VI-Net—View-Invariant Quality of Human Movement Assessment

We propose a view-invariant method towards the assessment of the quality of human movements which does not rely on skeleton data. Our end-to-end convolutional neural network consists of two stages, where at first a view-invariant trajectory descriptor for each body joint is generated from RGB images...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Sensors (Basel, Switzerland) Jg. 20; H. 18; S. 5258
Hauptverfasser: Sardari, Faegheh, Paiement, Adeline, Hannuna, Sion, Mirmehdi, Majid
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland MDPI 15.09.2020
MDPI AG
Schlagworte:
Artificial Intelligence
Computer Science
Computer Vision and Pattern Recognition
health monitoring
Humans
Image Processing
Machine Learning
Movement
movement analysis
Neural and Evolutionary Computing
Neural Networks, Computer
Signal and Image Processing
view-invariant convolutional neural network (CNN)
health monitoring
view-invariant convolutional neural network (CNN)
movement analysis
ISSN:1424-8220, 1424-8220
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose a view-invariant method towards the assessment of the quality of human movements which does not rely on skeleton data. Our end-to-end convolutional neural network consists of two stages, where at first a view-invariant trajectory descriptor for each body joint is generated from RGB images, and then the collection of trajectories for all joints are processed by an adapted, pre-trained 2D convolutional neural network (CNN) (e.g., VGG-19 or ResNeXt-50) to learn the relationship amongst the different body parts and deliver a score for the movement quality. We release the only publicly-available, multi-view, non-skeleton, non-mocap, rehabilitation movement dataset (QMAR), and provide results for both cross-subject and cross-view scenarios on this dataset. We show that VI-Net achieves average rank correlation of 0.66 on cross-subject and 0.65 on unseen views when trained on only two views. We also evaluate the proposed method on the single-view rehabilitation dataset KIMORE and obtain 0.66 rank correlation against a baseline of 0.62.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s20185258