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

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-co...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2023-06, Vol.23 (11), p.5260
Main Authors: Guerra, Bruna Maria Vittoria, Ramat, Stefano, Beltrami, Giorgio, Schmid, Micaela
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
ambient assisted living
Artificial intelligence
Assisted living facilities
Cameras
Classification
Data acquisition
Data augmentation
Deep learning
Genetic algorithms
human action recognition
Kinematics
Monitoring
Monitoring systems
Privacy
recurrent neural network
Recurrent neural networks
Sensors
skeletal data
Time series
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1424-8220
1424-8220
DOI:10.3390/s23115260