REPOSITORY OVERVIEWLive repository statistics
★ 3Stars
⑂ 0Forks
◯ 0Open issues
◉ 3Watchers
50/100
OPENREPOHUB HEALTH SIGNALMixed signals
A transparent discovery signal based on current public GitHub metadata.
Recent activity35% weight
52 Community adoption25% weight
7 Maintenance state20% weight
100 License clarity10% weight
0 Project information10% weight
100 This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
README preview
Machine-Learning-Based-Driver-Drowsiness-Detection-System
Instructions for Machine-Learning-Based Driver Drowsiness Detection System Using Raspberry Pi and OV5467 Camera
This system is designed to detect driver drowsiness using computer vision and machine learning techniques. The key components include a Raspberry Pi as the processing unit and an OV5467 camera module for real-time frame capture. The analysis is performed using the Dlib library for facial landmark detection and NumPy for mathematical operations, especially for calculating the Euclidean distance between eye landmarks to determine eye aspect ratio (EAR), a metric commonly used to assess drowsiness levels.
1. System Requirements
- Raspberry Pi (preferably 4B with 4GB RAM for performance)
- OV5467 camera module (connected via CSI interface)
- MicroSD card with Raspbian OS installed
- Python 3.x installed
- Required libraries:
dlib, numpy, opencv-python, imutils
2. System Setup
-
Camera Setup: Connect the OV5467 camera to the Raspberry Pi’s CSI port. Enable the camera from the Raspberry Pi configuration settings using sudo raspi-config.
-
Install Dependencies:
sudo apt-get update
sudo apt-get install python3-pip cmake libopenblas-dev liblapack-dev libx11-dev
pip3 install dlib numpy opencv-python imutils
-
Dlib Facial Landmark Model: Download the pre-trained shape predictor model:
shape_predictor_68_face_landmarks.dat from Dlib model
3. Working Principle
The system uses a live video stream from the OV5467 camera. Each frame is processed using Dlib’s face detector and facial landmark predictor. Specifically, landmarks around the eyes (usually points 36 to 41 for the left eye and 42 to 47 for the right eye) are extracted.
The Eye Aspect Ratio (EAR) is computed using the Euclidean distances between these landmarks:
$$
EAR = \frac{||p_2 - p_6|| + ||p_3 - p_5||}{2 \times ||p_1 - p_4||}
$$
ALGORITHMICALLY RELATEDSimilar Open-Source Projects
Selected from shared topics, language and repository description—not editorial ratings.
This project implements a real-time driver drowsiness detection system using a Raspberry Pi equipped with an OV camera module. The system employs computer vision (OpenCV) and machine learning techniques (NumPy, pre-trained models) to monitor the driver's facial landmarks—particularly eye and head movement.
51/100 healthActive repositoryHas homepage
PythonApache-2.0#3dprinting#blender3d#computer-vision#machine-learning-algorithms
⑂ 0 forks◯ 0 issuesUpdated Jul 26, 2025
Project homepage ↗