概率体素模型中建筑物精确三维结构提取

doi:10.3969/j.issn.1000-3428.2016.10.001

计算机工程

所属专题：虚拟现实专题；

概率体素模型中建筑物精确三维结构提取

吴斌^1,2,孙显²,王宏琦²,付琨²

(1.中国科学院大学,北京 100049; 2.中国科学院电子学研究所空间信息处理与应用系统重点实验室,北京 100190)

收稿日期:2016-02-22 出版日期:2016-10-15 发布日期:2016-10-15
作者简介:吴斌(1989—),男,博士,主研方向为遥感图像三维重建;孙显,副研究员;王宏琦、付琨,研究员。
基金资助:
国家自然科学基金资助项目(61331017,61302170)。

Accurate 3D Building Structure Extraction from Probabilistic Voxel Model

WU Bin^1,2,SUN Xian ²,WANG Hongqi²,FU Kun ²

(1.University of Chinese Academy of Sciences,Beijing 100049,China; 2.Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Institute of Electronics,Chinese Academy of Sciences,Beijing 100190,China)

Received:2016-02-22 Online:2016-10-15 Published:2016-10-15

摘要/Abstract

摘要：

从图像中重建的三维体素模型通常存在噪声和建筑物结构不完整的问题,分层边缘拟合方法为解决该类问题提供了一种思路,然而实际场景中建筑物横截面轮廓复杂多样。为此,提出一种两步式由粗到细的边缘拟合算法,在层图像上拟合建筑物横截面轮廓。利用分层投影方法将三维模型投影到二维层图像上,并采用一种结合上下文信息的基于密度的聚类方法去除场景中的噪声,通过形状分类和形状拟合得到平面轮廓的精细拟合结果。最终的三维模型由层图像上边缘拟合结果组合而成。实验结果表明,与最初重建的模型相比,该方法可使精确的建筑物模型更加规则完整且几乎没有噪声,同时大幅减少存储空间。

关键词: 建筑物结构提取, 概率体素模型, 形状分类, 边缘拟合, 可变形模板

Abstract:

3D voxel model reconstructed from images often suffers from problems of noise and incomplete building structure.Layered contour fitting method provides a way to solve this kind of problem.However,the cross planar contours are very complicated in the realistic scene.In view of this,this paper proposes a two-step contour fitting method to fit the cross-sectional contours of a building on the layer image.The hierarchical projection method is used to project the initial 3D model into a two-dimensional layer image which is then de-noised by a contextual density-based clustering algorithm.Precise fitting results of planar contours are obtained by shape classification and shape fitting.The final 3D model is composed of the results from the upper edge of the layer image.Experimental result shows that compared with the original reconstruction model,the precise building model has more regular and complete shape with less noise,and substantially reduces storage space.

Key words: building structure extraction, probabilistic voxel model, shape classification, contour fitting, deformable template

中图分类号:

TP391.41

吴斌,孙显,王宏琦,付琨. 概率体素模型中建筑物精确三维结构提取[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2016.10.001.

WU Bin,SUN Xian,WANG Hongqi,FU Kun. Accurate 3D Building Structure Extraction from Probabilistic Voxel Model[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2016.10.001.

http://www.ecice06.com/CN/Y2016/V42/I10/1

参考文献

参考文献［1］Pollefeys M,van Gool L,Vergauwen M,et al.Visual Modeling with a Hand-held Camera［J］.International Journal of Computer Vision,2004,59(3):207-232. ［2］Furukawa Y,Ponce J.Accurate Camera Calibration from Multi-view Stereo and Bundle Adjustment［C］//Pro-ceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1-8. ［3］Furukawa Y,Ponce J.Accurate,Dense,and Robust Multiview Stereopsis［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(8):1362-1376. ［4］Taylor C J,Kriegman D J.Structure and Motion from Line Segments in Multiple Images［J］.IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,1995,17(11):1021-1032. ［5］邓非,张祖勋,张剑清.基于序列影像的城市三维建模［J］.计算机工程,2007,33(8):208-209. ［6］Pollard T,Mundy J.Change Detection in a 3-d World［C］//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Reco-gnition.Washington D.C.,USA:IEEE Press,2007:1-6. ［7］Crispell D,Mundy J,Taubin G.A Variable-resolution Probabilistic Three-dimensional Model for Change Detection［J］.IEEE Transactions on Geoscience and Remote Sensing,2012,50(2):489-500. ［8］Pu Shi,Vosselman G.Knowledge Based Reconstruction of Building Models from Terrestrial Laser Scanning Data［J］.ISPRS Journal of Photogrammetry and Remote Sensing,2009,64(6):575-584. ［9］Calakli F,Ulusoy A O,Restrepo M,et al.High Resolu-tion Surface Reconstruction from Multi-view Aerial Imagery［C］//Proceedings of the 2nd International Conference on 3D Imaging,Modeling,Processing,Visualization and Transmission.Washington D.C.,USA:IEEE Press,2012:25-32. ［10］Huang Hai,Brenner C,Sester M.A Generative Statistical Approach to Automatic 3D Building Roof Reconstruction from Laser Scanning Data［J］.International Journal of Photogrammetry and Remote Sensing,2013,79(5):29-43. ［11］Wang Sendro,Tseng Y H,Habib A F.Least-squares Building Model Fitting Using Aerial Photos and LiDAR Data［C］//Proceedings of Annual Conference on American Society for Photogrammetry and Remote Sensing.San Diego,USA:［s.n.］,2010:956-965. ［12］Wu Bin,Sun Xian,Wu Qichang,et al.Building Reconstruction from High-resolution Multi-view Aerial Imagery［J］.IEEE Geoscience and Remote Sensing Letters,2015,12(4):855-859. ［13］Klassen E,Srivastava A,Mio W,et al.Analysis Planar Shapes Using Geodesic Paths on Shape Spaces［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(3):372-383. ［14］Srivastava A,Joshi S,Mio W,et al.Statistical Shape Analysis:Clustering,Learning,and Testing［J］.IEEE Transactions on Pattern Analysis and Machine Intel-ligence,2005,27(4):590-602. ［15］Sclaroff S,Lifeng L.Deformable Shape Detection and Description via Model-based Region Grouping［J］.IEEE Transactions on Pattern Analysis and Machine Intel-ligence,2001,23(5):475-489 ［16］Nelder J A,Mead R.A Simplex Method for Function Minimization［J］.Computer Journal,1965,7(4):308-311. ［17］毛宇航,李光耀,肖莽.基于平面结构信息的图像修复［J］.计算机工程,2016,42(3):236-241,248. 编辑顾逸斐

[1]	魏紫薇, 屈丹, 柳聪. 基于连接注意力的行人重识别特征提取方法[J]. 计算机工程, 2022, 48(7): 220-226.
[2]	张业星, 陈敏, 潘秋羽. 基于特征通道建模的目标检测方法[J]. 计算机工程, 2022, 48(7): 264-269,299.
[3]	郝阿香, 贾郭军. 结合注意力与批特征擦除的行人重识别模型[J]. 计算机工程, 2022, 48(7): 270-276,306.
[4]	崔云轩, 刘桂华, 余东应, 郭中远, 张文凯. 点线特征融合的激光雷达单目惯导SLAM系统[J]. 计算机工程, 2022, 48(7): 254-263.
[5]	胡新荣, 龚闯, 张自力, 朱强, 彭涛, 何儒汉. 基于改进Deeplab v3+的服装图像分割网络[J]. 计算机工程, 2022, 48(7): 284-291.
[6]	王安志, 任春洪, 何淋艳, 杨元英, 欧卫华. 基于多模态多级特征聚合网络的光场显著性目标检测[J]. 计算机工程, 2022, 48(7): 227-233,240.
[7]	周培春, 吴兰岸. 多尺度多核高斯过程隐变量模型[J]. 计算机工程, 2021, 47(2): 285-292.
[8]	顾砾, 季怡, 刘纯平. 基于多模态特征融合的三维点云分类方法[J]. 计算机工程, 2021, 47(2): 279-284.
[9]	王林, 李聪会. 基于多级注意力跳跃连接网络的行人属性识别[J]. 计算机工程, 2021, 47(2): 314-320.
[10]	陈扬, 李大威. 基于场景模态深度理解网络的单目图像深度理解[J]. 计算机工程, 2021, 47(2): 268-278.
[11]	周林勇, 谢晓尧, 刘志杰, 谭宏卫, 游善平. 基于ACGAN的图像识别算法[J]. 计算机工程, 2019, 45(10): 246-252,259.
[12]	时璇, 冯舒婷, 沈传科, 李晨, 李党超. 透射率与场景亮度分块优化的图像去雾算法[J]. 计算机工程, 2019, 45(9): 235-241,247.
[13]	官洪运, 欧阳江坤, 杨益伟, 吴炜. 基于特征融合的改进LCT跟踪算法[J]. 计算机工程, 2019, 45(8): 241-247.
[14]	单礼岩, 李新伟. 基于时空信息特征融合的视频指纹算法[J]. 计算机工程, 2019, 45(8): 260-265,274.
[15]	程淑红,周斌. 基于改进CNN的铝轮毂背腔字符识别[J]. 计算机工程, 2019, 45(5): 182-186.

选择文件类型/文献管理软件名称

选择包含的内容

概率体素模型中建筑物精确三维结构提取

Accurate 3D Building Structure Extraction from Probabilistic Voxel Model

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

概率体素模型中建筑物精确三维结构提取

Accurate 3D Building Structure Extraction from Probabilistic Voxel Model

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价