Structure inference and pose-estimation based on symmetry of object

Author

Wen, Wei ; Yuan, Baozong

Author_Institution

Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China

fYear

1994

fDate

22-26 Aug 1994

Firstpage

766

Abstract

Symmetry identification of an object is one important part of perceptual organization in the human visual system. This paper presents an algorithm for inferring structure and estimating pose or orientation of an object based on its symmetry. We first analyse the geometric relationships between 3D symmetry planes of an object and 2D symmetry axes of an image. Based on them we can determine the existence of symmetry planes in 3D from image symmetry and recover the structure of the object. Then we calculate the orientation parameters of three mutually orthogonal symmetry axes in 3D, and obtain the pose of the object. The experimental results are very satisfactory

Keywords

Hough transforms; computational geometry; inference mechanisms; object recognition; 2D symmetry axes; 3D symmetry planes; Hough Transform; geometric relationships; human visual system; image symmetry; object symmetry; orientation parameters; perceptual organization; pose-estimation; structure inference; symmetry identification; three dimensional symmetry planes; two dimensional symmetry axes; Application software; Computer vision; Humans; Inference algorithms; Information science; Libraries; Object recognition; Psychology; Robustness; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON '94. IEEE Region 10's Ninth Annual International Conference. Theme: Frontiers of Computer Technology. Proceedings of 1994

Print_ISBN

0-7803-1862-5

Type

conf

DOI

10.1109/TENCON.1994.369208

Filename

369208