as mentioned before, take advantage of the spacerelationship between features which is ignored by conventional bag-of-feature methods,therefor, has a better classify result.
Inordertounderstandthescenepresentedbythebuildingarea,abuildingareaunder-standing oriented semantic bayes network(SBN) which based on the city entities’ spaceconfiguration and semantic relationship, is proposed. After summarize the concept, com-position, and space configuration of the building entities class, as well as the city entityarea, the local semantic and space configuration of building entities are described undera unified probabilistic framework. The local semantic information of city entity area isexpressed by the building entity occurrence probability in the very city entity area; Thespace configuration of city entity area is expressed approximatively by verify the’Repre-sentative building entity class’ and their neighbors; The structure and parameters of SBNisderivedbydomainknowledgeandtrainingimages, andclassifythetestimageswiththeinference of the SBN, in other words, the understanding of the city entity area is achievedby the class probability of the city entity area. The experimental results shows that theproposed method has a better performance than traditional area classification methods.
引文
[1] ShahM.Guestintroduction:Thechangingshapeofcomputervisioninthetwenty-first century [J]. International Journal of Computer Vision.2002,50(2):103–110.
[2]高隽,谢昭.图像理解理论与方法[M].北京:科学出版社,2009.
[3] Blake A, Rother C, Brown M, et al. Interactive image segmentation using an adap-tive gmmrf model [C]. In European Conference on Computer Vision (ECCV).2004.
[4]边肇祺,张学工等.模式识别[M].北京:清华大学出版社,2000.
[5] Quiroga R Q, Reddy L, Kreiman G, et al. Invariant visual representation by singleneurons in the human brain [J]. Nature Letters.2005,435(23):1102–1107.
[6] Evans K K, Treisman A. Perception of objects in natural scenes: Is it really atten-tion free [J]. Journal of Experimental Psychology: Human Perception and Perfor-mance.2005,31(6):1476–1492.
[7] Oliva A, Torralba A. Modeling the shape of the scene: a holistic repesentation ofthe spatial envelope [J]. International Journal of Computer Vision.2001,42(3):145–175.
[8] Li F F, Perona P. A Bayesian hierarchical model for learning natural scene cate-gories [C]. In Proceedings of IEEE Conference on Computer Vision and PatternRecognition.2001:524–531.
[9] Torralba A, Fergus R, Freeman W.80million tiny images: A large dataset for non-parametricobjectandscenerecognition[J].IEEETransactionsonPatternAnalysisand Machine Intelligence.2008,30(11):1958–1970.
[10]章毓晋.图像工程[M].北京:清华大学出版社,2007.
[11]章毓晋.图像理解与计算机视觉[M].北京:清华大学出版社,2000.
[12] John J. A Remote Sensing Perspective [M].3rd ed. Prentice Hall,2005.
[13] Colwell R. History and place of photographic interpretation. America Society forPhotogrammetry&Remote Sensing, Bethesda,1997.
[14] Comaniciu D, Meer P. Mean shift: a robust approach toward feature space anal-ysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(5):603–619.
[15] Kass M, Witkin A, Terzopoulos D. Snakes: Active Contour Models [J]. Interna-tional Journal of Computer Cision.1988,1:321–331.
[16] Shi J, Malik J. Normalized Cuts and Image Segmentation [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.2000,22:888–905.
[17] Chan T, Vese L. Active Contours without Edges [J]. IEEE Transactions on ImageProcessing.2001,10:266–277.
[18] Geman S, Geman D. Stochastic Relaxation, Gibbs Distributions, and the BayesianRestoration of Images [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1984,6:721–741.
[19] BoumanC,LiuB.MultipleResolutionSegmentationofTexturedImages[J].IEEETransactions on Pattern Analysis and Machine Intelligence.1991,13:99–113.
[20] Melas D, Wilson S. Double Markov Random Fields and Bayesian Image Segmen-tation [J]. IEEE Transactions on Signal Processing.2002,50:357–365.
[21] Pieczynski W, Tebbache A. Pairwise Markov Random Fields and Segmentation ofTextured Images [J]. Machine Graphics and Vision.2000,9:705–718.
[22] D’Elia C, Poggi G, Scarpa G. A Tree-Structured Markov Random Field Model forBayesian Image Segmentation [J]. IEEE Transactions on Image Processing.2003,12:1259–1273.
[23] He X, Zemel R, Perpinan M C. Multiscale Conditional Random Fields for ImageLabeling [C]. In Proceedings of IEEE CS Conference of Computer Vision andPattern Recognition.2004:695–702.
[24] Zheng S, Tu Z, Yuille A L. Detecting Object Boundaries Using Low-, Mid-, andHigh-level Information [C]. In Proceedings of IEEE Conference on Computer Vi-sion and Pattern Recognition CVPR’07.2007:1–8.
[25] Leibe B, Leonardis A, Schiele B. Combined Object Categorization and Segmen-tation with an Implicit Shape Model [C]. In European Conference on ComputerVision Workshop Statistical Learning in Computer Vision.2004:17–32.
[26] Borges J, J Bioucas D, Marcal A. Bayesian Hyperspectral Image Segmentationwith Discriminative Class Learning [C]. In Proceedings of Third Iberian Confer-ence on Pattern Recognition and Image Analysis.2007:22–29.
[27] Hosaka T, Kobayashi T, Otsu N. Image Segmentation Using MAP-MRF Estima-tionandSupportVectorMachine[J].InterdisciplinaryInformationSciences.2007,13(1):33–42.
[28] Winn J, Jojic N. Locus: Learning Object Classes with Unsupervised Segmenta-tion [C]. In Proceedings of IEEE International Conference on Computer Vision.2005:756–763.
[29] Khan S, Shah M. Object Based Segmentation of Video Using Color, Motion andSpatial Information [C]. In Proceedings of IEEE CS Conference on Computer Vi-sion and Pattern Recognition.2001:746–751.
[30] TaiY,JiaJ,TangC.SoftColorSegmentationandItsApplications[J].IEEETrans-actions on Pattern Analysis and Machine Intelligence.2007,29(9):1520–1537.
[31] Borenstein E, Malik J. Shape Guided Object Segmentation [C]. In Proceedingsof IEEE CS Conference on Computer Vision and Pattern Recognition.2006:969–976.
[32] Tu Z, Chen X, Yuille A L, et al. Image parsing: unifying segmentation, detection,andrecognition[C].InProceedingsofIEEEIntenationalConferenceonComputerVision.2003:18–25.
[33] TuZ,NarrKL,DollarP,etal.BrainAnatomicalStructureSegmentationbyHybridDiscriminative/Generative Models [J]. IEEE Transactions on Medical Imaging.2008,27(4):495–508.
[34] HaraliekR.Decisionmakingincontext[J].IEEETransactionsonPatternAnalysisand Machine Intelligence.1983,5(4):417–428.
[35] Haraliek R, Shapiro L. Survey: Image segmentation techniques [J]. Computer Vi-sion，Graphics, and image Processing.1985,29:100–132.
[36] Pal R, Pal K. A review on image segmentation techniques [J]. Patten Recognition.1993,26(9):1277–1294.
[37] Blaschke T, Burnett C, Pekkarinen A. Remote Sensing Image Analysis: Includingthe spatial domain [M]. Dordrecht: Kluver Academic Publishers,2004:211–236.
[38] Kartikeyan B, Sarkar A, Majumder K. A segmentation approach to classificationof remote sensing imagery [J]. International Journal of Remote Sensing.1998,19(9):1695–1709.
[39] Baatz M, Schape A. Multiresolution segmentation: An optimization approach forhigh spatial multi-scale image segmentation [M]. Heidelberg: Wichmann,2000:12–23.
[40] Neubert M, Herold H, Meinel G. Object Based Image Analysis [M]. Heidelberg,Berlin, NewYork: Springer,2008:760–784.
[41]张桂峰.粒度理论下的多尺度遥感影响分割[D].武汉:武汉大学,2010.
[42] Nalwa V, Binford T. On Detecting Edges [J]. IEEE Transactions on Pattern Anal-ysis and Machine Intelligence.1986,8(6):699–711.
[43] Haraliek R. Digital Step Edges from Zero Crossing of Second Directional Deriva-tives [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1984,6(1):58–68.
[44] Staib L, Duncan J. Boundary Finding with Parametrically Deformable Models [J].IEEE Transactions on Patten Analysis and Machine Intelligence.1992,14(11):1061–1075.
[45] ArdeshirG.DesignandRecoveryof2-Dand3-DShapesUsingRationalGaussianCurves and Surfaces [J]. International Journal of Computer Vision.1993,10(3):233–256.
[46] Cohen L. On active contours and balloons [J]. GVGIP: Image Understanding.1991,53(2):211–218.
[47] Chan T, Vese L. A Level set Algorithm for Minimizing the Mumford-Shah Func-tional in image Processing [C]. In Proceedings of IEEE Workshop on Variationaland Level Set Methods. Vancouver, BC, Canada,2001:161–168.
[48] Mumford D, Shah J. Optimal approximation by piecewise smooth functions andassociated variational problems [J]. Communications on Pure and Applied Math-ematics.1989,42:577–685.
[49]薛景浩,章毓晋,林行刚.基于最大类间后验交叉熵的阈值化分割方法[J].中国图像图形学报.1999,4(2):110–114.
[50]程杰.一种基于直方图的分割方法[J].华中理工大学学报.1999,27(1):84–86.
[51]郑丽萍,李光耀,姜华.基于粒群算法的灰度图像阂值分割的改进[J].多媒体技术.2010,31(3):559–563.
[52]李佐勇,刘传才,程勇等.红外图像阈值分割方法[J].计算机科学.2010,15(1):282–286.
[53]王义敏,秦永元.基于区域生长的SAR图像的目标检测方法[J].计算机应用.2009,29(1):45–46.
[54]顾丹丹,汪西莉.结合区域生长和水平集的遥感影像道路提取[J].计算机应用.2010,30(2):433–436.
[55] Hu X, Tao C, Prenzel B. Automatic segmentation of high-resolution satellite im-agery by integrating texture, iniensity and color features [J]. Photogrammetric En-gineering and Remote Sensing.2005,71(12):1399–1406.
[56] Cheng H, Chen J, Li J. Threshold selection based on Fuzzy c-Partition entropyapproach [J]. Patten Recognition.1998,31(7):857–870.
[57] Huang L, Wang J. Image Thresholding by Minimizing the measure of Fuzzi-ness [J]. Patten Recognition.1995,28(1):41–51.
[58]潘桂芳,胡青泥.模糊聚类和边缘检测结合的彩色图像分割方法[J].微机发展.2005,8:75–77.
[59]柳强,张根耀.基于BP神经网络模型的遥感图像道路分割处理方法研究[J].哈尔滨工程大学学报.2005,25(1):69–71.
[60]李利伟,马建文,欧阳赞,et al.基于时刻独立脉冲祸合神经网络的高空间分辨率遥感影像分割[J].遥感学报.2008,12(1):64–69.
[61]林辉,莫登奎,熊育久,et al.高分辨率遥感影像均值调整法分割技术研究[J].中南林学院学报.2006,32(2):146–151.
[62]莫登奎,林辉,李际平,et al.基于均值漂移的高分辨率影像多尺度分割算法[J].广西师范大学学报:自然科学版.2006,24(4):247–250.
[63] Mansouri A, Mitiche A, Va’zquez C. Multiregion competition: A level set exten-sion of region competition to multiple region image partitioning [J]. ComputerVision and Image Understanding.2006,101:137–150.
[64]杨耘,马洪超,林颖,et al.多水平集演化的高分辨率遥感影像分割[J].武汉大学学报(信息科学版).2008,30(6):588–591.
[65] WuZ,LeahyR.Anoptimalgraphtheoreticapproachtodataclustering:Theoryandits application to image segmentation [J]. IEEE Transactions on Patten Analysisand Machine Intelligence.1993,15(11):1101–1113.
[66] Sarkar S, Boyer K. Quantitative measures of change based on feature organiza-tion: Eigenvalues and eigenvectors [C]. In Proceedings of IEEE Conference ofComputer Vision and Pattern Recognition.1996.
[67] TaoW,JinH,LiuL.Anewimagethresholdingmethodbasedongraphcuts[C].InICASSP2007，IEEE International Conference on Acoustics，speech and signalproeessing.2007.
[68]王爱萍.高分辨率遥感影像分割技术研究[D].武汉:武汉大学,2008.
[69] Gigandet X, Cuadra M, Pointet A, et al. Region-based satellite image classifi-cation: Method and validation [C]. In IEEE International Conference on ImageProeessing，2005(ICIP20O5).2005:832–825.
[70]张骥祥,戴居丰,郑宏兴.基于小波域马尔可夫模型多尺度图像分割[J].天津大学学报.2008,41(5):611–615.
[71]郭雷,侯一民,伦向敏.一种基于图像上下文信息的无监督彩色图像分割算法[J].模式识别与人工智能.2008,21(1):82–87.
[72] Zhang L, Ji Q. Image Segmentation with a Unified Graph Model [J]. IEEE Trans-actions on Pattern Analysis and Machine Intelligence.2010,32(8):1406–1425.
[73]钟平.面向图像标记的随机场模型研究[D].长沙:国防科学技术大学,2008.
[74] Nammalwar P, Ghita O, Whelan P. Integration of feature distributions for colourtexture segmentation [C]. In17th International Conference on pattern Recogni-tion(ICPR2004). Cambridge, UK,2004:716–719.
[75]肖鹏峰.高分辨率遥感图像频域特征提取与图像分割研究[D].南京:南京大学,2007.
[76] Chen Z, Zhao Z, Gong P, et al. A new Process for the segmentation of high reso-lution remote sensing imagery [J]. International Journal of Remote Sensing.2006,27(21-22):4991–5001.
[77] Huertas A, Nevada R. Detecting Buildings in Aerial Images [J]. Computer Vision,Graphics and Image Processing.1988,41(2):131–152.
[78] Irvin R, McKeown D. Methods for exploiting the relationship between buildingsandtheirshadowsinaerialimagery[J].IEEETransactionsonSystem,Man,Cyber.1989,19(6):1564–1575.
[79] Liowand Y, Pavlidis T. Use of Shadows for Extracting Buildings in Aerial Im-ages [J]. Computer Vision, Graphics and Image Processing.1990,49:242–277.
[80] Lin C, Nevitia R. Building detection and description from a single intensity im-age [J]. Computer Vision and Image Understanding.1998,72(2):101–121.
[81] Kim T, Vision J, Muller P. Development of a graph-based approach for buildingdetection [J]. Image Vision Computing.1999,17:3–14.
[82] Levitt S, Aghdasi F. Texture measures for building recognition in aerial pho-tographs [C]. In Proceedings of South African Symp. Communications and SignalProcessing COMSIG’97.1997:75–80.
[83] Stassopoulou A, Caelli T, Ramirez R. Automatic extraction of building statisticsfrom digital orthophotos [J]. International Journal of Geographical InformationScience.2000,14(8):759–841.
[84] Katartzis A, Sahli H. Detection buildings from a single airborne using MarkovRandom Field Model [C]. In Proceedings of IEEE International Geoscience andRemote sensing symposium(IGARSS2001). Sydney,Australia,2001.
[85] Tavakoli M, Rosenfield A. Building and road extraction from aerial pho-tographs [J]. IEEE Transactions on Systems, Man and Cybernetics.1982,12(1):84–91.
[86] Croitoru A, Doytsher Y. Right-angle building hypothesis generation in regular-ized urban areas by pose clustering [J]. Photogrammetric Engineering&RemoteSensing.2003,69(2):151–169.
[87] Lee D, Shan J, Bethel J. Class-Guided Building Extraction from IKONOS Im-agery [J]. Photogrammetry Engineering and Remote Sensing.2003,69(2):143–150.
[88] Baatz M, Schape A. Object-Oriented and Multi-Scale Image Analysis in SemanticNetwork [C]. In Proceedings of the2nd International Symposium on operational-ization of Remote Sensing. Enschede. ITC,1999.
[89]张煜,张祖勋,张剑清.几何约束与影像分割相结合的快速半自动房屋提取[J].武汉测绘科技大学学报.2000,25(3):239–242.
[90]杨益军,赵荣椿,汪文秉.航空图像中人工建筑物的自动检测[J].计算机工程.2002,28(8):20–22.
[91]陶文兵,柳健等.一种新型的航空图像城区建筑物自动提取方法[J].计算机学报.2003,26(7):867–873.
[92]田岩,张钧,陶文兵等.城市几何结构信息提取[R].2002.
[93]侯蕾,尹东,尤晓建.一种遥感图像中建筑物的自动提取方法[J].计算机仿真.2006,23(4):184–187.
[94] Laptev L, Mayer H, Lindeberg T, et al. Automatic extraction of roads from aerialimages based on scale and snakes [J]. Machine Vision and Applications.2000,12:23–31.
[95] Haverkamp D. Extracting Straight Road Structure in Urban Environments UsingIkonos Satellite Imagery [J]. Optical Engineering.2002,41(9):2107–2110.
[96]文贡坚,王润生.从航空遥感图像中自动提取主要道路[J].软件学报.2000,11(7):957–964.
[97]谢凤英,姜志国,秦世引.对偶空间上的高分辨率遥感影像道路提取[J].宇航学报.2006,27(5):1034–1038.
[98]江闽,骆剑承,周成虎等.结合高斯马尔可夫随机场纹理模型与支撑向量机在高分辨率遥感图像上提取道路网[J].遥感学报.2005,9(3):271–276.
[99] Tupin F, Houshmand B, Datcu M. Road Detection in Dense Urhan Areas UsingSAR Imagery and the Usefulness of Multiple Views [J]. IEEE Transactions onGeoscience and Remote Sensing.2002,40(11):2405–2414.
[100] Jeon B, Jang J, Hong K. Road Detection in Spaceborne SAR Images Using a Ge-netic Algorithm [J]. IEEE Transactions on Geoscience and RemoteSensing.2002,40(1):22–29.
[101] Hinz S, Baumgartner A. Automatic Extraction of Urban Road Networks fromMulti-View Aerial Imagery [J]. ISPRS Journal of Photogrammetry and RemoteSensing.2003,58:83–98.
[102] Liu D, He L, Carin L. Airport Detection in Large Aerial Optical Imagery [C].In IEEE International Conference on Acousties，Speech and Signal Proeessing.2004: V–761–764.
[103] Michel A. Airport Detection Using a Simple Model，Multi-Source Images andAltimetric Informations [C]. In Proceedings of SPIE.1994:604–615.
[104]谢建春.机场目标分割与识别方法研究[D].西安:西北工业大学,2004.
[105]陈旭光.卫星遥感图像中机场区域的识别方法研究[D].南京:南京理工大学,2005.
[106]张会章,郭雷.一个机场跑道的自动识别系统[J].计算机工程.2001,27(12):77–78.
[107]罗军,杨卫平,沈振康.红外图像中机场跑道的自动目标识别[J].红外技术.2003,25(3):13–17.
[108]叶斌,彭嘉雄.基于结构特征的军用机场识别与理解[J].华中科技大学学报.2001,29(3):39–42.
[109] Qu Y, Li C, Zheng N. Airport Detection Based on Support Vector Machine fromA Single Image [C]. In Fifth International Conference on Information，Commu-nications and Signal Processing(ICICS).2005:546–549.
[110]杜宗岗,卢凌,梁军等.基于知识的航空图像中大型水上桥梁目标识别[J].武汉理工大学学报.2005,29(2):230–233.
[111]孙琪,曹治国,张天序.基于框架的远距红外桥梁目标识别[J].华中科技大学学报.2001,29(4):1–3.
[112]唐林波,赵保军.一种航拍图像中水上桥梁的实时识别算法[J].电子学报.2007,35(3):511–514.
[113] Soergel U, E E C, Thiele A, et al. Feature Extraction and Visualization of BridgesOver Water From High-Resolution InSAR Data and One Orthophoto [J]. IEEEJoumal of Selected Topics in Applied Earth Observations and Remote Sensing.2008,1(2):147–153.
[114] Vergnet R, Saint-Marc P, Jezouin J. A Generic Bridge Finder [C]. In Workshop onDirections in Automated CAD-Based Vision.1991:176–185.
[115] Chaudhuri D, Samal A. An Automatic Bridge Detection Technique for Multispec-tral Images [J]. IEEE Transactions on Geoscience and Remote Sensing.2008,46(9):2720–2727.
[116]吴樊,王超,张红等.基于知识的中高分辨率光学卫星遥感影像桥梁目标识别研究[J].电子与信息学报.2006,28(4):587–591.
[117]程辉,于秋则,田金文等.基于小波支持向量机分割的SAR图像桥梁目标检测[J].华中科技大学学报.2006,34(4):52–55.
[118] Thiele A, Cadario E, Schulz K, et al. Building Recognition From Multi-AspectHigh-Resolution InSAR Data in Urban Areas [J]. IEEE Transactions on Geo-science and Remote Sensing.2007,45(11):3553–3593.
[119] Samadzadegan F, Schenk T, Mahmoudi F. A Multi-Agent Method for AutomaticBuilding Recognition Based on the Fusion of Lidar Range and Intensity Data [C].In Urban Remote Sensing Joint Event.2009:1–6.
[120] Weidner U, Forstner W. Towards Automatic Building Extraction from High-Resolution Digital Elevation Models [J]. ISPRS Joumal of Photogrammetry andRemote Sensing.1995,50(4):38–49.
[121] Michaelsen E, Stilla U, Soergel U, et al. Extraction of Building Polygons fromSAR Images: Grouping and Decision-Level in the GESTALT System [C]. In2008IAPR Workshop on Pattern Recognition in Remote Sensing.2008:1–4.
[122]马义德,李廉,绽馄等.脉冲祸合神经网络与数字图像处理[M].北京:科学出版社,2008.
[123] Frate F, Licciardi G, Pacifici F, et al. Pulse Coupled Neural Network for Auto-matic Features Extraction from Cosmo-Skymed and TerraSAR-XImagery [C]. InIGARSS.2009: III–384–387.
[124] Pacifici F, Frate F. Automatic Change Detection in Very High Resolution ImagesWith Pulse-Coupled Neural Networks [J]. IEEE Geoscience and Remote Sensingletters.2010,7(1):58–62.
[125] George D, Hawkins J. A Hierarchical Bayesian Model of Invariant Pattern Recog-nition in the Visual Cortex [C]. In Proceedings of International Joint Conferenceon Neural Network.2005:1812–1817.
[126]李鑫.基于生物视觉机理的直线图形认知系统研究[D].长春:吉林大学,2007.
[127]罗晓辉.双高斯差模型的低层次视觉尺度要素检测研究[D].重庆:重庆大学,2002.
[128] Boutell M, Luo J. Review of the state of the art in semantic scence classifica-tion.[R].2002.
[129] Vailaya A, Figueiredo M, Jain A, et al. Content-based hierarchical classificationof vacation images [C]. In Proceedings of IEEE International Conference on Mul-timedia Computing and Systems(ICMCS).1999:518–523.
[130] M S, W P. Indoor-Outdoor Image Classification [C]. In Proceedings of IEEE In-ternational Workshop on Content-based Access of Image and Video Databases.Bombay,1998:42–52.
[131] Chang E, Goh K, Sychay G. Cbsa: Content-based soft anotation for multimodalimage retrieval using Bayes point machines [J]. IEEE Transactions on Circuitsand Systems for Video Technology Special Issue on Conceptual and DynamicalAspects of Multimedia Content Description.2006,13(1):26–38.
[132] AnneHHNgu,ShengQuanZ,HuynhDuQ,etal.Combiningmulti-visualfeaturesfor efficient indexing in a large image database [J]. International Journal on VeryLarge Data Bases.2001,9(4):279–293.
[133] Paek S, Chang S. A knowledge engineering approach for image classificationbased on probabilistic reasoning systems [C]. In IEEE International Conferenceon Multimedia and Expo. New York,2000:1133–1136.
[134] Gokalp D, Aksoy S. Scene Classification Using Bag-of-Regions Representa-tions [C]. In Proceedings of IEEE International Conference on Computer Visionand Pattern Recognition(CVPR). June2007:1–8.
[135] Liu J, Mubarak S. Scene Modeling Using Co-Clustering [C]. In Proceedings ofIEEE International Conference on Computer Vision(ICCV). June2007:1–7.
[136] Askoy S, Koperski K, Tusk C, et al. Learning Bayesian classifiers for scene classi-fication with a visual grammer.[J]. IEEE Transactions on Geoscience and RemoteSensing.2004,43(3):581–589.
[137] FredembachC,SchroderM,SusstrunkS.Eigenregionsforimageclassification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2004,16(12):1645–1649.
[138] Vogel J, Schiele B. Semantic modeling of natural scenes for content-based imageretrieval [J]. International Journal of Computer Vision.2007,72(2):133–157.
[139] Csurka G, Bray C, Dance C. Visual categorization with bags of keypoints [C]. InEuropean Conference on Computer Vision, Workshop on Statistical Learning inComputer Vision.2004:1–22.
[140] Renninger L, Malik J. When is scene identification just texture recognition?[J].Vision Rearch.2004,44(19):2301–2311.
[141] Hofmann T. Unsupervised learning by probabilistic latent sematic analysis [J].Machine Learning.2001,41(2):177–196.
[142] Blei D, Ng A, Jordan M. Latent dirichlet allocation [J]. Journal of Machine Learn-ing Research.2003,3:993–1022.
[143] Bosch A, Zisserman A, Munoz X. Scene classification via pLSA [C]. In EuropeanConference on Computer Vision.2006:517–530.
[144] Quelhas P, Monay F, Odobez J, et al. Modeling scenes with local descriptors andlatent aspects [C]. In Proceedings of IEEE International Conference on ComputerVision.2005:883–890.
[145] Perromin F, Dance C, Csurka G, et al. Adapted vocabularies for generic visualcategorization [C]. In European Conference on Computer Vision.2006:464–475.
[146] Fergus R, Li F F, Perona P, et al. Learning objects categories from google’s imagesearch [C]. In Proceedings of IEEE International Conference on Computer Vision.2005:1816–1823.
[147] Rubin S. The argos image understanding system [D]. Pittsburgh, PA, USA:Carnegie Mellon University,1978.
[148] Kuan D, Shariat H, Dutta K. Constraint-based image understanding system foraerial imagery interpretation [C]. In Proceedings of AI Systems in GovernmentConference. Washington, DC, USA,1989:141–147.
[149] Matsuyama T, Hwang V. SIGMA: A Knowledge-Based Aerial Image Under-standing System (Advances in Computer Vision and Machine Intelligence)[M].Springer,1990.
[150] Brandtberg T. Towards structure-based classification of tree crowns in high spatialresolutionaerialimages[J].ScandinavianJournalofForestResearch.1997,12(1):89–96.
[151]崔巍.用本体实现地理信息系统语义集成和互操作[D].武汉:武汉大学,2004.
[152] Griffis K, Bystrom M. Automatic Object-Level Change Interpretation for Multispectral Remote Sensing Imagery [C]. In Proceedings of European Signal Pro-cessing Conference.2007.
[153]朱志刚,徐光,林学,et al.视觉导航的多尺度全方位时空图像综合理解方法[J].清华大学学报(自然科学版).1997,37(3):12–15.
[154] Gavrila D, Philomin V. Real-time object detection for”smart” vehicles [C]. InProceedings of the Seventh IEEE International Conference on computer vision.Kerkyra, Greece,1999:87–93.
[155] Lu D, Weng Q. A survey of image classification methods and techniques for im-proving classification performance [J]. International Journal of Remote Sensing.2007,28(5):823–870.
[156] VolpeF,RossiL.Quickbirdhighresolutionsatellitedataforurbanapplication[C].In2ndGRSS/ISPRSJointWorkshopDataFusionandRemoteSensingOverUrbanAreas.2003.
[157] LennartzS,CongaltonR.ClassifyingandmappingforestcovertypesusingIkonosimagery in the northeastern United States [C]. In ASPRS Annu. Conf.2004.
[158] Akcay H, Aksoy S. Automatic detection of geospatial objects using multiple hier-archicalsegmentations[J].IEEETransactionsonGeoscienceandRemoteSensing.2008,46(7):2097–2111.
[159] Chen C, Ho P. Statistical pattern recognition in remote sensing [J]. Patten Recog-nition.2008,41:2731–2741.
[160] Bruzzone L, Carlin L. A Multilevel Context-Based System for Classification ofVery High Spatial Resolution Images [J]. IEEE Transactions on Geoscience andRemote Sensing.2006,44(9):2587–2600.
[161] Guo C, Zhu S, Wu Y. Modeling visual patterns by integrating descriptive and gen-erative models [J]. International Journal of Computer Vision.2003,53(1):5–29.
[162] Kumar S, Loui A, Hebert M. Probabilistic classification of image regions using anobservation-constrained generative approach [C]. In Proceedings of ECCV Work-shop on Generative Models based Vision (GMBV).2002.
[163] Kumar S, Loui A, Hebert M. An observation-constrained generative approach forprobabilistic classification of image regions [J]. Image and Vision Computing,Special Issue on Generative Models Based Vision.2003,21:87–97.
[164] Fischler M. The representation and matching of pictorial structures [J]. IEEETransactions on Computers.1973,22(4):67–92.
[165] Yakimovksy Y, Feldman J. A semantics-based decision theory region ana-lyzer [C]. In Proceedings of Third Joint Conference on Artificial Intelligence.1973:580–588.
[166] Garvey T. Perceptual Strategies for Purposive Vision [D]. California: Departmentof Electrical Engineering, Stanford,1975.
[167] Kanade T. Survey region segmentation: Signal vs semantics [J]. Computer Graph-ics and Image Processing.1980,13:279–297.
[168] Hanson A, Riseman E. Visions: A computer vision system for interpretingscenes [M]. New York: Academic Press,1978.
[169] Ohta Y. A Region-Oriented Image-Analysis System by Computer [D]. Kyoto,Japan: Information Science Department, Kyoto University,1980.
[170] Ikeuchi K, Kanade T. Automatic generation of object recognition programs [C].In Proceedings of IEEE.1988:1016–1035.
[171] Pentland A. From Pixels to Predicates [M]. Norwood, NJ: Ablex,1986.
[172] Strat T. Natural Object Recognition [M]. New York: Springer Verlag,1992.
[173] Batlle J, Casals A, Freixenet J, et al. A review on strategies for recognizing naturalobjects in color images of outdoor scenes [J]. Image and Vision Computing.2000,18:515–530.
[174] Crevier D, Lepage R. Knowledge-based image understanding systems: a sur-vey [J]. Computer Vision and Image Understanding.1997,67(2):160–185.
[175] Harr R. Sketching, estimating object positions from relational descriptions [J].Computer Graphics and Image Processing.1982,19:227–247.
[176] Levine M, Nazif A. An experimental rule-based image segmentation: A dynamiccontrol strategy approach [C]. In Proceedings of Computer Vision, Graphics andImage Processing.1985.
[177] Winston P. Learning Structural Descriptions from Examples [D].[S. l.]: ProjectMAC, MIT,1970.
[178] Rao A, Jain R. Knowledge representation and control in computer vision sys-tems [J]. IEEE Expert.1988,3(3):64–79.
[179] Rosenfeld A, Hummel R, Zucker S. Scene labeling by relaxation operations [J].IEEE Transactions on System, Man, Cybernatics.1976,6:420–433.
[180] Kittler J, Pairman D. Contextual pattern recognition applied to cloud detection andidentification [J]. IEEE Transactions on Geoscience and Remote Sensing.1985,23(6):855–863.
[181] Kittler J, Hancock E. Combining evidence in probabilistic relaxation [J]. Inter-national Journal of Pattern Recognition and Artificial Intelligence.1989,3(1):29–51.
[182] Carbonetto P, Freitas N, Barnard K. A statistical model for general contextual ob-ject recognition [C]. In Proceedings of European Conference on Computer Vision.2004.
[183] Kittler J. Probabilistic relaxation: Potential, relationships and open problems [C].In Proceedings of Energy Minimization Methods in Computer Vision and PatternRecognition.1997:393–408.
