Skip to main content

Table of Contents

  1. Introduction Purpose of the package.
  2. Installation If you wish to use the package.
  3. Development If you wish to change the source code and enhance the package.

Introduction


The package provides various scripts to process a golf swing video and export the information to another package "GolfCoach" for analysis. The output feedback can then be used to improve the swing.

The package uses Google media pipe for detecting the golfer. It then detects the club head in the video and the golf poses to detect the start and finish of the golf swing. This information in written out to a json file that can be analyzed by a separate packge "GolfCoach" for analysis.

This is shown below Flowchart

Some sample vides for down the line, right hand golfer is available on GoogleDrive

Each video example has 3 files.

  • Video file

  • Pickle database that is the result of running the scripts below.

  • Json file for exporting to GolfCoach packge

The general sequence of steps for a video say "0001.mov"

Create Swing Database

This step runs google media pipe and stores all the landmarks. It will also try to detect the golf poses and club head position. Current version usually fails on this and requires hand labellling.

create_swing_db 00001.mov

Hand Label GolfPoses

Run the script below to label the golf poses. The golf pose consist of

  • Start Pose:
  • Top Pose: Indicates that the backswing is now complete.
  • Finish Pose: Indicates that the swing is complete.
label_golf_poses 00001.pkl

Hand Label Club Head Position

Label the club head in some of the frames. The script will then use a linear approx to fill the position in the remaining frames.

label_club_head 00001.pkl

Export To Json

Export the information to a json file for analysis by the GolfCoach package.

dump_swing_db 00001.pkl

Status

WIP: Detailed src documentation of this package is on ReadTheDocs

Status

The current steps are listed here GolfSwingCapture Initial thoughts on swing analysis are here GolfSwingAnalysis

Metadata

Release files for golftracker 2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for golftracker 2.0
File Interpreter ABI Platform Actions
golftracker-2.0-py3-none-any.whl Python 3 none any Details for golftracker-2.0-py3-none-any.whl

Release files / golftracker-2.0-py3-none-any.whl

Download URL golftracker-2.0-py3-none-any.whl
Size 25.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7067db7fb6862eb09d62e9487fd862011ec740aa84c69ae3e2b2ed9fb15ad20a
BLAKE2b-256 checksum
How to use checksums
67a5993788772739ed3b78c058b70920f2bd2696f7d16e915062e110df9eb88a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.0 CPython/3.9.7

Security for golftracker 2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page