Validation of deep learning-based markerless 3D pose estimation.

Journal: PloS one
Published Date: Oct 20, 2022

Abstract

Deep learning-based approaches to markerless 3D pose estimation are being adopted by researchers in psychology and neuroscience at an unprecedented rate. Yet many of these tools remain unvalidated. Here, we report on the validation of one increasingly popular tool (DeepLabCut) against simultaneous measurements obtained from a reference measurement system (Fastrak) with well-known performance characteristics. Our results confirm close (mm range) agreement between the two, indicating that under specific circumstances deep learning-based approaches can match more traditional motion tracking methods. Although more work needs to be done to determine their specific performance characteristics and limitations, this study should help build confidence within the research community using these new tools.

Authors

  • Veronika Kosourikhina
    School of Psychological Sciences, Faculty of Medicine, Health and Human Sciences, Macquarie University, Sydney, Australia.
  • Diarmuid Kavanagh
    The MARCS Institute for Brain, Behaviour and Development, Western Sydney University, Parramatta, Australia.
  • Michael J Richardson
    Department of Psychology, Center for Elite Performance, Expertise and Training, and Perception in Action Research Center, Macquarie University, Sydney, NSW, Australia.
  • David M Kaplan
    ARC Centre of Excellence in Cognition and its Disorders, Macquarie University, Sydney, NSW, 2109, Australia; Department of Cognitive Science, Macquarie University, Sydney, NSW, 2109, Australia; Perception in Action Research Centre, Macquarie University, Sydney, NSW, 2109, Australia.

Keywords

External Resources

Popular Topics
Recent Journals