[184] Christmas W, Kittler J, Petrou M. Structural matching in computer vision usingprobabilistic relaxation [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1995,17(8):749–764.
[185] Fink M, Perona P. Mutual boosting for contextual inference [C]. In In NIPS.2004.
[186] Kruppa H, Schiele B. Using local context to improve face detection [C]. In Pro-ceedings of BMVC.2003.
[187] Murphy K, Torralba A, Freeman W. Using the forest to see the tree: a graphicalmodel relating features, objects and the scenes [J]. NIPS.2003,21.
[188] WolfL,BileschiS.Acriticalviewofcontext[J].InternationalJournalofComputerVision.2006,69(2):251–261.
[189] Rabinovich A, Vedaldi A, Galleguillos C, et al. Objects in context [C]. In ICCV.2007.
[190] Shotton J, Winn J, Rother C, et al. Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling appearance, shapeand context [J]. International Journal of Computer Vision.2007,81(1):2–23.
[191] Verbeek J, Triggs B. Scene segmentation with CRFs learned from partially labeledimages [J]. NIPS.2008,11.
[192] Torralba A, Murphy K, Freeman W. Contextual models for object detection usingboosted random fields [J]. NIPS.2004.
[193] LaffertyJ,McCallumA,PereiraF.Conditionalrandomfields:probabilisticmodelsfor segmenting and labeling sequence data [C]. In International Conference onMachine Learning.2001.
[194] McCullagh P, Nelder J. Generalised Linear Models [M]. London, UK: Chapmanand Hall,1987.
[195] KumarS,HebertM.Ahierarchicalfieldframeworkforunifiedcontext-basedclas-sification [C]. In ICCV.2005:1284–1291.
[196] Kumar S, Hebert M. Discriminative random fields: A discriminative frameworkfor contextual interaction in cassification [C]. In IEEE International Conferenceon Computer Vision.2003:1150–1157.
[197] Itzykson C, Drouffle J. Statistical Field Theory [M]. Cambridge: Cambridge Uni-versity Press,1989.
[198] Hinton G. Training product of experts by minimizing contrastive divergence [J].Neural Computation.2002,14:1771–1800.
[199] Kumar S, Hebert M. Approximate Parameter Learning in DiscriminativeFields [C]. In Snowbird Learning Workshop.2004.
[200] Frey B, Mackay D. A revolution: belief propagation in graphs with cycles [M].MIT Press,1997.
[201] Mayer H. Automatic object extraction from aerial imagery—A survey focusing onbuildings [J]. Computer Vision and Image Understanding.1999,74(2):138–149.
[202] Peng J, Zhang D, Liu Y. An improved snake model for building detection fromurban aerial images [J]. Pattern Recognition Letters.2005,26(5):587–595.
[203] Cao G, Yang X, Mao Z. A Two-stage level set evolution scheme for man-madeobjects detection in aerial images [C]. In Proceedings of IEEE Computer SocietyConference on Computer Vision and Pattern Recognition. San Diego, USA,2005:474–479.
[204] Karantzalos K, Argialas D. A region-based level set segmentation for automaticdetectionofman-madeobjectsfromaerialandsatelliteimages[J].Photogrammet-ric Engineering and Remote Sensing.2009,75(6):667–678.
[205] Samson C, Blanc-Feraud L, Aubert G, et al. Two variational models for multi-spectral image classifation [C]. In Proceedings of the International Workshop onEnergy Minimization Methods in Computer Visionand Pattern Recognition. Nice,France,2001:344–356.
[206] Ball J, Bruce L. Level set segmentation of remotely sensed hyperspectral im-ages [C]. In Proceedings of IEEE International Geoscience and Remote SensingSymposium. Seoul, Korea,2005:5638–5642.
[207] Besbes O, Belhadj Z, Boujemaa N. Adaptive Satellite Images Segmentation byLevel Set Multiregion Competition, Technical Report5855[R].2006.
[208] Cremers D, Rousson M, Deriche R. A review of statistical approaches to levelset segmentation: Integrating color, texture, motion and shape [J]. InternationalJournal of Computer Vision.2007,72(2):195–215.
[209] Cremers D, Sochen N, Schnorr C. Towards recognition-based variational segmen-tation using shape priors and dynamic labeling [C]. In Proceedings of the4th In-ternational Conference on Scale Space Methods in Computer Vision. Isle of Skye,UK,2003:288–400.
[210] Paragios N, Chen Y, Faugeras O. Handbook of Mathematical Models in ComputerVision [M]. New York: Springer, Verlag,2005.
[211] Osher S, Sethian J. Fronts propagating with curvature-dependent speed: Algo-rithms based on Hamilton-Jacobi formulations [J]. Journal of Computer Physics.1988,79:12–49.
[212] Ranchin F, Chambolle A, Dibos F. Total Variation Minimization and Graph Cutsfor Moving Objects Segmentation [D]. Paris, France: University of Paris,2008.
[213] Paragios N, Deriche R. Geodesic active regions: A new framework to deal withframe partition problems in computer vision [J]. Journal of Visual Communicationand Image Representation.2002,13(1-2):249–268.
[214] Riklin-RavivT,KiryatiN,SochenN.Prior-basedsegmentationandshaperegistra-tioninthepresenceofperspectivedistortion[J].InternationalJournalofComputerVision.2007,72(3):309–328.
[215] Paragios N, Rousson M, Ramesh V. Matching distance functions: a shape-to-areavariational approach for global-to-local registration [C]. In Proceedings of Euro-pean Conference in Computer Vision. Copenhangen, Denmark,2002:775–789.
[216] Cremers D, Sochen N, Schnorr C. A multiphase dynamic labeling model for vari-ational recognition-driven image segmentation [J]. International Journal of Com-puter Vision.2006,66(1):67–81.
[217] Kato N, Fukui M, Isozaki T. Bag-of-features approach for improvement of lungtissue classification in diffuse lung disease [C]. In Proceedings of Progress inBiomedical Optics and Imaging. Lake Buena Vista, USA,2009.
[218] Lowe D. Distinctive image features from scale-invariant keypoints [J]. Interna-tional Journal of Computer Vision.2004,60(2):91–110.
[219] Koen E, Gevers T, Snoek C. Evaluating color descriptors for object and scenerecognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2010,32(9):1582–1596.
[220] KeY,SukthankarR.PCA-SIFT：amoredistinctiverepresentationforlocalimagedescriptors [C]. In Proceedings of IEEE Computer Society Conference on Com-puter Vision and Pattern Recognition. Washington D. C., USA,2004:506–513.
[221] Belongie S, Malik J, Puzicha J. hape matching and object recognition using shapecontexts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(4):509–522.
[222] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2005,27(10):1615–1630.
[223] BaudatG,AnouarF.Generalizeddiscriminantanalysisusingakernelapproach[J].Neural Computing.2000,12(10):2385–2404.
[224] Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets, or’how do i organize my holiday snaps?’[C]. In Proceedings of European Confer-ence on Computer Vision.2002:414–431.
[225] AdelsonE.Thedesignanduseofsteerablefilters[J].IEEETransactionsonPatternAnalysis and Machine Intelligence.1991,13(9):891–906.
[226] SchmidC,MohrR.Localgrayvalueinvariantsforimageretrieval[J].IEEETrans-actions on Pattern Analysis and Machine Intelligence.1997,19(5):530–535.
[227] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects usingmean shift [C]. In IEEE Conference on Computer Vision and Pattern Recogni-tion(CVPR’2000). Head Island, SC, USA,2000:142–149.
[228] Ojala T, Pietikainen M, Maenpaa T. Multiresolutio gray-scale and rotation invari-ant texture classification with local binary patterns [J]. IEEE Transactions on Pat-tern Analysis and Machine Intelligence.2002,24(7):971–987.
[229] PereiraS,ORuanaidhJ,DeguillaumeF,etal.TemplatebasedrecoveryofFourier-based watermarks using log-polar and log-log maps [C]. In Proceedings of Multi-media Computing and Systems. Florence, Italy,1999:870–874.
[230] Lorenzo B, Lorenzo C. A multilevel context-Based system for classification ofvery high spacial resolution images [J]. IEEE Transactions on Geoscience and Re-mote Sensing.2006,44(9):2587–2600.
[231] Li F, Perona P. A bayesian hierarchical model for learning natural scene cate-gories[C].InIEEEComputerSocietyConferenceonComputerVisionandPatternRecognition (CVPR2005).2005:524–531.
[232] GraumanK.MatchingSetsofFeaturesforEfficientRetrievalandRecognition[D].[S. l.]: MIT,2007.
[233] Greevy E, Smeaton A. Source classifying racist texts using a support vector ma-chine [C]. In Sheffield SIGIR-Twenty-Seventh Annual International ACM SIGIRConference on Research and Development in Information Retrieval. New York,USA,2004:468–469.
[234] Grauman K, Darrell T. Pyramid match kernels: Discriminative classification withsets of image features [C]. In International Conference on Computer Vision(ICCV2005). Beijing,2005:1458–1465.
[235] Shawe-Taylor J, Cristianini N. Kernel Methods for Pattern Analysis [M]. Cam-bridge, England: Cambridge University Press,2004.
[236] Odone F, Barla A, Verri A. Building kernels from binary strings for image match-ing [J]. IEEE Transactions on Image Processing.2005,14(2):169–180.
[237] LemaitreC,Perdoch M,Rahmoune A,et al. Detectionand matchingof curvilinearstructures [J]. Patten Recognition.2011,44(7):1514–1527.
[238] Griffin G, Holub A, Perona P. The Caltech-256, CNS-TR-2007-001[R].2007.
[239] Zhang J, Marszalek M, Lazebnik S, et al. Local features and kernels for classifca-tion of texture and object categories: A comprehensive study [C]. In Proceedingsof Computer Vision and Pattern Recognition Workshop (CVPRW’06). New York,USA,2006:13–20.
[240] Ballard D, Brown C. Computer Vision [M]. NJ: Prentice-Hall,1982.
[241] Sonka M, Hlavac V, Boyle R. Image Processing, Analysis, and Machine Vi-sion [M].2nd ed. Brooks&Cole Publishing,1999.
[242] SavakisA,LuoJ.Indoorvs.outdoorclassicationofconsumerphotographs[C].InProceedingsofIEEEInternationalConferenceonImageProcessing.Thessaloniki,Greece, September2001.
[243] Luo J, Singhal A, Etz S, et al. Performance scalable computational approach tomain subject detection in photographs [C]. In Proceedings of SPIE Conference onHuman Vision Electronic Imaging. San Jose, CA,2001.
[244] Luo J, Savakis A, Singhal A, et al. On the application of Bayesian networks tosemantic understanding of consumer photographs [C]. In Proceedings of IEEEInternational Conference on Image Processing. Vancouver, Canada,2000.
