计算机科学 ›› 2015, Vol. 42 ›› Issue (2): 277-279.doi: 10.11896/j.issn.1002-137X.2015.02.058

• 图形图像与模式识别 • 上一篇    下一篇

一种结合局部对称的三维模型对齐方法

朱新懿,耿国华   

  1. 西北大学信息科学与技术学院 西安710127,西北大学信息科学与技术学院 西安710127
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金面上项目:自动颅像重合身份认证关键技术研究(61172170),陕西省自然科学基金:结合多特征的三维颅面相似性比较(2014JQ8315),西北大学科学研究基金:三维颅面几何相似性的研究(12NW03),西北大学博士科研启动基金:三维颅面几何相似性比较(PR12277)资助

3D Model’s Alignment Approach Combining Partial Symmetry

ZHU Xin-yi and GENG Guo-hua   

  • Online:2018-11-14 Published:2018-11-14

摘要: 对称是自然界大多数模型具有的一种特征属性。针对三维模型坐标归一化过程中模型的对齐问题,提出了一种结合局部对称的三维模型对齐方法。通过三维模型的CPCA坐标轴确立其初始姿态,提出局部对称长度比来度量三维模型的局部对称性。以此为依据将三维模型分成两类,对于具有大于或等于2个局部对称平面的三维模型,利用最大局部对称长度比来确立最终姿态;对于仅有1个或没有局部对称平面的三维模型,通过面积替换质量,将模型达到力矩平衡时的姿态确立为最终姿态。算法既考虑到了模型的对称性质,又考虑了非对称模型的处理。实验结果显示了算法的有效性。

关键词: 三维模型检索,旋转归一化,主轴,对齐

Abstract: Symmetry is an important attribute for most natural objects.Alignment of 3D model is a key preprocess step for 3D model retrieval.For this problem,an approach to align 3D model using partial symmetry was proposed.First,CPCA coordinate planes of a 3D model are computed to establish the model’s initial pose.Then a new measure,which is called partial symmetry length ratio (PSLR),is introduced to judge the model’s partial symmetry plane.If the model has more than 2 planes,the pose with maximal PSLR is the estimated pose.Otherwise,moment balance is used to estimate the model’s final pose by computing area instead of mass.The algorithm takes into account both the symmetric nature of the model and the asymmetric model.The validity is showed by results demonstration.

Key words: 3D model retrieval,Rotation normalization,Principal axis,Alignment

[1] Vranic' D.3D model retrieval[D].Leipzig:University of Leipzig,2004
[2] Vranic' D,Saupe D.3D model retrieval[C] ∥Spring Conference on Computer Graphics and its Applications (SCCG2000).ACM,2000:89-93
[3] Chaouch M,Verroust-Blondet A.Alignment of 3D models[J].Graphical Model,2009,71:63-76
[4] 万丽莉.一种结合法线分布特征的三维模型旋转归一化方法[J].计算机辅助设计与图形学学报,2008,20(6):683-688
[5] Johan H,Li Bo,Wei Yuan-min,et al.3D model alignment based on minimum projection area[J].The Visual Computer,2011,27(6-8):565-574
[6] Joshua P,Philip S,Aleksey G,et al.A planar-reflective symmetry transform for 3D shapes[C]∥Proceedings of ACM SIGGRAPH 2006.ACM,2006:549-559
[7] Michael K,Thomas F,Szymon R.Symmetry descriptors and 3Dshape matching[C]∥Eurographics Symposium on Geometry Processing.ACM,2004:156-166
[8] Kazhdan M,Chazelle B,Dobkin D,et al.A reflective symmetry descriptor for 3D models[J].Algorithmica,2004,38(1):201-225
[9] Sfikas K,Theoharis T,Pratikakis I.ROSy+:3D Object PoseNormalization Based on PCA and Reflective Object Symmetry with Application in 3D Object Retrieval[J].International Journal of Computer Vision,2011,91(3):262-279
[10] Axenopoulos A,Litos G,Daras P.3D model retrieval using accurate pose estimation and view-based similarity[C]∥Proceedings of the 1st ACM International Conference on Multimedia Retrieval.ACM,2011:1-8
[11] Thompson D W.On Growth and Form[M].England:Cambridge University Press,1961
[12] Minovic P,Ishikawa S,Kato K.Symmetry identification of a 3-D object represented by octree[J].Pattern Analysis and Machine Intelligence,1993,15(5):507-514
[13] Princeton Shape Retrieval and Analysis Group.Princeton Shape Benchmark[DB/OL].2005-3-15.http://shape.cs.princeton.edu/benchmark
[14] Osada R,Funkhouser T,Chazelle B,et al.Shape distributions[J].ACM Transaction on Graphics,2002,21(4):807-832

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!