Skip to content

Latest commit

 

History

History
104 lines (71 loc) · 3.01 KB

README.md

File metadata and controls

104 lines (71 loc) · 3.01 KB

ObjecTrackion

ObjecTrackion is a versatile object recognition and tracking project that can analyze any video feed displayed on the main screen, including movies, TV shows, games, or city cameras. The project leverages state-of-the-art object detection techniques to provide seamless and customizable object recognition capabilities. 🔍

Example Video 1

ObjeTrackion_part1.mp4

Example Video 2

ObjeTrackion_part2.mp4

Features 🌟

  • Universal Object Recognition: Perform object detection on any content displayed on the screen without restrictions. 📽
  • Logging & Notifications: Automatically log detected objects and send notification messages based on recognition results. ✉️
  • Customizable Settings: Adjust screen resolution, FPS, and other parameters for optimized performance. 🔄
  • Highlighted Object Detection: Detected objects are displayed with bounding boxes on the screen for clear visibility. 🖥️
  • Automated Logging: Recognized objects are logged and saved to a file automatically for future reference. 🗂️
  • Smart Notifications: Send notifications based on specific object detection criteria to keep you informed in real time. 🔔

Requirements 📦

Before running the project, make sure you have the following dependencies installed:

pip install -r requirements.txt

The requirements.txt includes:

  • TensorFlow
  • Keras
  • OpenCV
  • NumPy
  • Matplotlib

Setup 🛠️

  1. Clone the repository:
git clone https://github.com/furkankarakuz/ObjecTrackion.git
  1. Navigate to the project directory:
cd ObjecTrackion
  1. Install dependencies:
pip install -r requirements.txt

Desktop Interface (GUI) 🖥️

This project includes a Desktop GUI built with PyQt5 for an interactive and user-friendly experience. To install the required dependency, run the following command:

pip install PyQt5

With PyQt5 installed, you can enjoy an intuitive desktop interface for running and interacting with the object detection and tracking system

YOLO Configuration ⚙️

  • ObjecTrackion uses the YOLO (You Only Look Once) algorithm for object detection.
  • The objects recognized by the system are based on the COCO dataset.
  • To customize the object names, you can modify the coco.names file found in the project directory.

Supported Object Classes 🏷️

  • person
  • bicycle
  • car
  • motorcycle
  • airplane
  • bus
  • train
  • truck
  • boat
  • and more...

For a full list of object classes, refer to the COCO dataset class labels.

Usage 🚀

Start the application:

python main.py

Contributing 🤝

Contributions are welcome! Feel free to open an issue or submit a pull request to enhance ObjecTrackion.

License 📄

This project is licensed under the MIT License. See the LICENSE file for more details.

✨ ObjecTrackion: Making object detection accessible and adaptable for any screen! ✨