[245]于静.基于目视解译的城市遥感影像语义结构研究[D].北京:中国科学院研究生院,2008.
[246]中华人民共和国原城乡建设环境保护部.《城市用地分类与规划建设用地标准》[S].1991.
[247] Heckerman D. A tutorial on learning with Bayesian network, Technical ReportMSD-TR,95–06[R].1995.
[248] Serrano N, Savakis A, Luo J. Improved scene classification using efficient low-level features and semantic cues [J]. Patten Recognition.2004,37:1773–1784.
[2]高隽,谢昭.图像理解理论与方法[M].北京:科学出版社,2009.
[3] Blake A, Rother C, Brown M, et al. Interactive image segmentation using an adap-tive gmmrf model [C]. In European Conference on Computer Vision (ECCV).2004.
[4]边肇祺,张学工等.模式识别[M].北京:清华大学出版社,2000.
[5] Quiroga R Q, Reddy L, Kreiman G, et al. Invariant visual representation by singleneurons in the human brain [J]. Nature Letters.2005,435(23):1102–1107.
[6] Evans K K, Treisman A. Perception of objects in natural scenes: Is it really atten-tion free [J]. Journal of Experimental Psychology: Human Perception and Perfor-mance.2005,31(6):1476–1492.
[7] Oliva A, Torralba A. Modeling the shape of the scene: a holistic repesentation ofthe spatial envelope [J]. International Journal of Computer Vision.2001,42(3):145–175.
[8] Li F F, Perona P. A Bayesian hierarchical model for learning natural scene cate-gories [C]. In Proceedings of IEEE Conference on Computer Vision and PatternRecognition.2001:524–531.
[9] Torralba A, Fergus R, Freeman W.80million tiny images: A large dataset for non-parametricobjectandscenerecognition[J].IEEETransactionsonPatternAnalysisand Machine Intelligence.2008,30(11):1958–1970.
[10]章毓晋.图像工程[M].北京:清华大学出版社,2007.
[11]章毓晋.图像理解与计算机视觉[M].北京:清华大学出版社,2000.
[12] John J. A Remote Sensing Perspective [M].3rd ed. Prentice Hall,2005.
[13] Colwell R. History and place of photographic interpretation. America Society forPhotogrammetry&Remote Sensing, Bethesda,1997.
[14] Comaniciu D, Meer P. Mean shift: a robust approach toward feature space anal-ysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(5):603–619.
[15] Kass M, Witkin A, Terzopoulos D. Snakes: Active Contour Models [J]. Interna-tional Journal of Computer Cision.1988,1:321–331.
[16] Shi J, Malik J. Normalized Cuts and Image Segmentation [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.2000,22:888–905.
[17] Chan T, Vese L. Active Contours without Edges [J]. IEEE Transactions on ImageProcessing.2001,10:266–277.
[18] Geman S, Geman D. Stochastic Relaxation, Gibbs Distributions, and the BayesianRestoration of Images [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1984,6:721–741.
[19] BoumanC,LiuB.MultipleResolutionSegmentationofTexturedImages[J].IEEETransactions on Pattern Analysis and Machine Intelligence.1991,13:99–113.
[20] Melas D, Wilson S. Double Markov Random Fields and Bayesian Image Segmen-tation [J]. IEEE Transactions on Signal Processing.2002,50:357–365.
[21] Pieczynski W, Tebbache A. Pairwise Markov Random Fields and Segmentation ofTextured Images [J]. Machine Graphics and Vision.2000,9:705–718.
[22] D’Elia C, Poggi G, Scarpa G. A Tree-Structured Markov Random Field Model forBayesian Image Segmentation [J]. IEEE Transactions on Image Processing.2003,12:1259–1273.
[23] He X, Zemel R, Perpinan M C. Multiscale Conditional Random Fields for ImageLabeling [C]. In Proceedings of IEEE CS Conference of Computer Vision andPattern Recognition.2004:695–702.
[24] Zheng S, Tu Z, Yuille A L. Detecting Object Boundaries Using Low-, Mid-, andHigh-level Information [C]. In Proceedings of IEEE Conference on Computer Vi-sion and Pattern Recognition CVPR’07.2007:1–8.
[25] Leibe B, Leonardis A, Schiele B. Combined Object Categorization and Segmen-tation with an Implicit Shape Model [C]. In European Conference on ComputerVision Workshop Statistical Learning in Computer Vision.2004:17–32.
[26] Borges J, J Bioucas D, Marcal A. Bayesian Hyperspectral Image Segmentationwith Discriminative Class Learning [C]. In Proceedings of Third Iberian Confer-ence on Pattern Recognition and Image Analysis.2007:22–29.
[27] Hosaka T, Kobayashi T, Otsu N. Image Segmentation Using MAP-MRF Estima-tionandSupportVectorMachine[J].InterdisciplinaryInformationSciences.2007,13(1):33–42.
[28] Winn J, Jojic N. Locus: Learning Object Classes with Unsupervised Segmenta-tion [C]. In Proceedings of IEEE International Conference on Computer Vision.2005:756–763.
[29] Khan S, Shah M. Object Based Segmentation of Video Using Color, Motion andSpatial Information [C]. In Proceedings of IEEE CS Conference on Computer Vi-sion and Pattern Recognition.2001:746–751.
[30] TaiY,JiaJ,TangC.SoftColorSegmentationandItsApplications[J].IEEETrans-actions on Pattern Analysis and Machine Intelligence.2007,29(9):1520–1537.
[31] Borenstein E, Malik J. Shape Guided Object Segmentation [C]. In Proceedingsof IEEE CS Conference on Computer Vision and Pattern Recognition.2006:969–976.
[32] Tu Z, Chen X, Yuille A L, et al. Image parsing: unifying segmentation, detection,andrecognition[C].InProceedingsofIEEEIntenationalConferenceonComputerVision.2003:18–25.
[33] TuZ,NarrKL,DollarP,etal.BrainAnatomicalStructureSegmentationbyHybridDiscriminative/Generative Models [J]. IEEE Transactions on Medical Imaging.2008,27(4):495–508.
[34] HaraliekR.Decisionmakingincontext[J].IEEETransactionsonPatternAnalysisand Machine Intelligence.1983,5(4):417–428.
[35] Haraliek R, Shapiro L. Survey: Image segmentation techniques [J]. Computer Vi-sion，Graphics, and image Processing.1985,29:100–132.
[36] Pal R, Pal K. A review on image segmentation techniques [J]. Patten Recognition.1993,26(9):1277–1294.
[37] Blaschke T, Burnett C, Pekkarinen A. Remote Sensing Image Analysis: Includingthe spatial domain [M]. Dordrecht: Kluver Academic Publishers,2004:211–236.
[38] Kartikeyan B, Sarkar A, Majumder K. A segmentation approach to classificationof remote sensing imagery [J]. International Journal of Remote Sensing.1998,19(9):1695–1709.
[39] Baatz M, Schape A. Multiresolution segmentation: An optimization approach forhigh spatial multi-scale image segmentation [M]. Heidelberg: Wichmann,2000:12–23.
[40] Neubert M, Herold H, Meinel G. Object Based Image Analysis [M]. Heidelberg,Berlin, NewYork: Springer,2008:760–784.
[41]张桂峰.粒度理论下的多尺度遥感影响分割[D].武汉:武汉大学,2010.
[42] Nalwa V, Binford T. On Detecting Edges [J]. IEEE Transactions on Pattern Anal-ysis and Machine Intelligence.1986,8(6):699–711.
[43] Haraliek R. Digital Step Edges from Zero Crossing of Second Directional Deriva-tives [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1984,6(1):58–68.
[44] Staib L, Duncan J. Boundary Finding with Parametrically Deformable Models [J].IEEE Transactions on Patten Analysis and Machine Intelligence.1992,14(11):1061–1075.
[45] ArdeshirG.DesignandRecoveryof2-Dand3-DShapesUsingRationalGaussianCurves and Surfaces [J]. International Journal of Computer Vision.1993,10(3):233–256.
[46] Cohen L. On active contours and balloons [J]. GVGIP: Image Understanding.1991,53(2):211–218.
[47] Chan T, Vese L. A Level set Algorithm for Minimizing the Mumford-Shah Func-tional in image Processing [C]. In Proceedings of IEEE Workshop on Variationaland Level Set Methods. Vancouver, BC, Canada,2001:161–168.
[48] Mumford D, Shah J. Optimal approximation by piecewise smooth functions andassociated variational problems [J]. Communications on Pure and Applied Math-ematics.1989,42:577–685.
[49]薛景浩,章毓晋,林行刚.基于最大类间后验交叉熵的阈值化分割方法[J].中国图像图形学报.1999,4(2):110–114.
[50]程杰.一种基于直方图的分割方法[J].华中理工大学学报.1999,27(1):84–86.
[51]郑丽萍,李光耀,姜华.基于粒群算法的灰度图像阂值分割的改进[J].多媒体技术.2010,31(3):559–563.
[52]李佐勇,刘传才,程勇等.红外图像阈值分割方法[J].计算机科学.2010,15(1):282–286.
[53]王义敏,秦永元.基于区域生长的SAR图像的目标检测方法[J].计算机应用.2009,29(1):45–46.
[54]顾丹丹,汪西莉.结合区域生长和水平集的遥感影像道路提取[J].计算机应用.2010,30(2):433–436.
[55] Hu X, Tao C, Prenzel B. Automatic segmentation of high-resolution satellite im-agery by integrating texture, iniensity and color features [J]. Photogrammetric En-gineering and Remote Sensing.2005,71(12):1399–1406.
[56] Cheng H, Chen J, Li J. Threshold selection based on Fuzzy c-Partition entropyapproach [J]. Patten Recognition.1998,31(7):857–870.
[57] Huang L, Wang J. Image Thresholding by Minimizing the measure of Fuzzi-ness [J]. Patten Recognition.1995,28(1):41–51.
[58]潘桂芳,胡青泥.模糊聚类和边缘检测结合的彩色图像分割方法[J].微机发展.2005,8:75–77.
[59]柳强,张根耀.基于BP神经网络模型的遥感图像道路分割处理方法研究[J].哈尔滨工程大学学报.2005,25(1):69–71.
[60]李利伟,马建文,欧阳赞,et al.基于时刻独立脉冲祸合神经网络的高空间分辨率遥感影像分割[J].遥感学报.2008,12(1):64–69.
[61]林辉,莫登奎,熊育久,et al.高分辨率遥感影像均值调整法分割技术研究[J].中南林学院学报.2006,32(2):146–151.
[62]莫登奎,林辉,李际平,et al.基于均值漂移的高分辨率影像多尺度分割算法[J].广西师范大学学报:自然科学版.2006,24(4):247–250.
