结合样本自动选择与规则性约束的窗户提取方法
|
摘要
针对窗户内部结构性与分布规则性等特点,提出了一种结合样本自动选择和分布规则性约束的窗户提取方法。首先,利用模板匹配对选取的单个窗户样本进行拓展,自动选择一定数量的正负样本;其次,利用自动选择的样本对JointBoost分类器进行训练,并对建筑物立面影像进行窗户提取;最后,建立包含窗户走向线、倾向线、兴趣点和相似度4个要素的窗户分布规则性模型,并利用规则性模型约束对提取结果进行优化,得到最终窗户提取结果。在复杂背景、复杂窗户结构及存在透视变形的建筑物影像窗户提取实验中,该方法均有较好的检测率与正确率。
Windows are important elements of building facade.Therefore,window extraction is of significant value to building structural analysis and facade reconstruction.With respect to the inner structural feature and the distribution regularity among windows,this paper proposed a window extract method based on automatic sample selection and distribution regularity constraint.Firstly,sample selection was performed by a template matching method to select a number of window samples,both the positive and the negative,from one selected window sample.Secondly,JointBoost classifier,trained by the window samples,was employed to achieve preliminary window extraction.Then,windows distribution regularity model,which includes horizontal direction,vertical direction,point of interest and similarity,was defined and reconstructed using the preliminary window extraction.Finally,the final window extraction result was achieved by optimizing preliminary window extraction result on the constraint of distribution regularity model.The experiments proved that the proposed method has high extraction ratio and accurate ratio on images with complicated background,complex window structure and perspective distortion.
Windows are important elements of building facade.Therefore,window extraction is of significant value to building structural analysis and facade reconstruction.With respect to the inner structural feature and the distribution regularity among windows,this paper proposed a window extract method based on automatic sample selection and distribution regularity constraint.Firstly,sample selection was performed by a template matching method to select a number of window samples,both the positive and the negative,from one selected window sample.Secondly,JointBoost classifier,trained by the window samples,was employed to achieve preliminary window extraction.Then,windows distribution regularity model,which includes horizontal direction,vertical direction,point of interest and similarity,was defined and reconstructed using the preliminary window extraction.Finally,the final window extraction result was achieved by optimizing preliminary window extraction result on the constraint of distribution regularity model.The experiments proved that the proposed method has high extraction ratio and accurate ratio on images with complicated background,complex window structure and perspective distortion.
引文
[1]Liu Quanhai,Deng Fei,Li Lou,et al.A Method on a Rapid Generation of Exquisite Textures of Building's Roof Towards Planning[J].Geomatics and Information Science of Wuhan University,2015,40(8):1 054-1 060(刘全海,邓非,李楼,等.面向规划的建筑物屋顶精细纹理快速生成方法[J].武汉大学学报·信息科学版,2015,40(8):1 054-1 060)
[2]Yang Bisheng,Dong Zhen,Wei Zheng,et al.Extracting Complex Building Facades from Mobile Laser Scanning Data[J].Acta Geodaetica et Cartographica Sinica,2013,42(3):411-417(杨必胜,董震,魏征,等.从车载激光扫描数据中提取复杂建筑物立面的方法[J].测绘学报,2013,42(3):411-417)
[3]Li Chang.Researching on Key Technique for 3D Auto-Reconstruction of City Street Elevation[J].Acta Geodaetica et Cartographica Sinica,2011,40(2):268(李畅.城市街道立面自动重建关键技术研究[J].测绘学报,2011,40(2):268)
[4]Gong Jianya,Cui Tingting,Shan Jie,et al.A Survey on Facade Modeling Using LiDAR Point Clouds and Image Sequences Collected by Mobile Mapping Systems[J].Geomatics and Information Science of Wuhan University,2015,40(9):1 137-1 143(龚健雅,崔婷婷,单杰,等.利用车载移动测量数据的建筑物立面建模方法[J].武汉大学学报·信息科学版,2015,40(9):1 137-1 143)
[5]Lee S C,Nevatia R.Extraction and Integration of Window in a 3DBuilding Model from Ground View Images[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Washington D C,US,2004
[6]Kostelijk T.Semantic Annotation of Urban Scenes:Skyline and Window Detection[D].Amsterdam:Universiteit van Amsterdam,2012
[7]Recky M,Leberl F.Windows Detection Using Kmeans in CIE-Lab Color Space[C].International Conference on Pattern Recognition,Istanbul,Turkey,2010
[8]Mayer H,Reznik S.Building Facade Interpretation from Uncalibrated Wide-Baseline Image Sequences[J].ISPRS Journal of Photogrammetry and Remote Sensing,2007,61(6):371-380
[9]Sirmacek B,Hoegner L,Stilla U.Detection of Windows and Doors from Thermal Images by Grouping Geometrical Features[C].Joint Urban Remote Sensing Event,Munich,Germany,2011
[10]Ali H,Seifert C,Jindal N,et al.Window Detection in Facades[C].International Conference on Image Analysis and Processing,Seville,Spain,2007
[11]Wang X.Research and Implementation of Semantic Based Window Extraction for Building Facade[D].Beijing:Beijing University,2010(王曦.基于语义的建筑物立面窗户检测算法研究及实现[D].北京;北京大学,2010)
