VI-Net: View-Invariant Quality of Human Movement Assessment
This addresses the need for view-invariant movement assessment in rehabilitation, though it is incremental as it builds on existing CNN architectures.
The authors tackled the problem of assessing human movement quality from RGB images without relying on skeleton data, proposing VI-Net, which achieved an average rank correlation of 0.66 on cross-subject and 0.65 on unseen views using their new QMAR dataset.
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 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.