城市三维重建中的自动纹理优化方法

doi:10.11947/j.AGCS.2017.20160467

测绘学报 ›› 2017, Vol. 46 ›› Issue (3): 338-345.doi: 10.11947/j.AGCS.2017.20160467

城市三维重建中的自动纹理优化方法

李明^1,2, 张卫龙¹, 范丁元³

1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079;
2. 武汉大学地球空间信息技术协同创新中心, 湖北武汉 430079;
3. 西南交通大学, 四川成都 610031

收稿日期:2016-09-20 修回日期:2017-02-10 出版日期:2017-03-20 发布日期:2017-04-11
通讯作者: 张卫龙 E-mail:2016106190039@whu.edu.cn
作者简介:李明(1985-),男,博士,研究方向为图像处理、三维感知与室内定位。E-mail:lisouming@whu.edu.cn
基金资助:
国家重点研发计划（2016YFB0502200）；国家自然科学基金（41127901）

Automatic Texture Optimization for 3D Urban Reconstruction

LI Ming^1,2, ZHANG Weilong¹, FAN Dingyuan³

1. State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
2. Collaborative Innovation Center for Geospatial Technology, Wuhan University, Wuhan 430079, China;
3. Southwest Jiaotong University, Chengdu 610031, China

Received:2016-09-20 Revised:2017-02-10 Online:2017-03-20 Published:2017-04-11
Supported by:
The National Key Research and Development Program of China(No. 2016YFB0502200);The National Natural Science Foundation of China(No. 41127901)

摘要/Abstract

摘要： 围绕低空多镜头倾斜摄影在三维城市影像模型生产中的纹理优化问题，提出了一种无缝纹理模型重建方法。文中首先采用相机响应函数和暗通道方法对影像进行预处理；然后，根据地物三角网格表面模型与影像的映射关系，利用稀疏构网方法进行遮挡检测，并建立了三角面片的可视纹理列表；最后，结合三角网格表面模型中基本面片的三维拓扑关系，利用影像的均值与方差信息，构建了基于马尔科夫随机场框架下的图割纹理优化算法，解决了纹理优化选择的离散多标号问题，保证了相邻三角面片映射纹理的一致性，实现了城市大场景无缝纹理模型的重建。试验结果验证了算法的可靠性和优越性。

关键词: 倾斜影像, 三角网格表面模型, 遮挡检测, 图割, 纹理优化

Abstract: In order to solve the problem of texture optimization in 3D city reconstruction by using multi-lens oblique images, the paper presents a method of seamless texture model reconstruction. At first, it corrects the radiation information of images by camera response functions and image dark channel. Then, according to the corresponding relevance between terrain triangular mesh surface model to image, implements occlusion detection by sparse triangulation method, and establishes the triangles' texture list of visible. Finally, combines with triangles' topology relationship in 3D triangular mesh surface model and means and variances of image, constructs a graph-cuts-based texture optimization algorithm under the framework of MRF(Markov random filed), to solve the discrete label problem of texture optimization selection and clustering, ensures the consistency of the adjacent triangles in texture mapping, achieves the seamless texture reconstruction of city. The experimental results verify the validity and superiority of our proposed method.

Key words: oblique image, triangular mesh surface model, occlusion detection, graph-cuts, texture optimization

中图分类号:

P234

李明, 张卫龙, 范丁元. 城市三维重建中的自动纹理优化方法[J]. 测绘学报, 2017, 46(3): 338-345.

LI Ming, ZHANG Weilong, FAN Dingyuan. Automatic Texture Optimization for 3D Urban Reconstruction[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(3): 338-345.

参考文献

[1] KAZHDAN M, BOLITHO M, HOPPE H. Poisson Surface Reconstruction[C]//Proceedings of the Fourth Eurographics Symposium on Geometry Processing. Switzerland:Eurographics Association Aire-la-Ville, 2006.
[2] SEITZ S M, CURLESS B, DIEBEL J, et al. A Comparison and Evaluation of Multi-view Stereo Reconstruction Algorithms[C]//Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, NY:IEEE, 2006.
[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] SCHÖNING J, HEIDEMANN G. Evaluation of Multi-view 3D Reconstruction Software[M]//AZZOPARDI C, PETKOV N. Computer Analysis of Images and Patterns:Lecture Notes in Computer Science. Switzerland:Springer International Publishing, 2015.
[5] 王竞雪, 朱庆, 王伟玺. 多匹配基元集成的多视影像密集匹配方法[J]. 测绘学报, 2013, 42(5):691-698. WANG Jingxue, ZHU Qing, WANG Weixi. A Dense Matching Algorithm of Multi-view Image Based on the Integrated Multiple Matching Primitives[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(5):691-698.
[6] PARK J S. Interactive 3D Reconstruction from Multiple Images:a Primitive-based Approach[J]. Pattern Recognition Letters, 2005, 26(16):2558-2571.
[7] FRUEH C, JAIN S, ZAKHOR A. Data Processing Algorithms for Generating Textured 3D Building Facade Meshes from Laser Scans and Camera Images[J]. International Journal of Computer Vision, 2005, 61(2):159-184.
[8] 崔红霞, 林宗坚, 孙杰. 大重叠度无人机遥感影像的三维建模方法研究[J]. 测绘科学, 2005, 30(2):36-38. CUI Hongxia, LIN Zongjian, SUN Jie. Research on the 3-Dimensional Modeling Method for Remote Sensing Images of Big Degree of Overlap Acquired by Unmaned Aerial Vehicle[J]. Science of Surveying and Mapping, 2005, 30(2):36-38.
[9] BERNARDINI F, MARTIN I M, RUSHMEIER H, et al. High-quality Texture Reconstruction from Multiple Scans[J]. IEEE Transactions on Visualization and Computer Graphics, 2001, 7(4):318-332.
[10] BAUMBERG A. Blending Images for Texturing 3D Models[C]//Marshall D, ROSIN L. Proceedings of the British Machine Vision Conference.[S.l.]:BMVA Press, 2002.
[11] LEMPITSKY V, IVANOV D. Seamless Mosaicing of Image-based Texture Maps[C]//Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN:IEEE, 2007.
[12] GAL R, WEXLER Y, OFEK E, et al. Seamless Montage for Texturing Models[J]. Computer Graphics Forum, 2010, 29(2):479-486.
[13] PERÉZ P, GANGNET M, BLAKE A. Poisson Image Editing[J]. ACM Transactions on Graphics, 2003, 22(3):313-318.
[14] GREENE N, KASS M, MILLER G. Hierarchical Z-buffer Visibility[C]//Proceedings of the 20th Annual Conference on Computer Graphics and Interactive Techniques. New York:ACM, 1993.
[15] PARKER S, SHIRLEY P, LIVNAT Y, et al. Interactive Ray Tracing for Isosurface Rendering[C]//Proceedings of 1998 International Conference on Visualization. Los Alamitos, CA:IEEE, 1998.
[16] 张春森, 张卫龙, 郭丙轩, 等. 倾斜影像的三维纹理快速重建[J]. 测绘学报, 2015, 44(7):782-790. DOI:10.11947/j.AGCS.2015.20140341. ZHANG Chunsen, ZHANG Weilong, GUO Bingxuan, et al. Rapidly 3D Texture Reconstruction Based on Oblique Photography[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(7):782-790. DOI:10.11947/j.AGCS.2015.20140341.
[17] HARTLEY R, ZISSERMAN A. Multiple View Geometry in Computer Vision[M]. 2nd ed. London:Cambridge University Press, 2003.
[18] BOYKOV Y, VEKSLER O, ZABIH R, et al. Fast Approximate Energy Minimization via Graph Cuts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11):1222-1239.
[19] SCHMIDT M, ALAHARI K. Generalized Fast Approximate Energy Minimization via Graph Cuts:α-Expansion β-Shrink Moves[C]//Proceedings of 27th Conference on Uncertainty in Artificial Intelligence. Barcelona, Spain:[s.n.], 2011.
[20] ZUREIKI A, DEVY M, CHATILA R. Stereo Matching and Graph Cuts[M]. Vienna, Austria:I-Tech Education and Publishing, 2008:349-372.
[21] HUSSMANN S, RINGBECK T, HAGEBEUKER B. A Performance Review of 3D TOF Vision Systems in Comparison to Stereo Vision Systems[M]. Vienna, Austria:InTech, 2008.
[22] HE Kaiming, SUN Jian, TANG Xiaoou. Single Image Haze Removal Using Dark Channel Prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353.
[23] 罗思. 基于Wallis原理改进的匀光算法[J]. 测绘科学技术, 2015, 3(3):51-58. LUO Si. Improved Dodging Algorithm Based on Wallis Principle[J]. Geomatics Science and Technology, 2015, 3(3):51-58.
[24] 李德仁, 王密, 潘俊. 光学遥感影像的自动匀光处理及应用[J]. 武汉大学学报(信息科学版), 2006, 31(9):753-756. LI Deren, WANG Mi, PAN Jun. Auto-dodging Processing and Its Application for Optical RS Images[J]. Geomatics and Information Science of Wuhan University, 2006, 31(9):753-756.
[25] KIM S J, POLLEFEYS M. Robust Radiometric Calibration and Vignetting Correction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(4):562-576.
[26] D'ANGELO P. Radiometric Alignment and Vignetting Calibration[C]//Proceedings of the 2007 ICVS Workshop on Camera Calibration Methods for Computer Vision System. Bielefeld, Germany:Applied Computer Science Group, Bielefeld University, 2007.

