|
Title:
|
A FAULT TOLERANT GESTURE RECOGNITION SYSTEM FOR MOBILE ROBOT |
|
Author(s):
|
Vanderlei Bonato , Márcio M. Fernandes , Eduardo Marques |
|
ISBN:
|
972-99353-8-6 |
|
Editors:
|
João M. P. Cardoso |
|
Year:
|
2005 |
|
Edition:
|
Single |
|
Keywords:
|
Fault Tolerant Gesture Recognition, Robotics, Vision System, SoC, RAM-Based Neural Network, MajorityVoting. |
|
Type:
|
Workshop Paper |
|
First Page:
|
59 |
|
Last Page:
|
68 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
This paper presents a vision system for gesture recognition with 100%of success rate.The system has been
implemented as a SoC(System-on-Chip)using reconfigurable computing technology,being integrated into a mobile robot control platform.The gesture images are captured by means of a CMOS digital camera.After
pre-processing steps,those are sent to the Fault Tolerant Module(FTM)for the actual recognition process.The FTM implements a RAM-based neural network(n-tuple classifier),using three knowledge bases.In addition,a majority voting
technique is used to improve the recognition
confidence level.Experimental results have shown the system to be robust,and also flexibleas new gesture patterns can be included by means of the on-chip trainning capabilitie. |
|
|
|
|
|
|
