Automatic Estimation of Self-Reported Pain by Interpretable Representations of Motion Dynamics

TL;DR

This paper introduces an interpretable, video-based method for automatic pain intensity estimation using facial motion dynamics, leveraging Riemannian manifold representations and SVR, achieving competitive results on a standard dataset.

Contribution

It presents a novel approach combining Riemannian geometry and temporal smoothing for pain estimation from facial movements, improving interpretability and performance.

Findings

Competitive accuracy with state-of-the-art methods

Effective use of Riemannian manifold for facial trajectory representation

Robustness demonstrated through cross-validation

Abstract

We propose an automatic method for pain intensity measurement from video. For each video, pain intensity was measured using the dynamics of facial movement using 66 facial points. Gram matrices formulation was used for facial points trajectory representations on the Riemannian manifold of symmetric positive semi-definite matrices of fixed rank. Curve fitting and temporal alignment were then used to smooth the extracted trajectories. A Support Vector Regression model was then trained to encode the extracted trajectories into ten pain intensity levels consistent with the Visual Analogue Scale for pain intensity measurement. The proposed approach was evaluated using the UNBC McMaster Shoulder Pain Archive and was compared to the state-of-the-art on the same data. Using both 5-fold cross-validation and leave-one-subject-out cross-validation, our results are competitive with respect to state-of-the-art methods.