Skip to Main Content (Press Enter)

Logo UNIPV
  • ×
  • Home
  • Corsi
  • Insegnamenti
  • Professioni
  • Persone
  • Pubblicazioni
  • Strutture

UNIFIND
Logo UNIPV

|

UNIFIND

unipv.it
  • ×
  • Home
  • Corsi
  • Insegnamenti
  • Professioni
  • Persone
  • Pubblicazioni
  • Strutture
  1. Pubblicazioni

Recurrent Network Solutions for Human Posture Recognition Based on Kinect Skeletal Data

Articolo
Data di Pubblicazione:
2023
Abstract:
Ambient Assisted Living (AAL) systems are designed to provide unobtrusive and user-friendly support in daily life and can be used for monitoring frail people based on various types of sensors, including wearables and cameras. Although cameras can be perceived as intrusive in terms of privacy, low-cost RGB-D devices (i.e., Kinect V2) that extract skeletal data can partially overcome these limits. In addition, deep learning-based algorithms, such as Recurrent Neural Networks (RNNs), can be trained on skeletal tracking data to automatically identify different human postures in the AAL domain. In this study, we investigate the performance of two RNN models (2BLSTM and 3BGRU) in identifying daily living postures and potentially dangerous situations in a home monitoring system, based on 3D skeletal data acquired with Kinect V2. We tested the RNN models with two different feature sets: one consisting of eight human-crafted kinematic features selected by a genetic algorithm, and another consisting of 52 ego-centric 3D coordinates of each considered skeleton joint, plus the subject's distance from the Kinect V2. To improve the generalization ability of the 3BGRU model, we also applied a data augmentation method to balance the training dataset. With this last solution we reached an accuracy of 88%, the best we achieved so far.
Tipologia CRIS:
1.1 Articolo in rivista
Keywords:
ambient assisted living; deep learning; human action recognition; recurrent neural network; skeletal data
Elenco autori:
Guerra, Bruna Maria Vittoria; Ramat, Stefano; Beltrami, Giorgio; Schmid, Micaela
Autori di Ateneo:
GUERRA BRUNA MARIA VITTORIA
RAMAT STEFANO
SCHMID MICAELA
Link alla scheda completa:
https://iris.unipv.it/handle/11571/1485936
Link al Full Text:
https://iris.unipv.it//retrieve/handle/11571/1485936/569392/Recurrent%20Network%20Solutions%20for%20Human%20Posture%20Recognition%20Based%20on%20Kinect%20Skeletal%20Data.pdf
Pubblicato in:
SENSORS
Journal
  • Utilizzo dei cookie

Realizzato con VIVO | Designed by Cineca | 25.7.0.0