城市三维重建中的自动纹理优化方法

Automatic Texture Optimization for 3D Urban Reconstruction

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 14

编辑推荐

Metrics

本文评价

[1]	巩丹超, 韩轶龙, 黄旭. 线特征约束的建筑物密集匹配边缘全局优化方法[J]. 测绘学报, 2021, 50(6): 833-846.
[2]	黄翔翔, 朱全生, 江万寿. 多视纹理映射中无需设定偏差的快速可见性检测[J]. 测绘学报, 2020, 49(1): 92-107.
[3]	张春森, 张奇源, 郭丙轩, 薛万唱. 倾斜影像自适应初始物方面元优化匹配算法[J]. 测绘学报, 2020, 49(1): 108-116.
[4]	杜守基, 邹峥嵘, 张云生, 何雪, 王竞雪. 融合LiDAR点云与正射影像的建筑物图割优化提取方法[J]. 测绘学报, 2018, 47(4): 519-527.
[5]	丁亚洲, 冯发杰, 吏军平, 胡艳, 崔卫红. 多星形约束图割与轮廓规则化的高分遥感影像直角建筑物提取[J]. 测绘学报, 2018, 47(12): 1630-1639.
[6]	刘莹, 陶超, 闫培, 邹峥嵘. 图割能量驱动的高分辨率遥感影像震害损毁建筑物检测[J]. 测绘学报, 2017, 46(7): 910-917.
[7]	闫利, 费亮, 叶志云, 夏旺. 大范围倾斜多视影像连接点自动提取的区域网平差法[J]. 测绘学报, 2016, 45(3): 310-317.
[8]	张春森, 张卫龙, 郭丙轩, 刘健辰, 李明. 倾斜影像的三维纹理快速重建[J]. 测绘学报, 2015, 44(7): 782-790.
[9]	肖雄武, 郭丙轩, 李德仁, 赵霞, 江万寿, 胡翰, 张春森. 一种具有仿射不变性的倾斜影像快速匹配方法[J]. 测绘学报, 2015, 44(4): 414-421.
[10]	肖卫峰张良孙大鹏李月锋. 光线追踪遮挡检测算法[J]. 测绘学报, 2014, 43(8): 862-868.
[11]	周绍光陈超岳建平. 基于形状先验和图割的高分辨率遥感影像道路提取[J]. 测绘学报, 2014, 43(1): 60-65.
[12]	王竞雪朱庆王伟玺. 多匹配基元集成的多视影像密集匹配方法[J]. , 2013, 42(5): 691-698.
[13]	钟成,黄先锋. 真正射影像生成的多边形反演成像遮蔽检测方法[J]. 测绘学报, 2010, 39(1): 0-82.
[14]	谢文寒,周国清. 城市大比例尺真正射影像阴影与遮挡问题的研究[J]. 测绘学报, 2010, 39(1): 0-82.