https://github.com/abhroroy365/tennis-tracker

This project utilizes OpenCV, YOLO and CNN to track the position, movement of players in a video. YOLOv8 is used to track the players. YOLOv5 is used to track the position of tennis ball at every frame of the video. ResNet34 is fine-tuned to detect the court keypoints.
https://github.com/abhroroy365/tennis-tracker

computer-vision deep-learning opencv pytorch tennis-game yolov5

Last synced: about 1 year ago
JSON representation

This project utilizes OpenCV, YOLO and CNN to track the position, movement of players in a video. YOLOv8 is used to track the players. YOLOv5 is used to track the position of tennis ball at every frame of the video. ResNet34 is fine-tuned to detect the court keypoints.

• Host: GitHub
• URL: https://github.com/abhroroy365/tennis-tracker
• Owner: abhroroy365
• Created: 2024-04-14T07:39:12.000Z (about 2 years ago)
• Default Branch: master
• Last Pushed: 2024-04-14T08:06:34.000Z (about 2 years ago)
• Last Synced: 2025-04-14T01:51:40.176Z (about 1 year ago)
• Topics: computer-vision, deep-learning, opencv, pytorch, tennis-game, yolov5
• Language: Jupyter Notebook
• Homepage:
• Size: 36.7 MB
• Stars: 10
• Watchers: 1
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          

# Tennis Match Tracker

This project utilizes OpenCV, YOLO and CNN to track the position, movement of players in a video. YOLOv8 is used to track the players. YOLOv5 is used to track the position of tennis ball at every frame of the video. ResNet34 is fine-tuned to detect the court keypoints. 

# Weights

Download the pretrained weights

https://drive.google.com/file/d/11oPP9h-lVfuOv09RFt0mmvydy4-maTjV/view?usp=sharing, 

https://drive.google.com/file/d/1iGQMabajjVm_MbUlCXJDnslnLmYvgleX/view?usp=sharing, 

https://drive.google.com/file/d/1ihueDeTl2XiYDiVMYBKpGygnBMG91pIW/view?usp=sharing

## Screenshots

![Demo output](https://github.com/abhroroy365/Tennis-Tracker/blob/master/output/output_video.gif)

## Run Locally

Clone the project

```bash

  git clone https://github.com/abhroroy365/Tennis-Tracker.git

```

Go to the project directory

```bash

  cd Tennis-Tracker

```

Create virtual environment

```bash

  python -m venv env

```

Activate the virtual environment

```bash

  env\Scripts\activate

```

Install dependencies

```bash

  pip install -r requirements.txt

```

For training (no need, weights alrady provided)

```bash

  python .\training\train.py

```

For running the tracker on your video

```bash

  python run-tracker.py

```

## 🛠 Skills

Pytorch, OpenCV, YOLO, Python, Computer Vision