[1] Xing Weiwei, Liu Weibin, Yuan Baozong,. Part-level 3-D object classification with improved interpretation tree [J]. Journal of Southeast University (English Edition), 2007, 23 (2): 221-225. [doi:10.3969/j.issn.1003-7985.2007.02.014]

Copy

Part-level 3-D object classification with improved interpretation tree()

基于改进解释树的部件级三维物体分类

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

23

Issue:

2007 2

Page:

221-225

Research Field:

Computer Science and Engineering

Publishing date:

2007-06-30

Info

Title:

Part-level 3-D object classification with improved interpretation tree

基于改进解释树的部件级三维物体分类

Author(s):

Xing Weiwei¹;  Liu Weibin²;  Yuan Baozong²

¹ School of Software, Beijing Jiaotong University, Beijing 100044, China
² Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China

邢薇薇¹;  刘渭滨²;  袁保宗²

¹ 北京交通大学软件学院, 北京 100044; ² 北京交通大学信息科学研究所, 北京 100044

Keywords:

3-D object classification;  shape match;  similarity measure;  interpretation tree

三维物体分类;  形状匹配;  相似性度量;  解释树

PACS:

TP391

DOI:

10.3969/j.issn.1003-7985.2007.02.014

Abstract:

For classifying unknown 3-D objects into a set of predetermined object classes, a part-level object classification method based on the improved interpretation tree is presented.The part-level representation is implemented, which enables a more compact shape description of 3-D objects.The proposed classification method consists of two key processing stages: the improved constrained search on an interpretation tree and the following shape similarity measure computation.By the classification method, both whole match and partial match with shape similarity ranks are achieved;especially, focus match can be accomplished, where different key parts may be labeled and all the matched models containing corresponding key parts may be obtained.A series of experiments show the effectiveness of the presented 3-D object classification method.

为了实现对未知物体的分类, 提出了一种基于改进解释树的部件级三维物体分类方法.采用部件级描述形式, 使得对物体类的描述更加简洁.所提的物体分类方法主要包括2个核心处理模块, 即改进的约束解释树搜索和形状相似性度量计算.利用该方法, 不但能够进行未知物体与三维模型之间的全局匹配和部分匹配, 得到具有形状相似度排序的分类结果;而且能够实现焦点匹配, 即对同一个未知物体, 为其标注不同的关键部件, 通过焦点匹配便可以获得所有包含对应关键部件的三维模型.大量的实验结果证明了所提出的部件级三维物体分类方法的有效性.

References:

[1] Tangelder J W H, Veltkamp R C.Polyhedral model retrieval using weighted point sets [J].International Journal on Image and Graphics, 2003, 3(1):209-229.
[2] Csákány P, Wallace A M.Representation and classification of 3-D objects [J].IEEE Trans on Systems, Man, and Cybernetics—Part B:Cybernetics, 2003, 33(4):638-647.
[3] Krivic J, Solina F.Part-level object recognition using superquadrics [J].Computer Vision and Image Understanding, 2004, 95(1):105-126.
[4] Huber D, Kapuria A, Donamukkala R R, et al.Parts-based 3-D object classification [C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington DC, 2004, 2:82-89.
[5] Borges D L, Fisher R B.Class-based recognition of 3-D objects represented by volumetric primitives [J].Image and Vision Computing, 1997, 15(8):655-664.
[6] Biederman I.Recognition-by-components:a theory of human image understanding [J].Psychological Review, 1987, 94:115-147.
[7] Grimson W E L, Huttenlocher D P.On the verification of hypothesized matches in model-based recognition [J].IEEE Trans on Pat Anal Machin Intel, 1991, 13(12):1201-1213.
[8] Xing Weiwei, Liu Weibin, Yuan Baozong.Superquadric similarity measure with spherical harmonics in 3-D object recognition [J].Chinese Journal of Electronics, 2005, 14(3):529-534.

Memo

Memo:

Biographies: Xing Weiwei(1980—), female, doctor, wwxing@bjtu.edu.cn;Yuan Baozong(1932—), male, doctor, professor, bzyuan@bjtu.edu.cn.

Common functions