QMAR was recorded using 6 Primesense cameras (3 different frontal views and 3 different side views) with 38 healthy subjects, 8 female and 30 male. The subjects were trained by a physiotherapist to perform two different types of movements while simulating three ailments, resulting in five overall possibilities: a return Walk to approximately the original position while simulating Parkinsons (W-P), Stroke (W-S) and Limp (W-L), and Standing up and Sitting down with Parkinson (SS-P) and Stroke (SS-S).
The dataset includes RGB (and depth and skeleton) data, although in this version, only the RGB data is released. We may be able to supply depth/skeleton data on request, however note they are available for two views only.
All documents and papers that use the QMAR dataset, or any derived part of the dataset, should cite the following paper:
F. Sardari, A. Paiement, S. Hannuna, M. Mirmehdi; VI-Net: View-Invariant Quality of Human Movement Assessment, Sensors, 2020, 20, 5258.
- Movement Quality Assessment
- Multiview Dataset
- Computer Vision