基于条件随机场的模型特征线提取方法

doi:10.3969/j.iss.0372-2012-2014.03.012

电子学报 ›› 2014, Vol. 42 ›› Issue (3): 498-504.DOI: 10.3969/j.iss.0372-2012-2014.03.012

基于条件随机场的模型特征线提取方法

张尧烨, 孙正兴, 刘凯, 宋沫飞, 章菲倩

南京大学计算机软件新技术国家重点实验室, 江苏南京 210046

收稿日期:2012-12-10 修回日期:2013-07-02 出版日期:2014-03-25
- 通讯作者:
- 孙正兴
- 作者简介:
- 张尧烨 男，1983年11月出生于江苏省江阴市.现为南京大学计算机科学与技术系博士研究生，主要研究领域为智能人机交互与计算机图形学.E-mail：flavor2@163.com
- 基金资助:
- 国家自然科学基金 (No.61272219，No.61100110，No.61021062）; 国家高技术研究发展计划 (863计划）课题 (No.2007AA01Z334）; 新世纪优秀人才支持计划 (No.NCET-04-04605）; 江苏省科技支撑计划 (No.BE2010072，No.BE2011058，No.BY2012190）

Extraction of Feature Lines for 3D Model Based on Conditional Random Fields

ZHANG Yao-ye, SUN Zheng-xing, LIU Kai, SONG Mo-fei, ZHANG Fei-qian

State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu 210046, China

Received:2012-12-10 Revised:2013-07-02 Online:2014-03-25 Published:2014-03-25
- Supported by:
- National Natural Science Foundation of China (No.61272219, No.61100110, No.61021062); Subject of National High-tech R&D Program of China (863 Program) (No.2007AA01Z334); Program for New Century Excellent Talents in University (No.NCET-04-04605); Science and Technology Support Project of Jiangsu Province (No.BE2010072, No.BE2011058, No.BY2012190)

摘要/Abstract

摘要： 本文提出了一种草图指导的三维模型特征线提取方法，该方法特点在于：一方面，建立了笔画采样点与模型特征线点间的条件随机场匹配模型，将模型几何特征与形状相似性结合匹配，实现了草图信息与模型特征线提取的有效融合；另一方面，提出了基于结构相似性的模型特征线度量机制，并采用迭代优化方法实现了全局最优模型特征线的提取.实验结果表明：本文提出的方法能有效获取与草图结构形状相对应的模型特征线绘图.

关键词: 非真实感绘制, 特征线提取, 条件随机场, 迭代优化, 指导草图

Abstract: This paper proposed a 3D model feature lines extracting method guided by user's sketch.There are two main contributions of our method:on the one hand,a conditional random fields(CRF)-matching model with geometric features and shape similarity between stroke points and candidate feature points is established,and the user drawing purpose is combined with the model feature lines extraction effectively;on the other hand,a topological similarity based metrics is proposed to evaluate the rationality of extracted feature lines,and an iterative optimization process is applied to obtain global optimized model feature lines.The experimental results show that our method is efficient to extract reasonable 3D model feature lines which are similar to sketch strokes on shape and topological properties.

Key words: non-photorealistic rendering, feature lines extraction, conditional random fields, iterative optimization, guided sketch

中图分类号:

TP391

张尧烨, 孙正兴, 刘凯, 等. 基于条件随机场的模型特征线提取方法[J]. 电子学报, 2014, 42(3): 498-504.

ZHANG Yao-ye, SUN Zheng-xing, LIU Kai, et al. Extraction of Feature Lines for 3D Model Based on Conditional Random Fields[J]. Acta Electronica Sinica, 2014, 42(3): 498-504.

参考文献

[1] Hertzmann A.Non-photorealistic rendering and the science of art[A].Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering[C].New York, USA:ACM, 2010.147-157.

[2] Catalano C E, Mortara M, et al.Semantics and 3D media:Current issues and perspectives[J].Computers & Graphics, 2011, 35(4):869-877.

[3] Hertzmann A.Introduction to 3Dnon-photorealistic rendering:Silhouettes and outlines[A].Non-Photorealistic Rendering, SIGGRAPH Course Notes[C].New York, USA:ACM, 1999.15-29.

[4] DeCarlo D, Finkelstein A, et al.Suggestive contours for conveying shape[J].ACM Transactions on Graphics, 2003, 22(3):848-855.

[5] InterranteV, Fuchs H, et al.Enhancing transparent skin surfaces with ridge and valley lines[A].Proceedings of the 6th Conference on Visualization'95[C].Washington, DC:IEEE Computer Society, 1995.52-59.

[6] Cole F, Golovinskiy A, et al.Where do people draw lines[J].ACM Trans Graph, 2008, 27(3):88:1-88:11.

[7] Kalogerakis E, Nowrouzezahrai D, et al.Learning hatching for pen-and-ink illustration of surfaces[J].ACM Transactions on Graphics, 2012, 31(1):1:1-1:17.

[8] Lum E B, Ma K L.Expressive line selection by example[J].The Visual Computer, 2005, 21(8-10):811-820.

[9] OlsenL, Samavati F F, et al.Sketch-based modeling:A survey[J].Computers & Graphics, 2009, 33(1):85-103.

[10] 申世群, 刘大有, 王生生, 等.基于草图的空间数据检索研究[J].电子学报, 2010, 38(8):1819-1824. SHEN Shi-qun, LIU Da-you, WANG Sheng-sheng, et al.Research on spatial dataretrieval based on sketch[J].Acta Electronica Sinica, 2010, 38(8):1819-1824.(in Chinese)

[11] ChenM, Sheng F Q, et al.A sketch-based approach to human body modeling[J].Computers & Graphics, 2009, 33(4):521-541.

[12] 章菲倩, 孙正兴, 张尧烨, 宋沫飞.采用单笔画草绘的三维模型编辑方法[J].计算机辅助设计与图形学学报, 2010, 22(9):1522-1528. ZHANG Fei-qian, SUN Zheng-xing, ZHANG Yao-ye, SONG Mo-fei.A method of 3D model modification using freehand sketch with single stroke[J].Journal of Computer-Aided Design & Computer Graphics, 2010, 22(9):1522-1528.(in Chinese)

[13] Kraevoy V, Sheffer A, et al.Modeling from contour drawings[A].Proceedings of the 6th Eurographics Symposium on Sketch-Based Interfaces and Modeling[C].New York, USA:ACM, 2009.37-44.

[14] Judd T, Durand F, et al.Apparent ridges for line drawing[J].ACM Transactions on Graphics, 2007, 26(3):19:1-19:7.

[15] Saito T, Takahashi T.Comprehensible rendering of 3D shapes[J].SIGGRAPH Comput Graph, 1990, 24(4):197-206.

[16] Lee Y, Markosian L, et al.Line drawings via abstracted shading[J].ACM Transactions on Graphics, 2007, 26(3):18:1-18:6.

[17] KalogerakisE, Nowrouzezahrai D, et al.Data-driven curvature for real-time line drawing of dynamic scenes[J].ACM Transactions on Graphics, 2009, 28(1):1-13.

[18] Lafferty J, McCallum A, et al.Conditional random lds:Probabilistic models for segmenting and labeling sequence data[A].Proceedings of the Eighteenth International Conference on Machine Learning[C].Williamstown, MA, USA:Morgan Kaufmann, 2001.282-289.

[19] Ramos F, Fox D, et al.CRF-matching:Conditional random fields for feature-based scan matching[A].Proc.of Robotics:Science and Systems[C].Cambridge, Massachusetts:MIT Press, 2007.201-208.

[20] Canny J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6):679-698.

[21] Murphy K, Weiss Y, et al.Loopy belief propagation for approximate inference:An empirical study[A].Proceedings of the Conference on Uncertainty in Artficial Intelligence[C].Stockholm, Sweden:Morgan/Kaufmann, 1999.467-475.

[22] Veltkamp R C, Hagedoorn M.State-of-the-art in Shape Matching[M].London, UK:Springer-Verlag, 1999.87-119.

基于条件随机场的模型特征线提取方法

Extraction of Feature Lines for 3D Model Based on Conditional Random Fields

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

[1]	任明荣, 孟娟, 王普. MEMS-INS室内行人定位三维地图匹配算法[J]. 电子学报, 2021, 49(1): 111-116.
[2]	王泽宇, 吴艳霞, 张国印, 布树辉. 基于空间结构化推理深度融合网络的RGB-D场景解析[J]. 电子学报, 2018, 46(5): 1253-1258.
[3]	刘威, 周婷, 袁淮, 赵宏. 基于多条件随机场模型的图像3D空间布局理解[J]. 电子学报, 2017, 45(2): 328-336.
[4]	孟颍辉, 陈剑, 闻英友, 赵宏. 基于贪婪思想的二阶段无线传感器网络定位算法[J]. 电子学报, 2014, 42(2): 328-334.
[5]	黄沛杰, 朱立华, 刘学慧, 吴恩华, 王传铭. 针对实时视觉通信的图像序列自动提炼[J]. 电子学报, 2009, 37(S1): 42-50,56.
[6]	冯元勇;;孙乐;张大鲲;李文波;. 基于小规模尾字特征的中文命名实体识别研究[J]. 电子学报, 2008, 36(9): 1833-1838.
[7]	周俊生, 戴新宇, 尹存燕, 陈家骏. 基于层叠条件随机场模型的中文机构名自动识别[J]. 电子学报, 2006, 34(5): 804-809.