Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sale, Carter, Stolar, Melissa N., Patil, Gaurav, Gostelow, Michael J., Wallier, Julia, Macpherson, Margaret C., Kruger, Jan-Louis, Dras, Mark, Hosking, Simon G., Kallen, Rachel W., Richardson, Michael J.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.17767
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915872190234624
author Sale, Carter
Stolar, Melissa N.
Patil, Gaurav
Gostelow, Michael J.
Wallier, Julia
Macpherson, Margaret C.
Kruger, Jan-Louis
Dras, Mark
Hosking, Simon G.
Kallen, Rachel W.
Richardson, Michael J.
author_facet Sale, Carter
Stolar, Melissa N.
Patil, Gaurav
Gostelow, Michael J.
Wallier, Julia
Macpherson, Margaret C.
Kruger, Jan-Louis
Dras, Mark
Hosking, Simon G.
Kallen, Rachel W.
Richardson, Michael J.
contents Real-time cognitive workload monitoring is crucial in safety-critical environments, yet established measures are intrusive, expensive, or lack temporal resolution. We tested whether facial movement dynamics from a standard webcam could provide a low-cost alternative. Seventy-two participants completed a multitasking simulation (OpenMATB) under varied load while facial keypoints were tracked via OpenPose. Linear kinematics (velocity, acceleration, displacement) and recurrence quantification features were extracted. Increasing load altered dynamics across timescales: movement magnitudes rose, temporal organisation fragmented then reorganised into complex patterns, and eye-head coordination weakened. Random forest classifiers trained on pose kinematics outperformed task performance metrics (85% vs. 55% accuracy) but generalised poorly across participants (43% vs. 33% chance). Participant-specific models reached 50% accuracy with minimal calibration (2 minutes per condition), improving continuously to 73% without plateau. Facial movement dynamics sensitively track workload with brief calibration, enabling adaptive interfaces using commodity cameras, though individual differences limit cross-participant generalisation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17767
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Facial Movement Dynamics Reveal Workload During Complex Multitasking
Sale, Carter
Stolar, Melissa N.
Patil, Gaurav
Gostelow, Michael J.
Wallier, Julia
Macpherson, Margaret C.
Kruger, Jan-Louis
Dras, Mark
Hosking, Simon G.
Kallen, Rachel W.
Richardson, Michael J.
Human-Computer Interaction
Computer Vision and Pattern Recognition
Real-time cognitive workload monitoring is crucial in safety-critical environments, yet established measures are intrusive, expensive, or lack temporal resolution. We tested whether facial movement dynamics from a standard webcam could provide a low-cost alternative. Seventy-two participants completed a multitasking simulation (OpenMATB) under varied load while facial keypoints were tracked via OpenPose. Linear kinematics (velocity, acceleration, displacement) and recurrence quantification features were extracted. Increasing load altered dynamics across timescales: movement magnitudes rose, temporal organisation fragmented then reorganised into complex patterns, and eye-head coordination weakened. Random forest classifiers trained on pose kinematics outperformed task performance metrics (85% vs. 55% accuracy) but generalised poorly across participants (43% vs. 33% chance). Participant-specific models reached 50% accuracy with minimal calibration (2 minutes per condition), improving continuously to 73% without plateau. Facial movement dynamics sensitively track workload with brief calibration, enabling adaptive interfaces using commodity cameras, though individual differences limit cross-participant generalisation.
title Facial Movement Dynamics Reveal Workload During Complex Multitasking
topic Human-Computer Interaction
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.17767