movement

a Python toolbox for analysing motion tracking data

Niko Sirmpilatze @ FOSDEM 2026

2026-01-31

whoami

Measuring behaviour as movement

Defining behaviour is tricky, but many have tried.

The total movements made by the intact animal (Tinbergen 1951).

We can quantify movements through various tools:

  • 🎥 Video cameras
  • 📱 Inertial measurement units (IMUs)
  • 🛰️ GPS-based biologgers

From videos to motion

By danceinthesky, openverse.org

CRISPR Ants Lose Ability to Smell” (2017)

Markerless pose estimation

Animal behaviour 🤝 computer vision

What happens after tracking?

  • Lack of standardised data formats and tools
  • Lots of fragile ‘in-house’ scripts
  • Piles of un-analysed data

movement: overview

movement: example applications

movement GUI

Community adoption

  • ~80k downloads (PyPI + conda-forge)
  • 34 code contributors | ~330 merged pull requests
  • External packages depending on movement:

The bigger picture

The even bigger picture

Long-term vision: movement as the scikit-image for animal motion data.

If you prefer the R ecosystem, check out the animovement toolbox by Mikkel Roald-Arbøl.

Acknowledgements

Join the movement!

📅 Aug 17-21 2026

Animals in Motion workshop at the Open Software Summer School.

References

CRISPR Ants Lose Ability to Smell.” 2017. Nature 548 (7667): 263–63. https://doi.org/10.1038/d41586-017-02337-4.
Mathis, Alexander, Pranav Mamidanna, Kevin M. Cury, Taiga Abe, Venkatesh N. Murthy, Mackenzie Weygandt Mathis, and Matthias Bethge. 2018. DeepLabCut: Markerless Pose Estimation of User-Defined Body Parts with Deep Learning.” Nature Neuroscience 21 (9): 1281–89. https://doi.org/10.1038/s41593-018-0209-y.
Pereira, Talmo D., Nathaniel Tabris, Arie Matsliah, David M. Turner, Junyu Li, Shruthi Ravindranath, Eleni S. Papadoyannis, et al. 2022. SLEAP: A Deep Learning System for Multi-Animal Pose Tracking.” Nature Methods 19 (4): 486–95. https://doi.org/10.1038/s41592-022-01426-1.
Tinbergen, Niko. 1951. The Study of Instinct. Clarendon Press.