[63] Mansouri A, Mitiche A, Va’zquez C. Multiregion competition: A level set exten-sion of region competition to multiple region image partitioning [J]. ComputerVision and Image Understanding.2006,101:137–150.
[64]杨耘,马洪超,林颖,et al.多水平集演化的高分辨率遥感影像分割[J].武汉大学学报(信息科学版).2008,30(6):588–591.
[65] WuZ,LeahyR.Anoptimalgraphtheoreticapproachtodataclustering:Theoryandits application to image segmentation [J]. IEEE Transactions on Patten Analysisand Machine Intelligence.1993,15(11):1101–1113.
[66] Sarkar S, Boyer K. Quantitative measures of change based on feature organiza-tion: Eigenvalues and eigenvectors [C]. In Proceedings of IEEE Conference ofComputer Vision and Pattern Recognition.1996.
[67] TaoW,JinH,LiuL.Anewimagethresholdingmethodbasedongraphcuts[C].InICASSP2007，IEEE International Conference on Acoustics，speech and signalproeessing.2007.
[68]王爱萍.高分辨率遥感影像分割技术研究[D].武汉:武汉大学,2008.
[69] Gigandet X, Cuadra M, Pointet A, et al. Region-based satellite image classifi-cation: Method and validation [C]. In IEEE International Conference on ImageProeessing，2005(ICIP20O5).2005:832–825.
[70]张骥祥,戴居丰,郑宏兴.基于小波域马尔可夫模型多尺度图像分割[J].天津大学学报.2008,41(5):611–615.
[71]郭雷,侯一民,伦向敏.一种基于图像上下文信息的无监督彩色图像分割算法[J].模式识别与人工智能.2008,21(1):82–87.
[72] Zhang L, Ji Q. Image Segmentation with a Unified Graph Model [J]. IEEE Trans-actions on Pattern Analysis and Machine Intelligence.2010,32(8):1406–1425.
[73]钟平.面向图像标记的随机场模型研究[D].长沙:国防科学技术大学,2008.
[74] Nammalwar P, Ghita O, Whelan P. Integration of feature distributions for colourtexture segmentation [C]. In17th International Conference on pattern Recogni-tion(ICPR2004). Cambridge, UK,2004:716–719.
[75]肖鹏峰.高分辨率遥感图像频域特征提取与图像分割研究[D].南京:南京大学,2007.
[76] Chen Z, Zhao Z, Gong P, et al. A new Process for the segmentation of high reso-lution remote sensing imagery [J]. International Journal of Remote Sensing.2006,27(21-22):4991–5001.
[77] Huertas A, Nevada R. Detecting Buildings in Aerial Images [J]. Computer Vision,Graphics and Image Processing.1988,41(2):131–152.
[78] Irvin R, McKeown D. Methods for exploiting the relationship between buildingsandtheirshadowsinaerialimagery[J].IEEETransactionsonSystem,Man,Cyber.1989,19(6):1564–1575.
[79] Liowand Y, Pavlidis T. Use of Shadows for Extracting Buildings in Aerial Im-ages [J]. Computer Vision, Graphics and Image Processing.1990,49:242–277.
[80] Lin C, Nevitia R. Building detection and description from a single intensity im-age [J]. Computer Vision and Image Understanding.1998,72(2):101–121.
[81] Kim T, Vision J, Muller P. Development of a graph-based approach for buildingdetection [J]. Image Vision Computing.1999,17:3–14.
[82] Levitt S, Aghdasi F. Texture measures for building recognition in aerial pho-tographs [C]. In Proceedings of South African Symp. Communications and SignalProcessing COMSIG’97.1997:75–80.
[83] Stassopoulou A, Caelli T, Ramirez R. Automatic extraction of building statisticsfrom digital orthophotos [J]. International Journal of Geographical InformationScience.2000,14(8):759–841.
[84] Katartzis A, Sahli H. Detection buildings from a single airborne using MarkovRandom Field Model [C]. In Proceedings of IEEE International Geoscience andRemote sensing symposium(IGARSS2001). Sydney,Australia,2001.
[85] Tavakoli M, Rosenfield A. Building and road extraction from aerial pho-tographs [J]. IEEE Transactions on Systems, Man and Cybernetics.1982,12(1):84–91.
[86] Croitoru A, Doytsher Y. Right-angle building hypothesis generation in regular-ized urban areas by pose clustering [J]. Photogrammetric Engineering&RemoteSensing.2003,69(2):151–169.
[87] Lee D, Shan J, Bethel J. Class-Guided Building Extraction from IKONOS Im-agery [J]. Photogrammetry Engineering and Remote Sensing.2003,69(2):143–150.
[88] Baatz M, Schape A. Object-Oriented and Multi-Scale Image Analysis in SemanticNetwork [C]. In Proceedings of the2nd International Symposium on operational-ization of Remote Sensing. Enschede. ITC,1999.
[89]张煜,张祖勋,张剑清.几何约束与影像分割相结合的快速半自动房屋提取[J].武汉测绘科技大学学报.2000,25(3):239–242.
[90]杨益军,赵荣椿,汪文秉.航空图像中人工建筑物的自动检测[J].计算机工程.2002,28(8):20–22.
[91]陶文兵,柳健等.一种新型的航空图像城区建筑物自动提取方法[J].计算机学报.2003,26(7):867–873.
[92]田岩,张钧,陶文兵等.城市几何结构信息提取[R].2002.
[93]侯蕾,尹东,尤晓建.一种遥感图像中建筑物的自动提取方法[J].计算机仿真.2006,23(4):184–187.
[94] Laptev L, Mayer H, Lindeberg T, et al. Automatic extraction of roads from aerialimages based on scale and snakes [J]. Machine Vision and Applications.2000,12:23–31.
[95] Haverkamp D. Extracting Straight Road Structure in Urban Environments UsingIkonos Satellite Imagery [J]. Optical Engineering.2002,41(9):2107–2110.
[96]文贡坚,王润生.从航空遥感图像中自动提取主要道路[J].软件学报.2000,11(7):957–964.
[97]谢凤英,姜志国,秦世引.对偶空间上的高分辨率遥感影像道路提取[J].宇航学报.2006,27(5):1034–1038.
[98]江闽,骆剑承,周成虎等.结合高斯马尔可夫随机场纹理模型与支撑向量机在高分辨率遥感图像上提取道路网[J].遥感学报.2005,9(3):271–276.
[99] Tupin F, Houshmand B, Datcu M. Road Detection in Dense Urhan Areas UsingSAR Imagery and the Usefulness of Multiple Views [J]. IEEE Transactions onGeoscience and Remote Sensing.2002,40(11):2405–2414.
[100] Jeon B, Jang J, Hong K. Road Detection in Spaceborne SAR Images Using a Ge-netic Algorithm [J]. IEEE Transactions on Geoscience and RemoteSensing.2002,40(1):22–29.
[101] Hinz S, Baumgartner A. Automatic Extraction of Urban Road Networks fromMulti-View Aerial Imagery [J]. ISPRS Journal of Photogrammetry and RemoteSensing.2003,58:83–98.
[102] Liu D, He L, Carin L. Airport Detection in Large Aerial Optical Imagery [C].In IEEE International Conference on Acousties，Speech and Signal Proeessing.2004: V–761–764.
[103] Michel A. Airport Detection Using a Simple Model，Multi-Source Images andAltimetric Informations [C]. In Proceedings of SPIE.1994:604–615.
[104]谢建春.机场目标分割与识别方法研究[D].西安:西北工业大学,2004.
[105]陈旭光.卫星遥感图像中机场区域的识别方法研究[D].南京:南京理工大学,2005.
[106]张会章,郭雷.一个机场跑道的自动识别系统[J].计算机工程.2001,27(12):77–78.
[107]罗军,杨卫平,沈振康.红外图像中机场跑道的自动目标识别[J].红外技术.2003,25(3):13–17.
[108]叶斌,彭嘉雄.基于结构特征的军用机场识别与理解[J].华中科技大学学报.2001,29(3):39–42.
[109] Qu Y, Li C, Zheng N. Airport Detection Based on Support Vector Machine fromA Single Image [C]. In Fifth International Conference on Information，Commu-nications and Signal Processing(ICICS).2005:546–549.
[110]杜宗岗,卢凌,梁军等.基于知识的航空图像中大型水上桥梁目标识别[J].武汉理工大学学报.2005,29(2):230–233.
[111]孙琪,曹治国,张天序.基于框架的远距红外桥梁目标识别[J].华中科技大学学报.2001,29(4):1–3.
[112]唐林波,赵保军.一种航拍图像中水上桥梁的实时识别算法[J].电子学报.2007,35(3):511–514.
[113] Soergel U, E E C, Thiele A, et al. Feature Extraction and Visualization of BridgesOver Water From High-Resolution InSAR Data and One Orthophoto [J]. IEEEJoumal of Selected Topics in Applied Earth Observations and Remote Sensing.2008,1(2):147–153.
[114] Vergnet R, Saint-Marc P, Jezouin J. A Generic Bridge Finder [C]. In Workshop onDirections in Automated CAD-Based Vision.1991:176–185.
[115] Chaudhuri D, Samal A. An Automatic Bridge Detection Technique for Multispec-tral Images [J]. IEEE Transactions on Geoscience and Remote Sensing.2008,46(9):2720–2727.
[116]吴樊,王超,张红等.基于知识的中高分辨率光学卫星遥感影像桥梁目标识别研究[J].电子与信息学报.2006,28(4):587–591.
[117]程辉,于秋则,田金文等.基于小波支持向量机分割的SAR图像桥梁目标检测[J].华中科技大学学报.2006,34(4):52–55.
[118] Thiele A, Cadario E, Schulz K, et al. Building Recognition From Multi-AspectHigh-Resolution InSAR Data in Urban Areas [J]. IEEE Transactions on Geo-science and Remote Sensing.2007,45(11):3553–3593.
[119] Samadzadegan F, Schenk T, Mahmoudi F. A Multi-Agent Method for AutomaticBuilding Recognition Based on the Fusion of Lidar Range and Intensity Data [C].In Urban Remote Sensing Joint Event.2009:1–6.
[120] Weidner U, Forstner W. Towards Automatic Building Extraction from High-Resolution Digital Elevation Models [J]. ISPRS Joumal of Photogrammetry andRemote Sensing.1995,50(4):38–49.
[121] Michaelsen E, Stilla U, Soergel U, et al. Extraction of Building Polygons fromSAR Images: Grouping and Decision-Level in the GESTALT System [C]. In2008IAPR Workshop on Pattern Recognition in Remote Sensing.2008:1–4.
[122]马义德,李廉,绽馄等.脉冲祸合神经网络与数字图像处理[M].北京:科学出版社,2008.
[123] Frate F, Licciardi G, Pacifici F, et al. Pulse Coupled Neural Network for Auto-matic Features Extraction from Cosmo-Skymed and TerraSAR-XImagery [C]. InIGARSS.2009: III–384–387.
