NL|EN

Database

Strategic

The database that didn't exist yet

Babon is building a large, labelled clinical motion database. Without that data, the question of which measurement adds something for which patient stays unanswered. The figures below come live from the research database.

LiveRecordings in database43.019Aggregated from public, CC-BY licensed datasets. Base layer for normative comparison and validation.
Unique subjects322Counted where the source records a subject id; AddBiomechanics does not. From practices and clinics: not yet.
Data sources2Two public datasets, both CC-BY licensed and fully attributed.
Infrastructurefr-parScaleway Paris. Data does not leave the EU.

Updated: 28 August 2026 · source: research.movalytics-db

Composition of the 43,019 recordings

// breakdown per bron
AddBiomechanics96%41.281
GAVD4%1.738
Why this database

Context

A large, representative clinical motion database from everyday practice does not currently exist. The only conventional source is a gait lab, where a single measurement costs tens of euros. As a result, analyses like age-norms, recovery patterns after knee surgery, and diagnosis-specific reference data are simply not feasible in practice.

That is exactly the question we work on: not how many movement variables we can measure, but which of them actually add something for which patient. It is not a question software answers, it is answered with data from practice. So we build this database together with programmes and researchers, and we name the origin of every source.

Source data

With thanks to

Every recording in the research database comes from publicly available, CC-BY licensed datasets. Full attribution below.

[01] Normative reference · healthy population

AddBiomechanics

Werling, K., Bianco, N.A., Raitor, M., Stingel, J., Hicks, J.L., Delp, S.L., Liu, C.K. (2023).AddBiomechanics: Automating model scaling, inverse kinematics, and inverse dynamics from human motion data through sequential optimization.PLoS ONE 18(11): e0295152.

Aggregated marker-based motion capture across 15 contributing studies. Base layer for normative comparison.

+Contributing studies15
  1. Lencioni et al. 201950 subjects
  2. Carter et al. 202350 subjects
  3. Santos et al. 201749 subjects
  4. Camargo et al. 202122 subjects
  5. Tan et al. 202317 subjects
  6. Moore et al. 201512 subjects
  7. Falisse et al. 201611 subjects
  8. Van der Zee et al. 202210 subjects
  9. Hamner et al. 201310 subjects
  10. Uhlrich et al. 202310 subjects
  11. Tan et al. 20229 subjects
  12. Wang et al. 20239 subjects
  13. Han et al. 20237 subjects
  14. Fregly et al. 20126 subjects
  15. Li et al. 20211 subjects
273subjects
41.281lab-mocap trials
CC BY 4.0addbiomechanics.org →
[02] Clinical and atypical gait

GAVD, Gait Abnormality Video Dataset

Ranjan, R., Ahmedt-Aristizabal, D., Ali Armin, M., Kim, J. (2025).Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video Dataset.IEEE Access 13: 45321, 45339. doi:10.1109/ACCESS.2025.3545787

Video-based gait recordings with clinical labels. Supports evaluation of pose extraction on in-the-wild video, beyond lab conditions.

276subjects
1.738videos
CC BY 4.0IEEE Access →
Research partnershipIn conversation with Hogeschool Utrecht, Jaap Jansen, Institute of Movement Studies. The setup is being explored jointly; no data has been contributed yet.

Own database or research question?

Get in touch