Skip to main content

Classes and methods for performing 3D pose tracking from 2D poses

Project description

# wf-pose-tracking-3d

Classes and methods for performing 3D pose tracking from 2D poses:

  • Functions which load 2D pose data from Wildflower S3 directories

  • Functions which perform very basic 3D pose reconstruction from multi-camera 2D pose data

  • Functions which support basic visualization of 2D and 3D pose data

## Testing

To run tests, change working directory to /tests and run one of the following.

python pulls a single frame of 2D pose data from S3 and performs a simple 3D pose reconstruction

python pulls multiple frames of 2D pose data from a local file and builds a set of 3D pose tracks

These scripts pull camera calibration parameter files and sample 2D pose data from tests/data

To run these scripts (and to use any of the functions data from S3), you need to set the AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY environment variables to keys belonging to an account that is a member of the Wildflower cameras group.

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

wf-pose-tracking-3d-0.1.0.tar.gz (17.3 kB view hashes)

Uploaded source

Built Distribution

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page