Skip to main content

Top-level package for skellytracker

Project description

skellytracker

The tracking backend for freemocap. Collects different pose estimation tools and aggregates them using a consistent API. Can run pose estimation on images, webcams, and videos.

Run skelly_tracker

Installation: pip install skellytracker Then it can be run with skellytracker.

Running the basic skellytracker will open the first webcam port on your computer and run pose estimaiton in realtime with mediapipe holistic as a tracker. You can specify the tracker with skellytracker TRACKER_NAME, where TRACKER_NAME is the name of an available tracker. To view the names of all available trackers, see RUN_ME.py.

It will take some time to initialize the tracker the first time you run it, as it will likely need to download the model.

Using skellytracker in your project

To use skellytracker in your project, import a tracker like from skellytracker import YOLOPoseTracker, then instantiate it with your desired parameters like tracker = YOLOPoseTracker(model_size="medium"), and then use tracker.process_image(frame) or tracker.process_video(video_filepath). Processing image by image will let you access each individual annotated frame with tracker.annotated_image, and you can optionally record the data with tracker.recorder.record(). Access recorded data with tracker.recorder.process_tracked_objects(). The running, recording, and processing are done separately to give control over the amount of processing done at each step in the pipeline. Processing an entire video allows you to save the annotated frames as a video, and optionally saves and returns the data as a numpy array. Each tracker has an associated ModelInfo class to access model attributes.

Skellytracker is still under development, so version updates may make breaking changes to the API. Please report any issues and pull requests to the skellytracker repo.

Extending the API

To extend the API, import the BaseTracker and BaseRecorder abstract base classes from skellytracker. Then create a new tracker and recorder inheriting from the base classes and implement all of the abstract methods.

Contributing

We love your input! We want to make contributing to this project as easy and transparent as possible, whether it's:

  • Reporting a bug
  • Discussing the current state of the code
  • Submitting a fix
  • Proposing new features
  • Becoming a maintainer

Pull requests are the best way to propose changes to the codebase (we use Github Flow). We actively welcome your pull requests:

  1. Fork the repo and create your branch from main.
  2. Download the development dependencies with pip install -e '.[dev]'.
  3. If you've added code that should be tested (including any tracker), add tests.
  4. If you've changed APIs, update the documentation.
  5. Ensure the test suite passes by running pytest skellytracker/tests.
  6. Make sure your code lints.
  7. Make that pull request!

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

skellytracker-2024.9.1019.tar.gz (51.0 kB view details)

Uploaded Source

Built Distribution

skellytracker-2024.9.1019-py3-none-any.whl (66.8 kB view details)

Uploaded Python 3

File details

Details for the file skellytracker-2024.9.1019.tar.gz.

File metadata

  • Download URL: skellytracker-2024.9.1019.tar.gz
  • Upload date:
  • Size: 51.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.19

File hashes

Hashes for skellytracker-2024.9.1019.tar.gz
Algorithm Hash digest
SHA256 857b38dc541eefa88cfbcf85e9dacdf00bafe55885c93d6819dee015dbc3ac3c
MD5 f553c09b2199404c99295446b7a9a0d4
BLAKE2b-256 465c126fa23981ba7b9677158273ec1fcf80f24c37c336e89d09ed31e05abf34

See more details on using hashes here.

File details

Details for the file skellytracker-2024.9.1019-py3-none-any.whl.

File metadata

File hashes

Hashes for skellytracker-2024.9.1019-py3-none-any.whl
Algorithm Hash digest
SHA256 9adc9829533eb8fda07a3270518d78e9f6d1cff058ae6463a6e031f6711eb27e
MD5 04e835d912c988a7d86ded79c9a79872
BLAKE2b-256 d650f40475a3b41b0ee40482f2e961bdbd171b2f30bdab2afe5dfd2ac5753746

See more details on using hashes here.

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