A Resource Constrained Neural Network for the Design of Embedded Human Posture Recognition Systems

A Resource Constrained Neural Network for the Design of Embedded Human Posture Recognition Systems

A custom HW design of a Fully Convolutional Neural Network (FCN) is presented in this paper to implement an embeddable Human Posture Recognition (HPR) system capable of very high accuracy both for laying and sitting posture recognition. The FCN exploits a new base-2 quantization scheme for weight an...

Full description

Bibliographic Details
Main Authors: Gian Domenico Licciardo, Alessandro Russo, Alessandro Naddeo, Nicola Cappetti, Luigi Di Benedetto, Alfredo Rubino, Rosalba Liguori
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Applied Sciences
Subjects:
posture recognition
human behavior
Convolutional Neural Network
low-power digital design
Online Access:https://www.mdpi.com/2076-3417/11/11/4752

Internet

https://www.mdpi.com/2076-3417/11/11/4752

Similar Items