Using Computer Vision and Deep Learning Methods to Capture Skeleton Push Start Performance

Laurie Needham; Murray Evans; Darren Cosker; Steffi Colyer

Using Computer Vision and Deep Learning Methods to Capture Skeleton Push Start Performance

Laurie Needham, Murray Evans, Darren Cosker, Steffi Colyer

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

94 Downloads (Pure)

Abstract

This study aimed to employ computer vision and deep learning methods in order to capture
skeleton push start kinematics. Push start data were captured concurrently by a markerbased motion capture system and a custom markerless system. Very good levels of
agreement were found between systems, particularly for spatial based variables (step
length error 0.001 ± 0.012 m) while errors for temporal variables (ground contact time and
flight time) were within 1.5 frames of the criterion measures. The computer vision based
methods tested in this research provide a viable alternative to marker-based motion
capture systems. Furthermore they can be deployed into challenging, real world
environments to non-invasively capture data where traditional approaches would fail.

Original language	English
Title of host publication	ISBS Proceedings Archive
Publisher	International Society of Biomechanics in Sports (ISBS)
Volume	38
Edition	1
Publication status	Published - 2 Mar 2020
Event	38th International Conference on Biomechanics in Sport - LJMU, Liverpool, UK United Kingdom Duration: 21 Jul 2020 → 25 Jul 2020 https://www.isbs2020.org/home.html

Conference

Conference	38th International Conference on Biomechanics in Sport
Abbreviated title	ISBS 2020
Country/Territory	UK United Kingdom
City	Liverpool
Period	21/07/20 → 25/07/20
Internet address	https://www.isbs2020.org/home.html

Keywords

Winter sports, computer vision, deep learning, pose estimation.

Access to Document

USING COMPUTER VISION AND DEEP LEARNING METHODS TO CAPTURE SKELETFinal published version, 225 KBLicence: Unspecified

https://commons.nmu.edu/isbs/vol38/iss1/191/

1 Finished
1 Active

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA) - 2.0
Campbell, N. (PI), Cosker, D. (PI), Bilzon, J. (CoI), Campbell, N. (CoI), Cazzola, D. (CoI), Colyer, S. (CoI), Cosker, D. (CoI), Lutteroth, C. (CoI), McGuigan, P. (CoI), O'Neill, E. (CoI), Petrini, K. (CoI), Proulx, M. (CoI) & Yang, Y. (CoI)
Engineering and Physical Sciences Research Council
1/11/20 → 31/10/25
Project: Research council
Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)
Cosker, D. (PI), Bilzon, J. (CoI), Campbell, N. (CoI), Cazzola, D. (CoI), Colyer, S. (CoI), Fincham Haines, T. (CoI), Hall, P. (CoI), Kim, K. I. (CoI), Lutteroth, C. (CoI), McGuigan, P. (CoI), O'Neill, E. (CoI), Richardt, C. (CoI), Salo, A. (CoI), Seminati, E. (CoI), Tabor, A. (CoI) & Yang, Y. (CoI)
Engineering and Physical Sciences Research Council
1/09/15 → 28/02/21
Project: Research council

Cite this

Using Computer Vision and Deep Learning Methods to Capture Skeleton Push Start Performance. / Needham, Laurie; Evans, Murray ; Cosker, Darren et al.
ISBS Proceedings Archive. Vol. 38 1. ed. International Society of Biomechanics in Sports (ISBS), 2020. 191.

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Needham, L, Evans, M , Cosker, D & Colyer, S 2020, Using Computer Vision and Deep Learning Methods to Capture Skeleton Push Start Performance. in ISBS Proceedings Archive. 1 edn, vol. 38, 191, International Society of Biomechanics in Sports (ISBS), 38th International Conference on Biomechanics in Sport, Liverpool, UK United Kingdom, 21/07/20. <https://commons.nmu.edu/isbs/vol38/iss1/191/>

@inproceedings{347d8c25f5b44d269afdafd1a761e658,

title = "Using Computer Vision and Deep Learning Methods to Capture Skeleton Push Start Performance",

abstract = "This study aimed to employ computer vision and deep learning methods in order to captureskeleton push start kinematics. Push start data were captured concurrently by a markerbased motion capture system and a custom markerless system. Very good levels ofagreement were found between systems, particularly for spatial based variables (steplength error 0.001 ± 0.012 m) while errors for temporal variables (ground contact time andflight time) were within 1.5 frames of the criterion measures. The computer vision basedmethods tested in this research provide a viable alternative to marker-based motioncapture systems. Furthermore they can be deployed into challenging, real worldenvironments to non-invasively capture data where traditional approaches would fail. ",

keywords = "Winter sports, computer vision, deep learning, pose estimation.",

author = "Laurie Needham and Murray Evans and Darren Cosker and Steffi Colyer",

year = "2020",

month = mar,

day = "2",

language = "English",

volume = "38",

booktitle = "ISBS Proceedings Archive",

publisher = "International Society of Biomechanics in Sports (ISBS)",

edition = "1",

note = "38th International Conference on Biomechanics in Sport, ISBS 2020 ; Conference date: 21-07-2020 Through 25-07-2020",

url = "https://www.isbs2020.org/home.html",

}

TY - GEN

T1 - Using Computer Vision and Deep Learning Methods to Capture Skeleton Push Start Performance

AU - Needham, Laurie

AU - Evans, Murray

AU - Cosker, Darren

AU - Colyer, Steffi

PY - 2020/3/2

Y1 - 2020/3/2

N2 - This study aimed to employ computer vision and deep learning methods in order to captureskeleton push start kinematics. Push start data were captured concurrently by a markerbased motion capture system and a custom markerless system. Very good levels ofagreement were found between systems, particularly for spatial based variables (steplength error 0.001 ± 0.012 m) while errors for temporal variables (ground contact time andflight time) were within 1.5 frames of the criterion measures. The computer vision basedmethods tested in this research provide a viable alternative to marker-based motioncapture systems. Furthermore they can be deployed into challenging, real worldenvironments to non-invasively capture data where traditional approaches would fail.

AB - This study aimed to employ computer vision and deep learning methods in order to captureskeleton push start kinematics. Push start data were captured concurrently by a markerbased motion capture system and a custom markerless system. Very good levels ofagreement were found between systems, particularly for spatial based variables (steplength error 0.001 ± 0.012 m) while errors for temporal variables (ground contact time andflight time) were within 1.5 frames of the criterion measures. The computer vision basedmethods tested in this research provide a viable alternative to marker-based motioncapture systems. Furthermore they can be deployed into challenging, real worldenvironments to non-invasively capture data where traditional approaches would fail.

KW - Winter sports, computer vision, deep learning, pose estimation.

M3 - Chapter in a published conference proceeding

VL - 38

BT - ISBS Proceedings Archive

PB - International Society of Biomechanics in Sports (ISBS)

T2 - 38th International Conference on Biomechanics in Sport

Y2 - 21 July 2020 through 25 July 2020

ER -

Using Computer Vision and Deep Learning Methods to Capture Skeleton Push Start Performance

Abstract

Conference

Keywords

Access to Document

Fingerprint

Projects

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA) - 2.0

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)

Cite this