Angle densities and recognition of 3D objects

Author

Malik, Raashid ; Whangbo, Taegkeun

Author_Institution

Dept. of Electr. & Comput. Eng., New Jersey Inst. of Technol., Newark, NJ, USA

Volume

19

Issue

1

fYear

1997

fDate

1/1/1997 12:00:00 AM

Firstpage

52

Lastpage

57

Abstract

Recognition of 3D objects using computer vision is complicated by the fact that geometric features vary with view orientation. An important factor in designing recognition algorithms in such situations is understanding the variation of certain critical features such as angles. In this paper we derive the two dimensional joint density function of two angles in a scene given an isotropic view orientation and an orthographic projection. The analytic expression for the densities are useful in determining statistical decision rules to recognize surfaces and objects. Experiments to evaluate the usefulness of the proposed methods are reported

Keywords

computer vision; edge detection; object recognition; statistical analysis; 2D joint density function; 3D object recognition; angle densities; computer vision; isotropic view orientation; object recognition; orthographic projection; statistical decision rules; surface recognition; Algorithm design and analysis; Azimuth; Cameras; Computer vision; Density functional theory; Goniometers; Graphics; Image analysis; Image recognition; Joining processes; Layout; Probability density function; Random variables; Read only memory; Rotation measurement; Shape; Solids;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.566810

Filename

566810