The term IoT (Internet of Things) refers to the set of technologies and protocols that enable the connection of physical devices with the Internet allowing the exchange and processing of information. To support and enable data processing by these systems, in recent years, there are more and more AI (Artificial Intelligence) algorithms within IoT solutions. The latter with AI integration, however, require both the ability to collect large amounts of data and the significant computing resources needed to process them. The current Cloud paradigm does not best support applications with stringent requirements in terms of response time or security. To overcome these limitations, research is focusing on the development of Edge Computing systems, i.e., based on a distributed computing model in which data processing occurs as close as possible to where the data is collected. In this work we do not aspire to the invention of a method or model of Edge Computing, but rather we want to analyze and verify the possibilities of the technology on the market. Developing an image classification system of subjects with or without face masks, we evaluate the performance increases obtained on a Raspberry Pi device, through the use of VPU (Vision Processing Unit) Movidius™ Myriad 2 and Myriad X accelerators. Developing an image classification system of subjects with or without face masks.

Image sensors and VPU acceleration for data analysis and classification

Iannello G.;Merone M.;Vollero L.
2021-01-01

Abstract

The term IoT (Internet of Things) refers to the set of technologies and protocols that enable the connection of physical devices with the Internet allowing the exchange and processing of information. To support and enable data processing by these systems, in recent years, there are more and more AI (Artificial Intelligence) algorithms within IoT solutions. The latter with AI integration, however, require both the ability to collect large amounts of data and the significant computing resources needed to process them. The current Cloud paradigm does not best support applications with stringent requirements in terms of response time or security. To overcome these limitations, research is focusing on the development of Edge Computing systems, i.e., based on a distributed computing model in which data processing occurs as close as possible to where the data is collected. In this work we do not aspire to the invention of a method or model of Edge Computing, but rather we want to analyze and verify the possibilities of the technology on the market. Developing an image classification system of subjects with or without face masks, we evaluate the performance increases obtained on a Raspberry Pi device, through the use of VPU (Vision Processing Unit) Movidius™ Myriad 2 and Myriad X accelerators. Developing an image classification system of subjects with or without face masks.
2021
978-1-6654-1980-2
Edge Computing
Inference at the Edge
Movidius™
Raspberry
VPU
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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12610/65282
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact