Next Article in Journal
Enhanced Spatial and Extended Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
Next Article in Special Issue
An Evaluation of Three Kinematic Methods for Gait Event Detection Compared to the Kinetic-Based ‘Gold Standard’
Previous Article in Journal
A Secure Video Steganography Based on the Intra-Prediction Mode (IPM) for H264
Previous Article in Special Issue
Shedding Light on Nocturnal Movements in Parkinson’s Disease: Evidence from Wearable Technologies
Open AccessArticle

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

1
Department of Computer Science, University of Bristol, Bristol BS8 1UB, UK
2
Université de Toulon, Aix Marseille Univ, CNRS, LIS, Marseille, France
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(18), 5258; https://doi.org/10.3390/s20185258
Received: 11 August 2020 / Revised: 5 September 2020 / Accepted: 9 September 2020 / Published: 15 September 2020
(This article belongs to the Special Issue Sensor-Based Systems for Kinematics and Kinetics)
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. View Full-Text
Keywords: movement analysis; view-invariant convolutional neural network (CNN); health monitoring movement analysis; view-invariant convolutional neural network (CNN); health monitoring
Show Figures

Figure 1

MDPI and ACS Style

Sardari, F.; Paiement, A.; Hannuna, S.; Mirmehdi, M. VI-Net—View-Invariant Quality of Human Movement Assessment. Sensors 2020, 20, 5258. https://doi.org/10.3390/s20185258

AMA Style

Sardari F, Paiement A, Hannuna S, Mirmehdi M. VI-Net—View-Invariant Quality of Human Movement Assessment. Sensors. 2020; 20(18):5258. https://doi.org/10.3390/s20185258

Chicago/Turabian Style

Sardari, Faegheh; Paiement, Adeline; Hannuna, Sion; Mirmehdi, Majid. 2020. "VI-Net—View-Invariant Quality of Human Movement Assessment" Sensors 20, no. 18: 5258. https://doi.org/10.3390/s20185258

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop