Combination Strategies for 2D Features to Recognize 3D Gestures

Author

Aran, Oya ; Akarun, Lale

Author_Institution

Bilgisayar Muhendisligi Bolumu, Bogazici Univ., Istanbul

fYear

2006

fDate

17-19 April 2006

Firstpage

1

Lastpage

4

Abstract

In this study, using a two camera setup, we designed a system that recognizes 3D gestures. When 3D reconstruction is not possible or infeasible, combining 2D hand trajectories at feature or decision level increases the system performance drastically. The trajectories are extracted by tracking the center-of-mass of the hand and the width, height and orientation of the enclosing ellipse. Trajectories are then smoothed using a Kalman filter. Following the translation and scale normalization, the trajectories are modelled using hidden Markov models (HMM) and using support vector machines (SVM) by converting the trajectories to fixed length using re-sampling. Trajectories extracted from different cameras are combined at different levels and the effect to the system performance is observed. The best result is obtained by modelling the trajectories using HMMs and combining at decision level, with %1 error in 210 test examples

Keywords

Kalman filters; feature extraction; gesture recognition; hidden Markov models; image sampling; support vector machines; video cameras; 2D features; 3D gesture recognition; HMM; Kalman filter; SVM; camera setup; combination strategy; hidden Markov model; resampling; scale normalization; support vector machine; trajectory extraction; Cameras; Hidden Markov models; Kalman filters; Support vector machines; System performance; Testing; Trajectory;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communications Applications, 2006 IEEE 14th

Conference_Location

Antalya

Print_ISBN

1-4244-0238-7

Type

conf

DOI

10.1109/SIU.2006.1659820

Filename

1659820