AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale

Keenon Werling; Janelle Kaneda; Alan Tan; Rishi Agarwal; Six Skov; Tom Van Wouwe; Scott Uhlrich; Nicholas Bianco; Carmichael Ong; Antoine Falisse; Shardul Sapkota; Aidan Chandra; Joshua Carter; Ezio Preatoni; Benjamin Fregly; Jennifer Hicks; Scott Delp; Karen C. Liu

doi:10.1007/978-3-031-73223-2

AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale

Keenon Werling, Janelle Kaneda, Alan Tan, Rishi Agarwal, Six Skov, Tom Van Wouwe, Scott Uhlrich, Nicholas Bianco, Carmichael Ong, Antoine Falisse, Shardul Sapkota, Aidan Chandra, Joshua Carter, Ezio Preatoni, Benjamin Fregly, Jennifer Hicks, Scott Delp, Karen C. Liu

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

Abstract

While reconstructing human poses in 3D from inexpen- sive sensors has advanced significantly in recent years, quantifying the dynamics of human motion, including the muscle-generated joint torques and external forces, remains a challenge. Prior attempts to estimate physics from reconstructed human poses have been hampered by a lack of datasets with high-quality pose and force data for a variety of movements. We present the AddBiomechanics Dataset 1.0, which includes physically accurate human dynamics of 273 human subjects, over 70h of motion and force plate data, totaling more than 24 mil- lion frames. To construct this dataset, novel analytical methods were required, which are also reported here. We propose a benchmark for esti- mating human dynamics from motion using this dataset, and present several baseline results. The AddBiomechanics Dataset is publicly avail- able at addbiomechanics.org/download/ data.html.

Original language	English
Title of host publication	Lecture Notes in Computer Science
Subtitle of host publication	Computer Vision – ECCV 2024. 18th European Conference Milan, Italy, September 29–October 4, 2024 Proceedings, Part LXXXVIII
Editors	Ales Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, Gül Varol
Place of Publication	Switzerland
Publisher	Springer Nature Switzerland AG
Pages	490-508
ISBN (Electronic)	9783031732232
ISBN (Print)	9783031732225
DOIs	https://doi.org/10.1007/978-3-031-73223-2
Publication status	Acceptance date - 3 Jul 2024
Event	The 18th European Conference on Computer Vision ECCV 2024 - Milan, Italy Duration: 1 Oct 2024 → 4 Oct 2024 Conference number: 18 https://eccv.ecva.net/

Publication series

Name	Lecture Notes in Computer Science
ISSN (Print)	0302-9743
ISSN (Electronic)	161103349

Conference

Conference	The 18th European Conference on Computer Vision ECCV 2024
Abbreviated title	ECCV 2024
Country/Territory	Italy
City	Milan
Period	1/10/24 → 4/10/24
Internet address	https://eccv.ecva.net/

Access to Document

10.1007/978-3-031-73223-2

https://arxiv.org/abs/2406.18537Licence: CC BY

Full Body Kinematics and Ground Reaction Forces of Fifty Heterogeneous Runners Completing Treadmill Running at Various Speeds and Gradients
Carter, J. (Creator), Chen, X. (Creator), Cazzola, D. (Creator), Trewartha, G. (Creator) & Preatoni, E. (Creator), University of Bath, 30 May 2024
DOI: 10.15125/BATH-01341
Dataset

Cite this

Werling, K., Kaneda, J., Tan, A., Agarwal, R., Skov, S., Van Wouwe, T., Uhlrich, S., Bianco, N., Ong, C., Falisse, A., Sapkota, S., Chandra, A., Carter, J., Preatoni, E., Fregly, B., Hicks, J., Delp, S., & Liu, K. C. (Accepted/In press). AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale. In A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.), Lecture Notes in Computer Science: Computer Vision – ECCV 2024. 18th European Conference Milan, Italy, September 29–October 4, 2024 Proceedings, Part LXXXVIII (pp. 490-508). (Lecture Notes in Computer Science). Springer Nature Switzerland AG. https://doi.org/10.1007/978-3-031-73223-2

AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale. / Werling, Keenon; Kaneda, Janelle; Tan, Alan et al.
Lecture Notes in Computer Science: Computer Vision – ECCV 2024. 18th European Conference Milan, Italy, September 29–October 4, 2024 Proceedings, Part LXXXVIII. ed. / Ales Leonardis; Elisa Ricci; Stefan Roth; Olga Russakovsky; Torsten Sattler; Gül Varol. Switzerland: Springer Nature Switzerland AG, 2024. p. 490-508 (Lecture Notes in Computer Science).

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

Werling, K, Kaneda, J, Tan, A, Agarwal, R, Skov, S, Van Wouwe, T, Uhlrich, S, Bianco, N, Ong, C, Falisse, A, Sapkota, S, Chandra, A, Carter, J , Preatoni, E, Fregly, B, Hicks, J, Delp, S & Liu, KC 2024, AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale. in A Leonardis, E Ricci, S Roth, O Russakovsky, T Sattler & G Varol (eds), Lecture Notes in Computer Science: Computer Vision – ECCV 2024. 18th European Conference Milan, Italy, September 29–October 4, 2024 Proceedings, Part LXXXVIII. Lecture Notes in Computer Science, Springer Nature Switzerland AG, Switzerland, pp. 490-508, The 18th European Conference on Computer Vision ECCV 2024, Milan, Italy, 1/10/24. https://doi.org/10.1007/978-3-031-73223-2

Werling K, Kaneda J, Tan A, Agarwal R, Skov S, Van Wouwe T et al. AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale. In Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G, editors, Lecture Notes in Computer Science: Computer Vision – ECCV 2024. 18th European Conference Milan, Italy, September 29–October 4, 2024 Proceedings, Part LXXXVIII. Switzerland: Springer Nature Switzerland AG. 2024. p. 490-508. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-73223-2

Werling, Keenon ; Kaneda, Janelle ; Tan, Alan et al. / AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale. Lecture Notes in Computer Science: Computer Vision – ECCV 2024. 18th European Conference Milan, Italy, September 29–October 4, 2024 Proceedings, Part LXXXVIII. editor / Ales Leonardis ; Elisa Ricci ; Stefan Roth ; Olga Russakovsky ; Torsten Sattler ; Gül Varol. Switzerland : Springer Nature Switzerland AG, 2024. pp. 490-508 (Lecture Notes in Computer Science).

