Show simple item record

dc.contributor.authorCronin, NJ
dc.contributor.authorRantalainen, T
dc.contributor.authorAhtiainen, JP
dc.contributor.authorHynynen, E
dc.contributor.authorWaller, B
dc.date.accessioned2019-06-14T04:19:15Z
dc.date.available2019-06-14T04:19:15Z
dc.date.issued2019
dc.identifier.issn0021-9290
dc.identifier.doi10.1016/j.jbiomech.2019.02.021
dc.identifier.urihttp://hdl.handle.net/10072/385572
dc.description.abstractKinematic analysis is often performed with a camera system combined with reflective markers placed over bony landmarks. This method is restrictive (and often expensive), and limits the ability to perform analyses outside of the lab. In the present study, we used a markerless deep learning-based method to perform 2D kinematic analysis of deep water running, a task that poses several challenges to image processing methods. A single GoPro camera recorded sagittal plane lower limb motion. A deep neural network was trained using data from 17 individuals, and then used to predict the locations of markers that approximated joint centres. We found that 300–400 labelled images were sufficient to train the network to be able to position joint markers with an accuracy similar to that of a human labeler (mean difference < 3 pixels, around 1 cm). This level of accuracy is sufficient for many 2D applications, such as sports biomechanics, coaching/training, and rehabilitation. The method was sensitive enough to differentiate between closely-spaced running cadences (45–85 strides per minute in increments of 5). We also found high test–retest reliability of mean stride data, with between-session correlation coefficients of 0.90–0.97. Our approach represents a low-cost, adaptable solution for kinematic analysis, and could easily be modified for use in other movements and settings. Using additional cameras, this approach could also be used to perform 3D analyses. The method presented here may have broad applications in different fields, for example by enabling markerless motion analysis to be performed during rehabilitation, training or even competition environments.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherElsevier
dc.relation.ispartofpagefrom75
dc.relation.ispartofpageto82
dc.relation.ispartofjournalJournal of Biomechanics
dc.relation.ispartofvolume87
dc.subject.fieldofresearchBiomedical engineering
dc.subject.fieldofresearchMechanical engineering
dc.subject.fieldofresearchSports science and exercise
dc.subject.fieldofresearchcode4003
dc.subject.fieldofresearchcode4017
dc.subject.fieldofresearchcode4207
dc.titleMarkerless 2D kinematic analysis of underwater running: A deep learning approach
dc.typeJournal article
dc.type.descriptionC1 - Articles
dc.type.codeC - Journal Articles
gro.hasfulltextNo Full Text
gro.griffith.authorCronin, Neil


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record