Slide Link - Here
Medium Article - Here
Welcome to the Drowsy Driver Detection Project. This repository hosts a machine learning-based solution aimed at detecting driver drowsiness in real-time. Our approach utilizes advanced Convolutional Neural Network (CNN) models to analyze video data, thereby contributing to road safety by identifying early signs of driver fatigue.
The project incorporates various CNN models such as VGG16, VGG19, and InceptionResNetV2, each rigorously trained and tested to ensure accuracy and reliability. These models work in tandem to process real-time video feeds, making the system robust in different driving conditions and lighting environments.
- Real-time detection of driver drowsiness.
- Integration of multiple CNN models.
- Comprehensive testing on diverse datasets.
- Detailed visualizations of model performances.
To get started with the project, clone this repository to your local machine. Ensure that you have the necessary prerequisites installed, including Python, Jupyter Notebook, and relevant libraries like TensorFlow and OpenCV.
- Python 3.x
- Jupyter Notebook
- TensorFlow
- OpenCV
- Additional libraries as listed in
requirements.txt
- Clone the repository:
https://github.com/aakashdhruva/Drowsy-Driver-Detection/blob/main/Drowsy_Driver_Detection.ipynb
- Install the required packages:
pip install -r requirements.txt
Open the Jupyter notebooks in the repository to view the project's code and visualizations. Each notebook is well-documented to facilitate easy understanding and navigation.
Contributions to the project are welcome. If you wish to contribute, please fork the repository and submit a pull request with your proposed changes. Ensure that your code adheres to the existing coding standards and include tests where applicable.
This project is the result of collaborative efforts by Aakash Dhruva, Alex Kim, Anubhav Nehru, Daniel Lievano, Ian McIntosh.
This project is licensed under the MIT License - see the LICENSE file for details.