@inproceedings{be0a961f9f1448cdbb0de9dea18572d1,

title = "AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale",

abstract = "While reconstructing human poses in 3D from inexpen- sive sensors has advanced significantly in recent years, quantifying the dynamics of human motion, including the muscle-generated joint torques and external forces, remains a challenge. Prior attempts to estimate physics from reconstructed human poses have been hampered by a lack of datasets with high-quality pose and force data for a variety of movements. We present the AddBiomechanics Dataset 1.0, which includes physically accurate human dynamics of 273 human subjects, over 70h of motion and force plate data, totaling more than 24 mil- lion frames. To construct this dataset, novel analytical methods were required, which are also reported here. We propose a benchmark for esti- mating human dynamics from motion using this dataset, and present several baseline results. The AddBiomechanics Dataset is publicly avail- able at addbiomechanics.org/download/ data.html.",

author = "Keenon Werling and Janelle Kaneda and Alan Tan and Rishi Agarwal and Six Skov and {Van Wouwe}, Tom and Scott Uhlrich and Nicholas Bianco and Carmichael Ong and Antoine Falisse and Shardul Sapkota and Aidan Chandra and Joshua Carter and Ezio Preatoni and Benjamin Fregly and Jennifer Hicks and Scott Delp and Liu, {Karen C.}",

year = "2024",

month = jul,

day = "3",

doi = "10.1007/978-3-031-73223-2",

language = "English",

isbn = "9783031732225",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature Switzerland AG",

pages = "490--508",

editor = "Leonardis, {Ales } and Elisa Ricci and Stefan Roth and Olga Russakovsky and Torsten Sattler and G{\"u}l Varol",

booktitle = "Lecture Notes in Computer Science",

address = "Switzerland",

note = "The 18th European Conference on Computer Vision ECCV 2024, ECCV 2024 ; Conference date: 01-10-2024 Through 04-10-2024",

url = "https://eccv.ecva.net/",

}

TY - GEN

T1 - AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale

AU - Werling, Keenon

AU - Kaneda, Janelle

AU - Tan, Alan

AU - Agarwal, Rishi

AU - Skov, Six

AU - Van Wouwe, Tom

AU - Uhlrich, Scott

AU - Bianco, Nicholas

AU - Ong, Carmichael

AU - Falisse, Antoine

AU - Sapkota, Shardul

AU - Chandra, Aidan

AU - Carter, Joshua

AU - Preatoni, Ezio

AU - Fregly, Benjamin

AU - Hicks, Jennifer

AU - Delp, Scott

AU - Liu, Karen C.

N1 - Conference code: 18

PY - 2024/7/3

Y1 - 2024/7/3

N2 - While reconstructing human poses in 3D from inexpen- sive sensors has advanced significantly in recent years, quantifying the dynamics of human motion, including the muscle-generated joint torques and external forces, remains a challenge. Prior attempts to estimate physics from reconstructed human poses have been hampered by a lack of datasets with high-quality pose and force data for a variety of movements. We present the AddBiomechanics Dataset 1.0, which includes physically accurate human dynamics of 273 human subjects, over 70h of motion and force plate data, totaling more than 24 mil- lion frames. To construct this dataset, novel analytical methods were required, which are also reported here. We propose a benchmark for esti- mating human dynamics from motion using this dataset, and present several baseline results. The AddBiomechanics Dataset is publicly avail- able at addbiomechanics.org/download/ data.html.

AB - While reconstructing human poses in 3D from inexpen- sive sensors has advanced significantly in recent years, quantifying the dynamics of human motion, including the muscle-generated joint torques and external forces, remains a challenge. Prior attempts to estimate physics from reconstructed human poses have been hampered by a lack of datasets with high-quality pose and force data for a variety of movements. We present the AddBiomechanics Dataset 1.0, which includes physically accurate human dynamics of 273 human subjects, over 70h of motion and force plate data, totaling more than 24 mil- lion frames. To construct this dataset, novel analytical methods were required, which are also reported here. We propose a benchmark for esti- mating human dynamics from motion using this dataset, and present several baseline results. The AddBiomechanics Dataset is publicly avail- able at addbiomechanics.org/download/ data.html.

U2 - 10.1007/978-3-031-73223-2

DO - 10.1007/978-3-031-73223-2

M3 - Chapter in a published conference proceeding

SN - 9783031732225

T3 - Lecture Notes in Computer Science

SP - 490

EP - 508

BT - Lecture Notes in Computer Science

A2 - Leonardis, Ales

A2 - Ricci, Elisa

A2 - Roth, Stefan

A2 - Russakovsky, Olga

A2 - Sattler, Torsten

A2 - Varol, Gül

PB - Springer Nature Switzerland AG

CY - Switzerland

T2 - The 18th European Conference on Computer Vision ECCV 2024

Y2 - 1 October 2024 through 4 October 2024

ER -

AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale

Abstract

Publication series

Conference

Access to Document

Fingerprint

Datasets

Full Body Kinematics and Ground Reaction Forces of Fifty Heterogeneous Runners Completing Treadmill Running at Various Speeds and Gradients

Cite this