Articulated object recognition, or: how to generalize the generalized Hough transform

Author

Beinglass, Avinoam ; Wolfson, Haim J.

Author_Institution

Dept. of Comput. Sci., Tel Aviv Univ., Israel

fYear

1991

fDate

3-6 Jun 1991

Firstpage

461

Lastpage

466

Abstract

A method for model-based recognition of articulated objects in cluttered scenes is presented. The objects consist of rigid parts connected by rotary or prismatic joints. The method is based on an extension of the generalized Hough transform approach. It is applicable to various viewing transformations. Unlike previous methods there is no significant degradation in performance for recognition of articulated objects compared with the recognition of rigid objects containing similar amounts of information. The method was implemented and successfully tested for recognition of partially overlapping 2-D objects with rotary joints which have undergone rotation, translation, and scaling

Keywords

pattern recognition; transforms; articulated object recognition; cluttered scenes; generalized Hough transform; model-based recognition; partially overlapping 2-D objects; performance; prismatic joints; rotary; scaling; translation; viewing transformations; Computer science; Degradation; Face detection; Layout; Machine vision; Machinery; Object recognition; Production facilities; Service robots; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on

Conference_Location

Maui, HI

ISSN

1063-6919

Print_ISBN

0-8186-2148-6

Type

conf

DOI

10.1109/CVPR.1991.139736

Filename

139736