1. Neuroscience
Download icon

DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning

  1. Jacob M Graving  Is a corresponding author
  2. Daniel Chae
  3. Hemal Naik
  4. Liang Li
  5. Benjamin Koger
  6. Blair R Costelloe
  7. Iain D Couzin
  1. Max Planck Institute of Animal Behavior, Germany
  2. Princeton University, United States
Tools and Resources
  • Cited 71
  • Views 16,245
  • Annotations
Cite this article as: eLife 2019;8:e47994 doi: 10.7554/eLife.47994

Abstract

Quantitative behavioral measurements are important for answering questions across scientific disciplines-from neuroscience to ecology. State-of-the-art deep-learning methods offer major advances in data quality and detail by allowing researchers to automatically estimate locations of an animal's body parts directly from images or videos. However, currently-available animal pose estimation methods have limitations in speed and robustness. Here we introduce a new easy-to-use software toolkit, DeepPoseKit, that addresses these problems using an efficient multi-scale deep-learning model, called Stacked DenseNet, and a fast GPU-based peak-detection algorithm for estimating keypoint locations with subpixel precision. These advances improve processing speed >2× with no loss in accuracy compared to currently-available methods. We demonstrate the versatility of our methods with multiple challenging animal pose estimation tasks in laboratory and field settings-including groups of interacting individuals. Our work reduces barriers to using advanced tools for measuring behavior and has broad applicability across the behavioral sciences.

Data availability

Data used and generated for experiments and model comparisons are included in the supporting files. Posture datasets can be found at: https://github.com/jgraving/deepposekit-dataThe code for DeepPoseKit is publicly available at the URL we provided in the paper: https://github.com/jgraving/deepposekit/The reviewers should follow the provided instructions for installation in the README file https://github.com/jgraving/deepposekit/blob/master/README.md#installation. Example Jupyter notebooks for how to use the code are provided here: https://github.com/jgraving/deepposekit/tree/master/examples

The following data sets were generated
The following previously published data sets were used

Article and author information

Author details

  1. Jacob M Graving

    Department of Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany
    For correspondence
    jgraving@gmail.com
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-5826-467X
  2. Daniel Chae

    Department of Computer Science, Princeton University, Princeton, United States
    Competing interests
    No competing interests declared.
  3. Hemal Naik

    Department for Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany
    Competing interests
    No competing interests declared.
  4. Liang Li

    Department for Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany
    Competing interests
    No competing interests declared.
  5. Benjamin Koger

    Department for Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany
    Competing interests
    No competing interests declared.
  6. Blair R Costelloe

    Department for Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany
    Competing interests
    No competing interests declared.
  7. Iain D Couzin

    Department of Collective Behaviour, Max Planck Institute of Animal Behavior, Konstanz, Germany
    Competing interests
    Iain D Couzin, Reviewing editor, eLife.

Funding

National Science Foundation (IOS-1355061)

  • Iain D Couzin

Horizon 2020 Framework Programme (Marie Sklodowska-Curie grant agreement No. 748549)

  • Blair R Costelloe

Nvidia (GPU Grant)

  • Blair R Costelloe

Office of Naval Research (N00014-09-1-1074)

  • Iain D Couzin

Office of Naval Research (N00014-14-1-0635)

  • Iain D Couzin

Army Research Office (W911NG-11-1-0385)

  • Iain D Couzin

Army Research Office (W911NF14-1-0431)

  • Iain D Couzin

Deutsche Forschungsgemeinschaft (DFG Centre of Excellence 2117)

  • Iain D Couzin

University of Konstanz (Zukunftskolleg Investment Grant)

  • Blair R Costelloe

The Strukture-und Innovations fonds fur die Forschung of the State of Baden-Wurttemberg

  • Iain D Couzin

Max Planck Society

  • Iain D Couzin

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Ethics

Animal experimentation: All procedures for collecting the zebra (E. grevyi) dataset were reviewed and approved by Ethikrat, the independent Ethics Council of the Max Planck Society. The zebra dataset was collected with the permission of Kenya's National Commission for Science, Technology and Innovation (NACOSTI/P/17/59088/15489 and NACOSTI/P/18/59088/21567) using drones operated by B.R.C. with the permission of the Kenya Civil Aviation Authority (authorization numbers: KCAA/OPS/2117/4 Vol. 2 (80), KCAA/OPS/2117/4 Vol. 2 (81), KCAA/OPS/2117/5 (86) and KCAA/OPS/2117/5 (87); RPAS Operator Certificate numbers: RPA/TP/0005 AND RPA/TP/000-0009).

Reviewing Editor

  1. Josh W Shaevitz, Princeton University, United States

Publication history

  1. Received: April 26, 2019
  2. Accepted: September 18, 2019
  3. Accepted Manuscript published: October 1, 2019 (version 1)
  4. Version of Record published: December 6, 2019 (version 2)

Copyright

© 2019, Graving et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 16,245
    Page views
  • 1,539
    Downloads
  • 71
    Citations

Article citation count generated by polling the highest count across the following sources: Crossref, PubMed Central, Scopus.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Download citations (links to download the citations from this article in formats compatible with various reference manager tools)

Open citations (links to open the citations from this article in various online reference manager services)

Further reading

    1. Neuroscience
    Jormay Lim et al.
    Research Article

    CNS neurons have no sensory function, protected by the skull. For this reason, brain neuromodulation by ultrasound were either done at a high intensity or through auditory nerves. We demonstrate in this study CNS neurons react to ultrasound stimulation at an intensity (5 mW/cm2) far lower than typical therapeutic ultrasound (>30 mW/cm2). Using micropipette ultrasound in calcium imaging, we show ASIC1a channels play a role in the reactions of CNS neurons to ultrasound, pointing to the molecular basis for direct ultrasound neuromodulation at low intensity. Furthermore, we also show evidence of neurogenesis with the same ultrasound stimulation, suggesting potential therapeutic translation.

    1. Neuroscience
    Eric L Denovellis et al.
    Research Article

    Representations related to past experiences play a critical role in memory and decision-making processes. The rat hippocampus expresses these types of representations during sharp-wave ripple (SWR) events, and previous work identified a minority of SWRs that contain ‘replay’ of spatial trajectories at ∼20x the movement speed of the animal. Efforts to understand replay typically make multiple assumptions about which events to examine and what sorts of representations constitute replay. We therefore lack a clear understanding of both the prevalence and the range of representational dynamics associated with replay. Here, we develop a state space model that uses a combination of movement dynamics of different speeds to capture the spatial content and time evolution of replay during SWRs. Using this model, we find that the large majority of replay events contain spatially coherent, interpretable content. Furthermore, many events progress at real-world, rather than accelerated, movement speeds, consistent with actual experiences.