Using deep neural networks for kinematic analysis: Challenges and opportunities

Cronin, Neil ORCID: 0000-0002-5332-1188 (2021) Using deep neural networks for kinematic analysis: Challenges and opportunities. Journal of Biomechanics, 123. p. 110460. doi:10.1016/j.jbiomech.2021.110460

[img]
Preview
Text (Published version)
10022-Cronin-(2021)-Using-deep-neural-networks-for-kinematic-analysis.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview

Abstract

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.

Item Type: Article
Article Type: Article
Uncontrolled Keywords: Motion analysis; Kinematics; Deep neural network; Markerless tracking; AI
Subjects: G Geography. Anthropology. Recreation > GV Recreation Leisure > GV557 Sports
Q Science > QA Mathematics > QA76 Computer software
Q Science > QM Human anatomy
T Technology > T Technology (General)
Divisions: Schools and Research Institutes > School of Sport and Exercise > Applied Sport & Exercise Sciences
Research Priority Areas: Health, Life Sciences, Sport and Wellbeing
Depositing User: Rhiannon Goodland
Date Deposited: 02 Aug 2021 14:19
Last Modified: 02 Aug 2021 14:30
URI: http://eprints.glos.ac.uk/id/eprint/10022

University Staff: Request a correction | Repository Editors: Update this record

University Of Gloucestershire

Bookmark and Share

Find Us On Social Media:

Social Media Icons Facebook Twitter Google+ YouTube Pinterest Linkedin

Other University Web Sites

University of Gloucestershire, The Park, Cheltenham, Gloucestershire, GL50 2RH. Telephone +44 (0)844 8010001.