[124] Pacifici F, Frate F. Automatic Change Detection in Very High Resolution ImagesWith Pulse-Coupled Neural Networks [J]. IEEE Geoscience and Remote Sensingletters.2010,7(1):58–62.
[125] George D, Hawkins J. A Hierarchical Bayesian Model of Invariant Pattern Recog-nition in the Visual Cortex [C]. In Proceedings of International Joint Conferenceon Neural Network.2005:1812–1817.
[126]李鑫.基于生物视觉机理的直线图形认知系统研究[D].长春:吉林大学,2007.
[127]罗晓辉.双高斯差模型的低层次视觉尺度要素检测研究[D].重庆:重庆大学,2002.
[128] Boutell M, Luo J. Review of the state of the art in semantic scence classifica-tion.[R].2002.
[129] Vailaya A, Figueiredo M, Jain A, et al. Content-based hierarchical classificationof vacation images [C]. In Proceedings of IEEE International Conference on Mul-timedia Computing and Systems(ICMCS).1999:518–523.
[130] M S, W P. Indoor-Outdoor Image Classification [C]. In Proceedings of IEEE In-ternational Workshop on Content-based Access of Image and Video Databases.Bombay,1998:42–52.
[131] Chang E, Goh K, Sychay G. Cbsa: Content-based soft anotation for multimodalimage retrieval using Bayes point machines [J]. IEEE Transactions on Circuitsand Systems for Video Technology Special Issue on Conceptual and DynamicalAspects of Multimedia Content Description.2006,13(1):26–38.
[132] AnneHHNgu,ShengQuanZ,HuynhDuQ,etal.Combiningmulti-visualfeaturesfor efficient indexing in a large image database [J]. International Journal on VeryLarge Data Bases.2001,9(4):279–293.
[133] Paek S, Chang S. A knowledge engineering approach for image classificationbased on probabilistic reasoning systems [C]. In IEEE International Conferenceon Multimedia and Expo. New York,2000:1133–1136.
[134] Gokalp D, Aksoy S. Scene Classification Using Bag-of-Regions Representa-tions [C]. In Proceedings of IEEE International Conference on Computer Visionand Pattern Recognition(CVPR). June2007:1–8.
[135] Liu J, Mubarak S. Scene Modeling Using Co-Clustering [C]. In Proceedings ofIEEE International Conference on Computer Vision(ICCV). June2007:1–7.
[136] Askoy S, Koperski K, Tusk C, et al. Learning Bayesian classifiers for scene classi-fication with a visual grammer.[J]. IEEE Transactions on Geoscience and RemoteSensing.2004,43(3):581–589.
[137] FredembachC,SchroderM,SusstrunkS.Eigenregionsforimageclassification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2004,16(12):1645–1649.
[138] Vogel J, Schiele B. Semantic modeling of natural scenes for content-based imageretrieval [J]. International Journal of Computer Vision.2007,72(2):133–157.
[139] Csurka G, Bray C, Dance C. Visual categorization with bags of keypoints [C]. InEuropean Conference on Computer Vision, Workshop on Statistical Learning inComputer Vision.2004:1–22.
[140] Renninger L, Malik J. When is scene identification just texture recognition?[J].Vision Rearch.2004,44(19):2301–2311.
[141] Hofmann T. Unsupervised learning by probabilistic latent sematic analysis [J].Machine Learning.2001,41(2):177–196.
[142] Blei D, Ng A, Jordan M. Latent dirichlet allocation [J]. Journal of Machine Learn-ing Research.2003,3:993–1022.
[143] Bosch A, Zisserman A, Munoz X. Scene classification via pLSA [C]. In EuropeanConference on Computer Vision.2006:517–530.
[144] Quelhas P, Monay F, Odobez J, et al. Modeling scenes with local descriptors andlatent aspects [C]. In Proceedings of IEEE International Conference on ComputerVision.2005:883–890.
[145] Perromin F, Dance C, Csurka G, et al. Adapted vocabularies for generic visualcategorization [C]. In European Conference on Computer Vision.2006:464–475.
[146] Fergus R, Li F F, Perona P, et al. Learning objects categories from google’s imagesearch [C]. In Proceedings of IEEE International Conference on Computer Vision.2005:1816–1823.
[147] Rubin S. The argos image understanding system [D]. Pittsburgh, PA, USA:Carnegie Mellon University,1978.
[148] Kuan D, Shariat H, Dutta K. Constraint-based image understanding system foraerial imagery interpretation [C]. In Proceedings of AI Systems in GovernmentConference. Washington, DC, USA,1989:141–147.
[149] Matsuyama T, Hwang V. SIGMA: A Knowledge-Based Aerial Image Under-standing System (Advances in Computer Vision and Machine Intelligence)[M].Springer,1990.
[150] Brandtberg T. Towards structure-based classification of tree crowns in high spatialresolutionaerialimages[J].ScandinavianJournalofForestResearch.1997,12(1):89–96.
[151]崔巍.用本体实现地理信息系统语义集成和互操作[D].武汉:武汉大学,2004.
[152] Griffis K, Bystrom M. Automatic Object-Level Change Interpretation for Multispectral Remote Sensing Imagery [C]. In Proceedings of European Signal Pro-cessing Conference.2007.
[153]朱志刚,徐光,林学,et al.视觉导航的多尺度全方位时空图像综合理解方法[J].清华大学学报(自然科学版).1997,37(3):12–15.
[154] Gavrila D, Philomin V. Real-time object detection for”smart” vehicles [C]. InProceedings of the Seventh IEEE International Conference on computer vision.Kerkyra, Greece,1999:87–93.
[155] Lu D, Weng Q. A survey of image classification methods and techniques for im-proving classification performance [J]. International Journal of Remote Sensing.2007,28(5):823–870.
[156] VolpeF,RossiL.Quickbirdhighresolutionsatellitedataforurbanapplication[C].In2ndGRSS/ISPRSJointWorkshopDataFusionandRemoteSensingOverUrbanAreas.2003.
[157] LennartzS,CongaltonR.ClassifyingandmappingforestcovertypesusingIkonosimagery in the northeastern United States [C]. In ASPRS Annu. Conf.2004.
[158] Akcay H, Aksoy S. Automatic detection of geospatial objects using multiple hier-archicalsegmentations[J].IEEETransactionsonGeoscienceandRemoteSensing.2008,46(7):2097–2111.
[159] Chen C, Ho P. Statistical pattern recognition in remote sensing [J]. Patten Recog-nition.2008,41:2731–2741.
[160] Bruzzone L, Carlin L. A Multilevel Context-Based System for Classification ofVery High Spatial Resolution Images [J]. IEEE Transactions on Geoscience andRemote Sensing.2006,44(9):2587–2600.
[161] Guo C, Zhu S, Wu Y. Modeling visual patterns by integrating descriptive and gen-erative models [J]. International Journal of Computer Vision.2003,53(1):5–29.
[162] Kumar S, Loui A, Hebert M. Probabilistic classification of image regions using anobservation-constrained generative approach [C]. In Proceedings of ECCV Work-shop on Generative Models based Vision (GMBV).2002.
[163] Kumar S, Loui A, Hebert M. An observation-constrained generative approach forprobabilistic classification of image regions [J]. Image and Vision Computing,Special Issue on Generative Models Based Vision.2003,21:87–97.
[164] Fischler M. The representation and matching of pictorial structures [J]. IEEETransactions on Computers.1973,22(4):67–92.
[165] Yakimovksy Y, Feldman J. A semantics-based decision theory region ana-lyzer [C]. In Proceedings of Third Joint Conference on Artificial Intelligence.1973:580–588.
[166] Garvey T. Perceptual Strategies for Purposive Vision [D]. California: Departmentof Electrical Engineering, Stanford,1975.
[167] Kanade T. Survey region segmentation: Signal vs semantics [J]. Computer Graph-ics and Image Processing.1980,13:279–297.
[168] Hanson A, Riseman E. Visions: A computer vision system for interpretingscenes [M]. New York: Academic Press,1978.
[169] Ohta Y. A Region-Oriented Image-Analysis System by Computer [D]. Kyoto,Japan: Information Science Department, Kyoto University,1980.
[170] Ikeuchi K, Kanade T. Automatic generation of object recognition programs [C].In Proceedings of IEEE.1988:1016–1035.
[171] Pentland A. From Pixels to Predicates [M]. Norwood, NJ: Ablex,1986.
[172] Strat T. Natural Object Recognition [M]. New York: Springer Verlag,1992.
[173] Batlle J, Casals A, Freixenet J, et al. A review on strategies for recognizing naturalobjects in color images of outdoor scenes [J]. Image and Vision Computing.2000,18:515–530.
[174] Crevier D, Lepage R. Knowledge-based image understanding systems: a sur-vey [J]. Computer Vision and Image Understanding.1997,67(2):160–185.
[175] Harr R. Sketching, estimating object positions from relational descriptions [J].Computer Graphics and Image Processing.1982,19:227–247.
[176] Levine M, Nazif A. An experimental rule-based image segmentation: A dynamiccontrol strategy approach [C]. In Proceedings of Computer Vision, Graphics andImage Processing.1985.
[177] Winston P. Learning Structural Descriptions from Examples [D].[S. l.]: ProjectMAC, MIT,1970.
[178] Rao A, Jain R. Knowledge representation and control in computer vision sys-tems [J]. IEEE Expert.1988,3(3):64–79.
[179] Rosenfeld A, Hummel R, Zucker S. Scene labeling by relaxation operations [J].IEEE Transactions on System, Man, Cybernatics.1976,6:420–433.
[180] Kittler J, Pairman D. Contextual pattern recognition applied to cloud detection andidentification [J]. IEEE Transactions on Geoscience and Remote Sensing.1985,23(6):855–863.
[181] Kittler J, Hancock E. Combining evidence in probabilistic relaxation [J]. Inter-national Journal of Pattern Recognition and Artificial Intelligence.1989,3(1):29–51.
[182] Carbonetto P, Freitas N, Barnard K. A statistical model for general contextual ob-ject recognition [C]. In Proceedings of European Conference on Computer Vision.2004.
[183] Kittler J. Probabilistic relaxation: Potential, relationships and open problems [C].In Proceedings of Energy Minimization Methods in Computer Vision and PatternRecognition.1997:393–408.
[184] Christmas W, Kittler J, Petrou M. Structural matching in computer vision usingprobabilistic relaxation [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1995,17(8):749–764.
[185] Fink M, Perona P. Mutual boosting for contextual inference [C]. In In NIPS.2004.
[186] Kruppa H, Schiele B. Using local context to improve face detection [C]. In Pro-ceedings of BMVC.2003.
[187] Murphy K, Torralba A, Freeman W. Using the forest to see the tree: a graphicalmodel relating features, objects and the scenes [J]. NIPS.2003,21.
