Extracting 3D model feature lines based on conditional random fields  

作　　者：Yao-ye ZHANG Zheng-xing SUN Kai LIU Mo-fei SONG Fei-qian ZHANG 

机构地区：[1]State Key Laboratory for Novel Software Technology, Nanjing University

出　　处：《Journal of Zhejiang University-Science C(Computers and Electronics)》2013年第7期551-560,共10页浙江大学学报C辑（计算机与电子（英文版）

基　　金：supported by the National Natural Science Foundation of China (Nos. 61272219, 61100110, and 61021062);the National High-Tech R&D Program (863) of China (No. 2007AA01Z334);the Program for New Century Excellent Talents in University (No. NCET-0404605);the Science and Technology Program of Jiangsu Province, China (Nos. BE2010072, BE2011058, and BY2012190)

摘　　要：We propose a 3D model feature line extraction method using templates for guidance. The 3D model is first projected into a depth map, and a set of candidate feature points are extracted. Then, a conditional random fields (CRF) model is established to match the sketch points and the candidate feature points. Using sketch strokes, the candidate feature points can then be connected to obtain the feature lines, and using a CRF-matching model, the 2D image shape similarity features and 3D model geometric features can be effectively integrated. Finally, a relational metric based on shape and topological similarity is proposed to evaluate the matching results, and an iterative matching process is applied to obtain the globally optimized model feature lines. Experimental results showed that the proposed method can extract sound 3D model feature lines which correspond to the initial sketch template.We propose a 3D model feature line extraction method using templates for guidance. The 3D model is first projected into a depth map, and a set of candidate feature points are extracted. Then, a conditional random fields （CRF） model is established to match the sketch points and the candidate feature points. Using sketch strokes, the candidate feature points can then be con- nected to obtain the feature lines, and using a CRF-matching model, the 2D image shape similarity features and 3D model geo- metric features can be effectively integrated. Finally, a relational metric based on shape and topological similarity is proposed to evaluate the matching results, and an iterative matching process is applied to obtain the globally optimized model feature lines. Experimental results showed that the proposed method can extract sound 3D model feature lines which correspond to the initial sketch template.

关 键 词：Nonphotorealistic rendering Model feature lines Conditional random fields Feature line metrics Iterative matching 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]