Kitman is a Python package providing utilities for player classification in soccer-related projects. It streamlines data handling, field visualization, and player segmentation.
- Dataset Support: Facilitates handling of SoccerNetV2 and SoccerNetV3 datasets.
- Data Management: Specialized structures for sequential managing of hierarchical directory structures of frames and metadata.
- Field Calibration: Functions for loading homography data and visualizing it on a soccer field.
- Player Segmentation: Tools for loading and visualizing player segmentations directly onto frames.
It is recommended to use a Mamba or Conda environment to manage dependencies and ensure a clean workspace.
- Python 3.9+
- pip
You do not need to clone this repository to use it; simply install directly via pip:
pip install git+https://github.com/gorayni/kitman.gitThe authors acknowledge support by MICINN/FEDER UE project, ref. PID2021-127643NB-I00, and the support of the European Commission, Horizon Europe Programme, EMERALD Project 101119800.
