计算机科学 ›› 2014, Vol. 41 ›› Issue (4): 292-296.

• 图形图像与模式识别 • 上一篇    下一篇

三维可变形物体的特征点层次提取

潘翔,章国栋,陈启华   

  1. 浙江工业大学计算机科学与技术学院 杭州310023;浙江工业大学计算机科学与技术学院 杭州310023;浙江工业大学计算机科学与技术学院 杭州310023
  • 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(61272304),浙江省自然科学基金(Y1110780)资助

Hierarchically Extracting Feature Points of 3D Deformable Shapes

PAN Xiang,ZHANG Guo-dong and CHEN Qi-hua   

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

摘要: 针对不同姿态下的三维可变形物体特征点一致性问题,提出了一种基于样例学习的特征点层次提取方法。该方法首先提取出三维模型的外部特征点;其次,根据外部特征点在不同姿态下所具有的局部特征相似性,采用热核信号和支持向量机识别出外部特征点的语义标签;最后,根据语义标签和测地距离,层次地提取出三维模型的其它语义特征点。实验结果表明,该方法能很好地得到三维可变形物体的各种语义上的有效特征点。

关键词: 三维模型特征点,层次提取,语义标签,支持向量机,热核信号

Abstract: This paper addressed the problem about the consistency of feature points,with different posed of 3D deformable shapes.It proposed a new algorithm to hierarchically detect feature points,based on the learning samples.Firstly,the algorithm detects the external feature points from input 3D shapes.Secondly,according to the local similarity of external points under different postures,semantic tags of external point are recognized by heat kernel signature and support vector machine.Finally,other feature points are hierarchically extracted by combining semantic tags and the geodesic distance of external points.In experiment,the proposed algorithm is proven to be very robust in detecting semantic-aware feature points on deformable shapes.

Key words: 3D model feature point,Hierarchical extraction,Semantic tags,Support vector machine,Heat kernel signature

[1] Chen D Y,Pei X T.On Visual Similarity Based 3D Model Re-trieval[J].Computer Graphics Forum,2003,2(3):223-232
[2] Karni Z,Gotsman C.Spectral compress of mesh geometry[C]∥Proceedings of SIGGRPATH’ 00.USA:ACM press,2000,279-286
[3] Sagi K,George L,Ayellet T.Mesh Segementation using feature point and core extraction[J].The Visual Computer,2005,9:649-659
[4] Bronsteiny A,Bronsteiny M,Bustos B.SHREC 2010:robustfeature detection and description benchmark[C]∥Proceedings of the IEEE Conference on CVPR.New York:IEEE computer society press,2010
[5] Mikolajczyk K,Schmid C.Scale and Affine invariant interestpoint detectors[J].International Journal of Computer Vision,2004,60(1):63-86
[6] Schmid C,Mohr R,Bauckhage C.Evaluation of interest pointdetectors[J].International Journal of Computer Vision,2000,37(2):151-172
[7] Sipiran I,Bustos B.Harris 3D:A robust extension of the Harris operator for interest point detection on 3D meshes[J].The Vi-sual Computer,2011,27(11):963-976
[8] Castellani U,Cristani M,Fantoni S.Sparse points matching by combining 3D mesh saliency with statistical descriptors[J].Computer Graphics Forum,2008,27(2):643-652
[9] Zaharescu A,Boyer E,Varanasi K.Surface feature detection and description with applications to mesh matching[C]∥Procee-dings of IEEE Conference on CVPR.New York:IEEE computer society press,2009:373-380
[10] Zou G,Hua J,Dong M.Surface matching with salient keypoints in geodesic scale space[J].Computer Animation and Virtual Worlds,2008,19(3):399-410
[11] Sun J,Ovsjanikov M,Guibas L.A concise and provably informative multi-scale signature based on heat diffusion[J].Conputer Graphics Forum,2009,28:1383-1392
[12] Mian A,Bennamoun M,Owens R.On the Repeatability andQuality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes[J].International Journal of Computer Vision,2009,89(2):348-361
[13] 陈启华,潘翔,张三元.语义知识约束的三维人体特征点检测和分割[J].计算机辅助设计与图形学学报,2011,23(6):1061-1068
[14] Kristin P,Campbell C.Support Vector machines:hype or hallelujah[C]∥Proceedings of ACM SIGKDD Explorations Newsletter.fNew York:ACM Press,2000,2(2):1-13
[15] Kim V G,Yaron L,Thomas F.Blended Intrinsic Maps[J].ACMTransaction on Graphics,2011,0(4)
[16] Robert W,Sumner,Jovan P.Deformation Transfer for Triangle Meshes[J].ACM Transactions on Graphics,2004,3(3):399-405

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!