期刊文献+

三维物体的形态图表达方法 被引量:8

A Representation Method Based on aspect Graph for 3D Objects
下载PDF
导出
摘要 三维物体的表达方法是计算机视觉中的关键问题之一 ,现有的各种三维物体表达方法虽然在各自的识别中得到应用 ,但都存在各自的局限性 .用形态图表达三维物体是一种以视点为中心的表达方法 ,由于它列举了一个物体所有可能的“定性”形象 ,即它可使用最少的二维投影线图 (特征视图 )来表达一个完整的三维物体 ,因此使三维物体识别转化为 2 D与 2 D的匹配 .该文首先定义了二维线图拓扑结构等价的判别准则 ;然后给出了构造透明物体形态图的方法 ;最后根据拓扑结构等价准则来得到不透明物体的形态图和特征视图 ,并用圆锥与圆柱相交的实例进行了验证 . The 3D object representation method is a key problem on computer vision. The existent methods of 3D object representation have applied for 3D object recognition. But, they have themselves drawback. The 3D object representation method based on aspect graph is a kind of means on a center of the observant. It completely describes the 3D object by a finite set of 2D views of the object from different viewpoint. According to geometry structure of object, the set of viewpoint on the viewing space is partitioned into regions such that in each region the equivalent structure of the line drawing is consistent. An aspect is defined for the same of qualitative structure of topology of the line drawing. The 3D object representation method based on aspect graph makes 3D object recognition become problem on matching 2D image and 2D aspect. To begin with, The thesis defines a principle of equivalent structure of topology for the line drawing. In addition, it studies the partition theory and structure method of aspect graph for 3D object of transparent under perspective projection. At last, according to the principle of equivalent structure of topology, the aspect graph for 3D object of opaque and aspect are established. At the same time, it is proved for example of 3D object.
出处 《中国图象图形学报(A辑)》 CSCD 北大核心 2002年第9期906-910,共5页 Journal of Image and Graphics
基金 江西省跨世纪学科带头人培养计划 (第三批 ) 江西省自然科学基金项目 ( 99110 13)
关键词 表达方法 三维物体识别 三维物体表达 形态图 特征视图 计算机视觉 3D object recognition, 3D object representation, Aspect graph, Aspect
  • 相关文献

参考文献3

二级参考文献51

  • 1马利庄 王荣良.计算机辅助几何造型技术及其应用[M].北京:科学出版社,1997..
  • 2Chang I C,Pattern Recognition,1992年,25卷,10期,1075页
  • 3Plantinga W H, Dyer C R. Visibility, occlusion, and the aspect graph, IJCV, 1990,5:137-160.
  • 4Huttenloeber D P, Ullman Sb. Recognizing solid objects by alignment with an image. IJCV, 1990,5(2):195-212.
  • 5Nagao K, Grimson W E L. Object reeognition by alignment asing invaziant proiections of planar surfaces, MIT: AI Lab Tech. Report, 1994.
  • 6Jurie F. Robust hypothesis verification: application to modelbased obiect recognition. PR, 1999, 32:1069-1081.
  • 7Gandhi T, Camps O. Robust feature selection for object recogntition using uncertain 2d image data. In:IEEE Conference on Computer Vision and Pattern Recognition Seattle Washington, 1994:281-287.
  • 8Yi J H, Chelberg D M. Model based 3D ohject recognition using bayesian undexing. CVIU, 1998,69(1):87-105.
  • 9Grimson W E L, Penes T L. Localizing overlapping paris by searching the interpretation tree, ITPAMI, 1991,13(9): 920-934.
  • 10Ikeuchi K, Hong K S, Determining linear shape change: Toward automatic generation of object recognition programs. CVGIP,1991,53(2): 154-170.

共引文献28

同被引文献57

引证文献8

二级引证文献17

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部