Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Dynamic Time Warping for Binocular Hand Tracking and Reconstruction
 

Summary: Dynamic Time Warping for Binocular Hand Tracking and
Reconstruction
Javier Romero, Danica Kragic Ville Kyrki Antonis Argyros
CAS-CVAP-CSC Dept. of Information Technology Institute of Computer Science
KTH, Stockholm, Sweden LUT, Lappeenranta, Finland FORTH, Crete, Greece
Abstract-- We show how matching and reconstruction of
contour points can be performed using Dynamic Time Warping
(DTW) for the purpose of 3D hand contour tracking. We
evaluate the performance of the proposed algorithm in object
manipulation activities and perform comparison with the Iter-
ative Closest Point (ICP) method.
I. INTRODUCTION
In a learning by demonstration context, a robot observes
a human performing a task, after which it is supposed
to perform the action and thus learn through an imitation
process. In order to imitate a human action, the robot needs
to retrieve information about of how a specific task was
performed it needs to register the movement of the whole or
parts of a human body and an object, as well as the sequence
of different actions performed on the object. The goal of our

  

Source: Argyros, Antonis - Foundation of Research and Technology, Hellas & Department of Computer Science, University of Crete

 

Collections: Computer Technologies and Information Sciences