choreopath 1.0.0

Transform human movement into generative art. Track body poses from video and create SVG visualizations of motion trajectories

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

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

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 animated tracking data

License

This software is under a MIT license. Please see LICENSE.md