Transform human movement into generative art. Track body poses from video and create SVG visualizations of motion trajectories
Project description
choreopath
Transform human movement into generative art. A Python tool that uses MediaPipe to track body poses from video and creates SVG visualizations of motion trajectories - perfect for pen plotters, laser cutters, and digital art.
Features
- Track 33 body landmarks using MediaPipe Pose
- Process video files with OpenCV to extract tracking data
- Export tracking data to CSV with coordinates and visibility scores
- Generate SVG visualizations with hierarchical body part grouping, ready to be used in Inkscape
- Analyze tracking data quality with detailed reports
- Create animated visualizations of pose tracking
- Command-line interface
Installation
choreopath is pushed to Pypi at each new release. You can pip install choreopath to install it. Beware though, some versions of Python are incompatible with it as MediaPipe isn't currently available for Python >=3.13.
Instead, it is suggested to use uv and run choreopath like this:
uvx --python 3.12 choreopath
Usage
Track poses from video
choreopath track video.mp4 tracking_data.csv
Track with custom confidence thresholds
choreopath track video.mp4 tracking_data.csv --min-detection-confidence 0.7 --min-tracking-confidence 0.7
Generate SVG visualization
choreopath draw tracking_data.csv output.svg
Generate SVG with custom dimensions
choreopath draw tracking_data.csv output.svg --width 1920 --height 1080 --min-visibility 0.7
Generate an overlay video
choreopath overlay video.mp4 video-overlay.mp4
Analyze tracking data
choreopath analyze tracking_data.csv --animation output.mp4 --fps 30
Origin Story
This project was created when working on a generative art project. I used generated videos of dancers to create SVG that I could then plot using a pen plotter.
See example files:
original video overlay video animated tracking data examples/fall-recovery-4.svg
Development
- Use
uv - Run smoke test by using
make smoke-test
Changelog
See CHANGELOG.md.
License
This software is under a MIT license. See LICENSE.md.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file choreopath-1.1.0.tar.gz.
File metadata
- Download URL: choreopath-1.1.0.tar.gz
- Upload date:
- Size: 2.9 MB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6f4b5256170698ebf5b7b8ce82d15d1f10ac035c70abb36ef5068a0cf39eb33a
|
|
| MD5 |
0da1b1a65074b864ca9680d89fdb5e7f
|
|
| BLAKE2b-256 |
d743539919bfff6d7f0b8741a589ed67e6ab58a57a67474bc1fbeb6337b6a098
|
Provenance
The following attestation bundles were made for choreopath-1.1.0.tar.gz:
Publisher:
publish.yml on marcw/choreopath
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
choreopath-1.1.0.tar.gz -
Subject digest:
6f4b5256170698ebf5b7b8ce82d15d1f10ac035c70abb36ef5068a0cf39eb33a - Sigstore transparency entry: 604973512
- Sigstore integration time:
-
Permalink:
marcw/choreopath@ce28eeb20198aaad112c9ca96bd17e0e4495c943 -
Branch / Tag:
refs/tags/v1.1.0 - Owner: https://github.com/marcw
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@ce28eeb20198aaad112c9ca96bd17e0e4495c943 -
Trigger Event:
push
-
Statement type:
File details
Details for the file choreopath-1.1.0-py3-none-any.whl.
File metadata
- Download URL: choreopath-1.1.0-py3-none-any.whl
- Upload date:
- Size: 13.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
03d6cc2bd87619bef63ad7292ad81e58953c3d4d6e4980861b32cdf14b1ba79f
|
|
| MD5 |
490caf3b9d9d579fa956acfee7bbfabb
|
|
| BLAKE2b-256 |
7b741b032987789f0457449a1179ea696b59668b19623ba6182f0fd4d4e91b0f
|
Provenance
The following attestation bundles were made for choreopath-1.1.0-py3-none-any.whl:
Publisher:
publish.yml on marcw/choreopath
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
choreopath-1.1.0-py3-none-any.whl -
Subject digest:
03d6cc2bd87619bef63ad7292ad81e58953c3d4d6e4980861b32cdf14b1ba79f - Sigstore transparency entry: 604973514
- Sigstore integration time:
-
Permalink:
marcw/choreopath@ce28eeb20198aaad112c9ca96bd17e0e4495c943 -
Branch / Tag:
refs/tags/v1.1.0 - Owner: https://github.com/marcw
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@ce28eeb20198aaad112c9ca96bd17e0e4495c943 -
Trigger Event:
push
-
Statement type: