Skip to content

Commit

Permalink
edited movement text
Browse files Browse the repository at this point in the history
  • Loading branch information
niksirbi committed Oct 24, 2023
1 parent 9f5e8b6 commit 90bc186
Showing 1 changed file with 4 additions and 4 deletions.
8 changes: 4 additions & 4 deletions docs/source/projects/behaviour.md
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
# Behaviour

## movement
[movement](https://movement.neuroinformatics.dev/) aims to **facilitate the study of animal behaviour in neuroscience** by providing a suite of **Python tools to process body movement data** across space and time.
[movement](https://movement.neuroinformatics.dev/) aims to **facilitate the study of animal behaviour in neuroscience** by providing a suite of **Python tools to analyse body movements** across space and time.

At its core, movement processes trajectories of *keypoints*, which are specific body parts of an *individual*. An individual's posture or *pose* in a given frame is represented by a set of keypoint coordinates, which are given in 2D (x,y) or 3D (x,y,z). The sequential collection of poses over time is referred to as *pose tracks*. In the field of neuroscience, pose tracks are typically extracted from video data using tools like [DeepLabCut](http://www.mackenziemathislab.org/deeplabcut) or [SLEAP](https://sleap.ai/).
At its core, movement handles trajectories of *keypoints*, which are specific body parts of an *individual*. An individual's posture or *pose* is represented by a set of keypoint coordinates, given in 2D (x,y) or 3D (x,y,z). The sequential collection of poses over time forms *pose tracks*. In neuroscience, these tracks are typically extracted from video data using software like [DeepLabCut](http://www.mackenziemathislab.org/deeplabcut) or [SLEAP](https://sleap.ai/).

movement's goal is to offer a **unified interface for pose tracks** and to **process them via modular and accessible tools**. We aim to support data produced by a variety of pose estimation tools, in **2D or 3D space**, tracking a **single or multiple individuals**. The focus will be on providing functionalities for data cleaning, visualisation and motion quantification.
With movement, our vision is to present a consistent interface for pose tracks and to analyse them using modular and accessible tools. We aim to accommodate data from a range of pose estimation packages, in 2D or 3D, tracking a single or multiple individuals. The focus will be on providing functionalities for data cleaning, visualisation and motion quantification.

Movement is not designed for behaviour classification or action segmentation, but it may extract features useful for these tasks. We are planning to develop separate tools for these purposes, which will be compatible with movement.
While movement isn't designed for behaviour classification or action segmentation, it may extract features useful for these tasks. We are planning to develop separate packages for this purpose, which will be compatible with movement and the existing ecosystem of related tools.

0 comments on commit 90bc186

Please sign in to comment.