Design of a real-time gesture recognition system: high performance through algorithms and software

Author

Ozer, I. Burak ; Lu, Tiehan ; Wolf, Wayne

Author_Institution

Princeton Univ., NJ, USA

Volume

22

Issue

3

fYear

2005

fDate

5/1/2005 12:00:00 AM

Firstpage

57

Lastpage

64

Abstract

The embedded systems group at Princeton University in New Jersey has developed, as an example of smart cameras, a gesture recognition system that can build a complete model of the torso and recognize gestures at 30 frames/s. Designing a real-time gesture recognition system is a complex task that involves many issues such as algorithm design, processing speed, system architecture, and video interface. In this article, the authors describe a method to manage the complexity by decomposing the entire process into different design and implementation phases.

Keywords

CAD; gesture recognition; image classification; image colour analysis; image matching; video cameras; video signal processing; boundary extraction; complexity management; graph matching; optimization; pattern classification; real-time gesture recognition system; skin color detection; smart camera; super-ellipse fitting; system architecture; video interface; Algorithm design and analysis; Application software; Biological system modeling; Humans; MATLAB; Mathematical model; Process design; Real time systems; Security; Smart cameras;

fLanguage

English

Journal_Title

Signal Processing Magazine, IEEE

Publisher

ieee

ISSN

1053-5888

Type

jour

DOI

10.1109/MSP.2005.1425898

Filename

1425898