Vision-based 3D Shape Reconstructure of a Non-Rigid Object

Author

Fangwen, Zhu ; Zhenbang, Gong ; Ze, Cui

Author_Institution

Sch. of Electromechanical Eng. & Autom., Shanghai Univ.

fYear

2006

fDate

25-28 June 2006

Firstpage

1769

Lastpage

1773

Abstract

A method for positioning the feature points on a nonrigid object that have small nonrigid motion are described. It is applied to reconstruct a human being´s hand gesture in 3D space in a vision-based mechanical gripper control system. The positioning method provided a simple way for matching feature points between images in the stereo vision system. The result is used on a real time control system of a dexterous gripper and the gesture information is converted to the action gesture of a dexterous gripper by a specially designed algorithm, it also can be used to reconstruct a virtual hand skeleton

Keywords

dexterous manipulators; position control; robot vision; dexterous gripper; positioning method; real time control system; stereo vision system; virtual hand skeleton; vision-based 3D shape reconstructure; vision-based mechanical gripper control system; Algorithm design and analysis; Control systems; Grippers; Humans; Image converters; Image reconstruction; Real time systems; Shape; Skeleton; Stereo vision; Stereo vision-based system; dexterous mechanical gripper; feature points positioning and matching;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Automation, Proceedings of the 2006 IEEE International Conference on

Conference_Location

Luoyang, Henan

Print_ISBN

1-4244-0465-7

Electronic_ISBN

1-4244-0466-5

Type

conf

DOI

10.1109/ICMA.2006.257482

Filename

4026360