[188] WolfL,BileschiS.Acriticalviewofcontext[J].InternationalJournalofComputerVision.2006,69(2):251–261.
[189] Rabinovich A, Vedaldi A, Galleguillos C, et al. Objects in context [C]. In ICCV.2007.
[190] Shotton J, Winn J, Rother C, et al. Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling appearance, shapeand context [J]. International Journal of Computer Vision.2007,81(1):2–23.
[191] Verbeek J, Triggs B. Scene segmentation with CRFs learned from partially labeledimages [J]. NIPS.2008,11.
[192] Torralba A, Murphy K, Freeman W. Contextual models for object detection usingboosted random fields [J]. NIPS.2004.
[193] LaffertyJ,McCallumA,PereiraF.Conditionalrandomfields:probabilisticmodelsfor segmenting and labeling sequence data [C]. In International Conference onMachine Learning.2001.
[194] McCullagh P, Nelder J. Generalised Linear Models [M]. London, UK: Chapmanand Hall,1987.
[195] KumarS,HebertM.Ahierarchicalfieldframeworkforunifiedcontext-basedclas-sification [C]. In ICCV.2005:1284–1291.
[196] Kumar S, Hebert M. Discriminative random fields: A discriminative frameworkfor contextual interaction in cassification [C]. In IEEE International Conferenceon Computer Vision.2003:1150–1157.
[197] Itzykson C, Drouffle J. Statistical Field Theory [M]. Cambridge: Cambridge Uni-versity Press,1989.
[198] Hinton G. Training product of experts by minimizing contrastive divergence [J].Neural Computation.2002,14:1771–1800.
[199] Kumar S, Hebert M. Approximate Parameter Learning in DiscriminativeFields [C]. In Snowbird Learning Workshop.2004.
[200] Frey B, Mackay D. A revolution: belief propagation in graphs with cycles [M].MIT Press,1997.
[201] Mayer H. Automatic object extraction from aerial imagery—A survey focusing onbuildings [J]. Computer Vision and Image Understanding.1999,74(2):138–149.
[202] Peng J, Zhang D, Liu Y. An improved snake model for building detection fromurban aerial images [J]. Pattern Recognition Letters.2005,26(5):587–595.
[203] Cao G, Yang X, Mao Z. A Two-stage level set evolution scheme for man-madeobjects detection in aerial images [C]. In Proceedings of IEEE Computer SocietyConference on Computer Vision and Pattern Recognition. San Diego, USA,2005:474–479.
[204] Karantzalos K, Argialas D. A region-based level set segmentation for automaticdetectionofman-madeobjectsfromaerialandsatelliteimages[J].Photogrammet-ric Engineering and Remote Sensing.2009,75(6):667–678.
[205] Samson C, Blanc-Feraud L, Aubert G, et al. Two variational models for multi-spectral image classifation [C]. In Proceedings of the International Workshop onEnergy Minimization Methods in Computer Visionand Pattern Recognition. Nice,France,2001:344–356.
[206] Ball J, Bruce L. Level set segmentation of remotely sensed hyperspectral im-ages [C]. In Proceedings of IEEE International Geoscience and Remote SensingSymposium. Seoul, Korea,2005:5638–5642.
[207] Besbes O, Belhadj Z, Boujemaa N. Adaptive Satellite Images Segmentation byLevel Set Multiregion Competition, Technical Report5855[R].2006.
[208] Cremers D, Rousson M, Deriche R. A review of statistical approaches to levelset segmentation: Integrating color, texture, motion and shape [J]. InternationalJournal of Computer Vision.2007,72(2):195–215.
[209] Cremers D, Sochen N, Schnorr C. Towards recognition-based variational segmen-tation using shape priors and dynamic labeling [C]. In Proceedings of the4th In-ternational Conference on Scale Space Methods in Computer Vision. Isle of Skye,UK,2003:288–400.
[210] Paragios N, Chen Y, Faugeras O. Handbook of Mathematical Models in ComputerVision [M]. New York: Springer, Verlag,2005.
[211] Osher S, Sethian J. Fronts propagating with curvature-dependent speed: Algo-rithms based on Hamilton-Jacobi formulations [J]. Journal of Computer Physics.1988,79:12–49.
[212] Ranchin F, Chambolle A, Dibos F. Total Variation Minimization and Graph Cutsfor Moving Objects Segmentation [D]. Paris, France: University of Paris,2008.
[213] Paragios N, Deriche R. Geodesic active regions: A new framework to deal withframe partition problems in computer vision [J]. Journal of Visual Communicationand Image Representation.2002,13(1-2):249–268.
[214] Riklin-RavivT,KiryatiN,SochenN.Prior-basedsegmentationandshaperegistra-tioninthepresenceofperspectivedistortion[J].InternationalJournalofComputerVision.2007,72(3):309–328.
[215] Paragios N, Rousson M, Ramesh V. Matching distance functions: a shape-to-areavariational approach for global-to-local registration [C]. In Proceedings of Euro-pean Conference in Computer Vision. Copenhangen, Denmark,2002:775–789.
[216] Cremers D, Sochen N, Schnorr C. A multiphase dynamic labeling model for vari-ational recognition-driven image segmentation [J]. International Journal of Com-puter Vision.2006,66(1):67–81.
[217] Kato N, Fukui M, Isozaki T. Bag-of-features approach for improvement of lungtissue classification in diffuse lung disease [C]. In Proceedings of Progress inBiomedical Optics and Imaging. Lake Buena Vista, USA,2009.
[218] Lowe D. Distinctive image features from scale-invariant keypoints [J]. Interna-tional Journal of Computer Vision.2004,60(2):91–110.
[219] Koen E, Gevers T, Snoek C. Evaluating color descriptors for object and scenerecognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2010,32(9):1582–1596.
[220] KeY,SukthankarR.PCA-SIFT：amoredistinctiverepresentationforlocalimagedescriptors [C]. In Proceedings of IEEE Computer Society Conference on Com-puter Vision and Pattern Recognition. Washington D. C., USA,2004:506–513.
[221] Belongie S, Malik J, Puzicha J. hape matching and object recognition using shapecontexts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24(4):509–522.
[222] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2005,27(10):1615–1630.
[223] BaudatG,AnouarF.Generalizeddiscriminantanalysisusingakernelapproach[J].Neural Computing.2000,12(10):2385–2404.
[224] Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets, or’how do i organize my holiday snaps?’[C]. In Proceedings of European Confer-ence on Computer Vision.2002:414–431.
[225] AdelsonE.Thedesignanduseofsteerablefilters[J].IEEETransactionsonPatternAnalysis and Machine Intelligence.1991,13(9):891–906.
[226] SchmidC,MohrR.Localgrayvalueinvariantsforimageretrieval[J].IEEETrans-actions on Pattern Analysis and Machine Intelligence.1997,19(5):530–535.
[227] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects usingmean shift [C]. In IEEE Conference on Computer Vision and Pattern Recogni-tion(CVPR’2000). Head Island, SC, USA,2000:142–149.
[228] Ojala T, Pietikainen M, Maenpaa T. Multiresolutio gray-scale and rotation invari-ant texture classification with local binary patterns [J]. IEEE Transactions on Pat-tern Analysis and Machine Intelligence.2002,24(7):971–987.
[229] PereiraS,ORuanaidhJ,DeguillaumeF,etal.TemplatebasedrecoveryofFourier-based watermarks using log-polar and log-log maps [C]. In Proceedings of Multi-media Computing and Systems. Florence, Italy,1999:870–874.
[230] Lorenzo B, Lorenzo C. A multilevel context-Based system for classification ofvery high spacial resolution images [J]. IEEE Transactions on Geoscience and Re-mote Sensing.2006,44(9):2587–2600.
[231] Li F, Perona P. A bayesian hierarchical model for learning natural scene cate-gories[C].InIEEEComputerSocietyConferenceonComputerVisionandPatternRecognition (CVPR2005).2005:524–531.
[232] GraumanK.MatchingSetsofFeaturesforEfficientRetrievalandRecognition[D].[S. l.]: MIT,2007.
[233] Greevy E, Smeaton A. Source classifying racist texts using a support vector ma-chine [C]. In Sheffield SIGIR-Twenty-Seventh Annual International ACM SIGIRConference on Research and Development in Information Retrieval. New York,USA,2004:468–469.
[234] Grauman K, Darrell T. Pyramid match kernels: Discriminative classification withsets of image features [C]. In International Conference on Computer Vision(ICCV2005). Beijing,2005:1458–1465.
[235] Shawe-Taylor J, Cristianini N. Kernel Methods for Pattern Analysis [M]. Cam-bridge, England: Cambridge University Press,2004.
[236] Odone F, Barla A, Verri A. Building kernels from binary strings for image match-ing [J]. IEEE Transactions on Image Processing.2005,14(2):169–180.
[237] LemaitreC,Perdoch M,Rahmoune A,et al. Detectionand matchingof curvilinearstructures [J]. Patten Recognition.2011,44(7):1514–1527.
[238] Griffin G, Holub A, Perona P. The Caltech-256, CNS-TR-2007-001[R].2007.
[239] Zhang J, Marszalek M, Lazebnik S, et al. Local features and kernels for classifca-tion of texture and object categories: A comprehensive study [C]. In Proceedingsof Computer Vision and Pattern Recognition Workshop (CVPRW’06). New York,USA,2006:13–20.
[240] Ballard D, Brown C. Computer Vision [M]. NJ: Prentice-Hall,1982.
[241] Sonka M, Hlavac V, Boyle R. Image Processing, Analysis, and Machine Vi-sion [M].2nd ed. Brooks&Cole Publishing,1999.
[242] SavakisA,LuoJ.Indoorvs.outdoorclassicationofconsumerphotographs[C].InProceedingsofIEEEInternationalConferenceonImageProcessing.Thessaloniki,Greece, September2001.
[243] Luo J, Singhal A, Etz S, et al. Performance scalable computational approach tomain subject detection in photographs [C]. In Proceedings of SPIE Conference onHuman Vision Electronic Imaging. San Jose, CA,2001.
[244] Luo J, Savakis A, Singhal A, et al. On the application of Bayesian networks tosemantic understanding of consumer photographs [C]. In Proceedings of IEEEInternational Conference on Image Processing. Vancouver, Canada,2000.
[245]于静.基于目视解译的城市遥感影像语义结构研究[D].北京:中国科学院研究生院,2008.
[246]中华人民共和国原城乡建设环境保护部.《城市用地分类与规划建设用地标准》[S].1991.
[247] Heckerman D. A tutorial on learning with Bayesian network, Technical ReportMSD-TR,95–06[R].1995.
[248] Serrano N, Savakis A, Luo J. Improved scene classification using efficient low-level features and semantic cues [J]. Patten Recognition.2004,37:1773–1784.