Realtime-TFOD is a system that performs real-time gesture detection and classification using computer vision and deep learning. This project focuses on recognizing specific hand gestures such as hello, thumbs-up, thumbs-down, and namaste, providing a robust platform for intuitive interaction between humans and machines.
- Gesture Detection: Detect and classify hand gestures in real-time.
- Real-Time Analysis: Process video streams to provide instant feedback.
- Deep Learning Models: Utilize advanced deep learning techniques for accurate gesture recognition.
- Customizable Labels: Expand or modify the gesture labels as needed for specific use cases.
- Versatile Applications: Suitable for interactive kiosks, sign language interpretation, robotics, and other human-computer interaction scenarios.
- Computer Vision
- Deep Learning
- TensorFlow
- OpenCV
- Python
- pyqt5
GestureDetectionDemo.mp4
- Clone the repository:
git clone https://github.com/Chauhan-Aman/Realtime--TFOD.git
cd realtime-tfod
- Set up a virtual environment:
python -m venv venv
source venv/bin/activate.ps1 # On Windows use `venv\Scripts\activate.ps1`
- Install required dependencies:
Install required dependencies:
- Create Your Gesture Dataset:
Run the Script Image Collection.ipynb
- Train the model and do realtime gesture detection
Run the Script Training and Detection.ipynb
This setup will allow you to run the Gesture Detection system locally.