Using deep neural networks for kinematic analysis : challenges and opportunities
Cronin, N. J. (2021). Using deep neural networks for kinematic analysis : challenges and opportunities. Journal of Biomechanics, 123, Article 110460. https://doi.org/10.1016/j.jbiomech.2021.110460
Published in
Journal of BiomechanicsAuthors
Date
2021Copyright
© 2021 The Author(s). Published by Elsevier Ltd.
Kinematic analysis is often performed in a lab using optical cameras combined with reflective markers. With the advent of artificial intelligence techniques such as deep neural networks, it is now possible to perform such analyses without markers, making outdoor applications feasible. In this paper I summarise 2D markerless approaches for estimating joint angles, highlighting their strengths and limitations. In computer science, so-called “pose estimation” algorithms have existed for many years. These methods involve training a neural network to detect features (e.g. anatomical landmarks) using a process called supervised learning, which requires “training” images to be manually annotated. Manual labelling has several limitations, including labeller subjectivity, the requirement for anatomical knowledge, and issues related to training data quality and quantity. Neural networks typically require thousands of training examples before they can make accurate predictions, so training datasets are usually labelled by multiple people, each of whom has their own biases, which ultimately affects neural network performance. A recent approach, called transfer learning, involves modifying a model trained to perform a certain task so that it retains some learned features and is then re-trained to perform a new task. This can drastically reduce the required number of training images. Although development is ongoing, existing markerless systems may already be accurate enough for some applications, e.g. coaching or rehabilitation. Accuracy may be further improved by leveraging novel approaches and incorporating realistic physiological constraints, ultimately resulting in low-cost markerless systems that could be deployed both in and outside of the lab.
...
Publisher
Elsevier BVISSN Search the Publication Forum
0021-9290Keywords
Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/68771597
Metadata
Show full item recordCollections
- Liikuntatieteiden tiedekunta [3120]
Related funder(s)
Research Council of FinlandFunding program(s)
Academy Project, AoFAdditional information about funding
Academy of Finland for funding (decision number: 323473).License
Related items
Showing items with similar title or keywords.
-
Feasibility of OpenPose markerless motion analysis in a real athletics competition
Cronin, Neil J.; Walker, Josh; Tucker, Catherine B.; Nicholson, Gareth; Cooke, Mark; Merlino, Stéphane; Bissas, Athanassios (Frontiers Media, 2024)This study tested the performance of OpenPose on footage collected by two cameras at 200 Hz from a real-life competitive setting by comparing it with manually analyzed data in SIMI motion. The same take-off recording from ... -
Evaluation of 3D Markerless Motion Capture System Accuracy during Skate Skiing on a Treadmill
Torvinen, Petra; Ruotsalainen, Keijo S.; Zhao, Shuang; Cronin, Neil; Ohtonen, Olli; Linnamo, Vesa (MDPI AG, 2024)In this study, we developed a deep learning-based 3D markerless motion capture system for skate skiing on a treadmill and evaluated its accuracy against marker-based motion capture during G1 and G3 skating techniques. ... -
Between- and within-day repeatability of markerless 2D motion analysis using deep neural networks
Romppanen, Vesa (2021)The purpose of this study was to evaluate kinematic analysis repeatability by deep learning approach in countermovement jump. Seventy athletes (39 women, 31 men) performed two maximal countermovement jumps in either one ... -
Estimating the mechanical cost of transport in human walking with a simple kinematic data-driven mechanical model
Katwal, Parvat; Jaiswal, Suraj; Jiang, Dezhi; Pyrhönen, Lauri; Tuomisto, Jenni; Rantalainen, Timo; Schwab, Arend L.; Mikkola, Aki (Public Library of Science, 2024)This work utilizes a simplified, streamlined approach to study the mechanical cost of transport in human walking. Utilizing the kinematic motion data of the center of mass, velocities and accelerations are determined using ... -
Deep learning in gait analysis : the effect of marker presence in neural network training to kinematic outcomes
Uitto, Roope (2021)Ihmisen tuottaman liikkeen määrittämiseen käytetään yleensä optoelektronisia liikkeenkaappausjärjestelmiä, jotka perustuvat kohteen iholle kiinnitettävien valoa heijastavien markkerien seurantaan. Nämä laboratorio-olosuhteissa ...