Design of embedded gesture recognition system for robotic applications

Ainur Begalinova, Almas Shintemirov

2014

Closed access Metadata (CSL-JSON)
DOI 10.1109/icaict.2014.7035931
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Recent developments of system-on-chip (SOC) technologies have found a lot of applications in robotic embedded system design. Powerful miniature SOC boards allow development of mobile robots with advanced onboard computation performance executing complex data processing and control algorithms. This paper presents a preliminary results of an embedded system design of a mobile robot platform implementing gesture recognition and control. The system is designed using a BeagleBoard-xM SOC board and an Asus Xtion Live 3D camera. System implementation and analysis of a human hand detection and tracking from depth images are discussed.