A Cloud-Based Scene Recognition framework for In-Home Assistive Robot

The rapidly increasing number of elderly people has led to the development of in-home assistive robots for assisting and monitoring elderly people in their daily life. To these ends, indoor scene and human activity recognition is fundamental. However, image processing is an expensive process, in computational, energy, storage and pricing terms, which can be problematic for consumer robots. For this reason, we propose the use of computer vision cloud services and a Naive Bayes model to perform indoor scene and human daily activity recognition. We implement the developed method on the telepresence robot Double to make it autonomously find and approach the person in the environment as well as detect the performed activity.

Risorse UNIGE


Titolo: A Cloud-Based Scene Recognition framework for In-Home Assistive Robot
Autori: 
SGORBISSA, ANTONIO
MENICATTI, ROBERTO
Data di pubblicazione: 2017
Handle: http://hdl.handle.net/11567/883767
Appare nelle tipologie:04.01 - Contributo in atti di convegno

File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
 
 
 
Powered by IRIS-about IRIS-Utilizzo dei cookie
Logo CINECA  Copyright © 2020