[12]Pauly M,Mitra N J,Wallner J,et al.Discovering Structural Regularity in 3D Geometry[J].ACM Trans Graph,2008,27(3):1-11
[13]Li W,Zheng X,Chen J.Discovering Structural Regularity in Facade Image[C].IEEE International Conference on Systems Man and Cybernetics,Istanbul,Turkey,2010
[14]Iwaszczuk D,Hoegner L,Stilla U.Detection of Windows in IR Building Textures Using Masked Correlation[C].Photogrammetric Image Analysisisprs Conference,Berlin,2011
[15]Yu Ling,Wu Tiejun.Assemble Learning:A Survery of Boosting Algorithms[J].Pattern Recognition and Artificial Intelligence,2004,17(1):52-59(于玲,吴铁军.集成学习:Boosting算法综述[J].模式识别与人工智能,2004,17(1):52-59)
[16]Tao Jianbin,Shu Ning,Shen Zhaoqing.An Improvement of Naive Bayesian Network Classifier for Remote Sensing Images Based on Mutual Information[J].Geomatics and Information Science of Wuhan University,2010,35(2):228-232(陶建斌,舒宁,沈照庆.利用互信息改进遥感影像朴素贝叶斯网络分类器[J].武汉大学学报·信息科学版,2010,35(2):228-232)
[17]Dalal N,Triggs B.Histograms of Oriented Gradients for Human Detection[C].IEEE Conference on Computer Vision and Pattern Recognition,San Diego,USA,2005
[18]Rahtu E,Salo M,Heikkil J.Affine Invariant Pattern Recognition Using Multiscale Autoconvolution[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(6):908-918
[19]Rahtu E,Salo M,Heikkila J,et al.Generalized Afcne Moment Invariants for Object Recognition[C].International Conference on Pattern Recognition,Hong Kong,China,2006
[2]Yang Bisheng,Dong Zhen,Wei Zheng,et al.Extracting Complex Building Facades from Mobile Laser Scanning Data[J].Acta Geodaetica et Cartographica Sinica,2013,42(3):411-417(杨必胜,董震,魏征,等.从车载激光扫描数据中提取复杂建筑物立面的方法[J].测绘学报,2013,42(3):411-417)
[3]Li Chang.Researching on Key Technique for 3D Auto-Reconstruction of City Street Elevation[J].Acta Geodaetica et Cartographica Sinica,2011,40(2):268(李畅.城市街道立面自动重建关键技术研究[J].测绘学报,2011,40(2):268)
[4]Gong Jianya,Cui Tingting,Shan Jie,et al.A Survey on Facade Modeling Using LiDAR Point Clouds and Image Sequences Collected by Mobile Mapping Systems[J].Geomatics and Information Science of Wuhan University,2015,40(9):1 137-1 143(龚健雅,崔婷婷,单杰,等.利用车载移动测量数据的建筑物立面建模方法[J].武汉大学学报·信息科学版,2015,40(9):1 137-1 143)
[5]Lee S C,Nevatia R.Extraction and Integration of Window in a 3DBuilding Model from Ground View Images[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Washington D C,US,2004
[6]Kostelijk T.Semantic Annotation of Urban Scenes:Skyline and Window Detection[D].Amsterdam:Universiteit van Amsterdam,2012
[7]Recky M,Leberl F.Windows Detection Using Kmeans in CIE-Lab Color Space[C].International Conference on Pattern Recognition,Istanbul,Turkey,2010
[8]Mayer H,Reznik S.Building Facade Interpretation from Uncalibrated Wide-Baseline Image Sequences[J].ISPRS Journal of Photogrammetry and Remote Sensing,2007,61(6):371-380
[9]Sirmacek B,Hoegner L,Stilla U.Detection of Windows and Doors from Thermal Images by Grouping Geometrical Features[C].Joint Urban Remote Sensing Event,Munich,Germany,2011
[10]Ali H,Seifert C,Jindal N,et al.Window Detection in Facades[C].International Conference on Image Analysis and Processing,Seville,Spain,2007
[11]Wang X.Research and Implementation of Semantic Based Window Extraction for Building Facade[D].Beijing:Beijing University,2010(王曦.基于语义的建筑物立面窗户检测算法研究及实现[D].北京;北京大学,2010)
[12]Pauly M,Mitra N J,Wallner J,et al.Discovering Structural Regularity in 3D Geometry[J].ACM Trans Graph,2008,27(3):1-11
[13]Li W,Zheng X,Chen J.Discovering Structural Regularity in Facade Image[C].IEEE International Conference on Systems Man and Cybernetics,Istanbul,Turkey,2010
[14]Iwaszczuk D,Hoegner L,Stilla U.Detection of Windows in IR Building Textures Using Masked Correlation[C].Photogrammetric Image Analysisisprs Conference,Berlin,2011
[15]Yu Ling,Wu Tiejun.Assemble Learning:A Survery of Boosting Algorithms[J].Pattern Recognition and Artificial Intelligence,2004,17(1):52-59(于玲,吴铁军.集成学习:Boosting算法综述[J].模式识别与人工智能,2004,17(1):52-59)
[16]Tao Jianbin,Shu Ning,Shen Zhaoqing.An Improvement of Naive Bayesian Network Classifier for Remote Sensing Images Based on Mutual Information[J].Geomatics and Information Science of Wuhan University,2010,35(2):228-232(陶建斌,舒宁,沈照庆.利用互信息改进遥感影像朴素贝叶斯网络分类器[J].武汉大学学报·信息科学版,2010,35(2):228-232)
[17]Dalal N,Triggs B.Histograms of Oriented Gradients for Human Detection[C].IEEE Conference on Computer Vision and Pattern Recognition,San Diego,USA,2005
[18]Rahtu E,Salo M,Heikkil J.Affine Invariant Pattern Recognition Using Multiscale Autoconvolution[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(6):908-918
[19]Rahtu E,Salo M,Heikkila J,et al.Generalized Afcne Moment Invariants for Object Recognition[C].International Conference on Pattern Recognition,Hong Kong,China,2006