Skip to content

Releases: AtomScott/SportsLabKit

Patch Release 0.3.1

Choose a tag to compare

@AtomScott AtomScott released this 13 Sep 13:12
efbcc90
  • Add TeamClassificationCallback and VectorModel to work with classifying teams from feature vectors.
  • Fix GitPython related bug which prevented importing SportsLabKit in Google Colab.

Introducing SportsLabKit 0.3.0

Choose a tag to compare

@AtomScott AtomScott released this 04 Sep 18:08

Whats New?

Meet SportsLabKit: The essential toolkit for advanced sports analytics. Designed for pros and amateurs alike, we convert raw game footage into actionable data.

Highlights

Core Capabilities

  • High-Performance Tracking: In-house implementations of SORT, DeepSORT, ByteTrack, and TeamTrack for object tracking in sports.

Flexibility

  • Plug-and-Play Architecture: Swap out detection and ReID models on the fly. Supported models include YOLOv8 and torch-ReID.

Usability

  • 2D Pitch Calibration: Translate bounding boxes to 2D pitch coordinates.

  • DataFrame Wrappers: BoundingBoxDataFrame and CoordinatesDataFrame for effortless manipulation and analysis of tracking data.

Tutorials

  • Get Started: Your first steps in understanding and setting up SportsLabKit.
  • User Guide: A comprehensive guide for effectively using the toolkit in real-world scenarios.
  • Core Components: Deep dive into the essential elements that make up SportsLabKit, including tracking algorithms and DataFrame wrappers.

Installation

To install SportsLabKit, simply run:

pip install SportsLabKit

Note: We're in active development, so expect updates and changes.

Example Usage

To get started with tracking your first game, follow this simple example:

import sportslabkit as slk

# Initialize your camera and models
cam = slk.Camera(path_to_mp4)
det_model = slk.detection_model.load('YOLOv8x')
motion_model = slk.motion_model.load('KalmanFilter')

# Configure and execute the tracker
tracker = slk.mot.SORTTracker(detection_model=det_model, motion_model=motion_model)
bbdf = tracker.track(cam)

# The tracking data is now ready for analysis

0.2.3

0.2.3 Pre-release
Pre-release

Choose a tag to compare

@AtomScott AtomScott released this 05 Feb 02:48
7cdb952
update to 0.2.3

0.2.2

0.2.2 Pre-release
Pre-release

Choose a tag to compare

@AtomScott AtomScott released this 03 Feb 15:21
c03fa1b

Update due to dependency API change

0.2.1 hotfix

0.2.1 hotfix Pre-release
Pre-release

Choose a tag to compare

@AtomScott AtomScott released this 26 Jan 05:59

Sorry, I forgot to update the poetry files.

SoccerTrack 0.2.0

SoccerTrack 0.2.0 Pre-release
Pre-release

Choose a tag to compare

@AtomScott AtomScott released this 26 Jan 05:16
update to version 0.2.0

SoccerTrack Pre-release v0.1.0

Pre-release

Choose a tag to compare

@AtomScott AtomScott released this 17 Jan 06:26
2ec4f34

This pre-release is a preview of new features and improvements included in the upcoming stable version 1.0.0 🎉

Changelog.
Coming soon. Should be installable with pip.

We've updated the documentation and API quite a bit but there is still a lot more to do until we can release stable version.
In the meanwhile, this version should be useful to preview the available features. We are still in rapid development and therefore there will be many changes to the core API.

Pre-release (nothing works)

Pre-release

Choose a tag to compare

@AtomScott AtomScott released this 08 Dec 05:47

Full Changelog: https://github.com/AtomScott/SoccerTrack/commits/v0.0.1-alpha

Nothing really works yet, but please contact us if you are interested in using SoccerTrack.

Will delete when a release is ready.