https://github.com/skalskip/sports

Cool experiments at the intersection of Computer Vision and Sports ⚽🏃
https://github.com/skalskip/sports

computer-vision deep-learning deep-neural-networks gpt-4 gpt-4-vision object-detection prompt-engineering pytorch sports-analytics tutorial yolov5 yolov7

Last synced: 2 days ago
JSON representation

Cool experiments at the intersection of Computer Vision and Sports ⚽🏃

• Host: GitHub
• URL: https://github.com/skalskip/sports
• Owner: SkalskiP
• Created: 2022-12-14T16:58:14.000Z (about 2 years ago)
• Default Branch: master
• Last Pushed: 2023-12-12T11:10:48.000Z (about 1 year ago)
• Last Synced: 2025-01-12T10:05:39.937Z (10 days ago)
• Topics: computer-vision, deep-learning, deep-neural-networks, gpt-4, gpt-4-vision, object-detection, prompt-engineering, pytorch, sports-analytics, tutorial, yolov5, yolov7
• Language: Jupyter Notebook
• Homepage:
• Size: 15.1 MB
• Stars: 487
• Watchers: 12
• Forks: 34
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml

Awesome Lists containing this project

README

        
# ⚽  Football Players Tracking with YOLOv5 + ByteTrack

[![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://www.youtube.com/watch?v=QCG8QMhga9k)

[![Roboflow](https://raw.githubusercontent.com/roboflow-ai/notebooks/main/assets/badges/roboflow-blogpost.svg)](https://blog.roboflow.com/track-football-players/)

[![GitHub](https://badges.aleen42.com/src/github.svg)](https://github.com/roboflow-ai/notebooks/blob/main/notebooks/how-to-track-football-players.ipynb)

I have long been fascinated by the use of Computer Vision in sports. After all, it is a combination of two things I love. Almost three years ago, I wrote a post on my personal blog in which I tried — at that time, still using YOLOv3 — to [detect and classify basketball players on the court](https://towardsdatascience.com/chess-rolls-or-basketball-lets-create-a-custom-object-detection-model-ef53028eac7d).

FIFA World Cup 2022 has motivated me to revisit this idea. This time I used a combination of [YOLOv5](https://github.com/ultralytics/yolov5) and [ByteTrack](https://github.com/ifzhang/ByteTrack) to track football players on the field. This blog post accompanies the Roboflow video where I talk through how to track players on a football field.

https://user-images.githubusercontent.com/26109316/207858600-ee862b22-0353-440b-ad85-caa0c4777904.mp4

# 🤸  3D Football Players Pose Estimation with YOLOv7

[![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://www.youtube.com/watch?v=AWjKfjDGiYE)

[![GitHub](https://badges.aleen42.com/src/github.svg)](https://github.com/SkalskiP/sport/tree/master/football-players-pose-estimation)

I was watching a FIFA 2022 World Cup match the other day, and one of the things that caught my eye was VAR - Video Assistant Referee, or to be more precise, the part of it responsible for analyzing whether a player was on the offside. I did a little [research](https://www.youtube.com/watch?v=WycjDx6giVE) and found that the system performs pose estimation on multiple cameras at once. I decided to check how difficult it would be to reproduce it at home using two cameras and [YOLOv7](https://github.com/WongKinYiu/yolov7).

https://user-images.githubusercontent.com/26109316/207677038-20f951a6-e469-4b3f-a934-66e036fcff69.mp4

# 👕 Assigning Football Players to Teams by Uniform Color with GPT-4V

[![GitHub](https://badges.aleen42.com/src/github.svg)](https://github.com/SkalskiP/sport/tree/master/football-analysis-with-gpt4-vision)

This project explores the use of [GPT-4V](https://openai.com/research/gpt-4v-system-card) in sports analytics, specifically in the context of football. Its primary aim was to evaluate whether GPT-4V could effectively distinguish and assign players to teams based on the color of their uniforms. This was achieved through the implementation of several advanced vision prompting techniques.

https://github.com/SkalskiP/sports/assets/26109316/b354b38d-1a12-477d-9283-45059ce12467