https://github.com/sanskaryo/driver-drowsiness-detection-alert

Drowsiness detection system with alert message and voice
https://github.com/sanskaryo/driver-drowsiness-detection-alert

computer-vision dlib-face-detection haarcascade-frontalface numpy opencv pandas raspberry-pi

Last synced: 6 days ago
JSON representation

Drowsiness detection system with alert message and voice

• Host: GitHub
• URL: https://github.com/sanskaryo/driver-drowsiness-detection-alert
• Owner: sanskaryo
• License: mit
• Created: 2024-05-27T08:18:45.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-06-29T11:31:07.000Z (7 months ago)
• Last Synced: 2024-11-22T06:18:09.481Z (2 months ago)
• Topics: computer-vision, dlib-face-detection, haarcascade-frontalface, numpy, opencv, pandas, raspberry-pi
• Language: Python
• Homepage:
• Size: 71 MB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Drowsiness Detection System for yawning as well as sleepy eyes 😴 🚫 🚗

A real-time drowsiness detection system using computer vision, OpenCV, and other relevant libraries. This system detects when a person is drowsy and alerts them to prevent accidents.

## Features

- Real-time drowsiness detection

- Alerts the user with a sound when drowsiness is detected

- Utilizes facial landmarks to detect eye closure and yawning

## How It Works

1. **Facial Landmark Detection**: Uses dlib’s pre-trained shape predictor model to detect facial landmarks. The landmarks around the eyes are used to compute the Eye Aspect Ratio (EAR).

2. **Eye Aspect Ratio (EAR)**: The EAR is calculated based on the distances between the vertical eye landmarks and the horizontal eye landmarks. When the EAR falls below a certain threshold, it indicates that the eyes are closed.

3. **Yawning Detection**: Measures the distance between upper and lower lips to detect yawning, another indicator of drowsiness.

4. **Alert Mechanism**: When drowsiness or yawning is detected for a certain duration, the system triggers an alert sound to wake up the user.

## Working images

![Drowsiness Detection Alert](https://github.com/sanskaryo/Drowsiness_detection_using_dlib_and_cv/blob/main/images/WhatsApp%20Image%202024-06-29%20at%2016.21.34_cd625042.jpg)

![Drowsiness Detection Alert](https://github.com/sanskaryo/Drowsiness_detection_using_dlib_and_cv/blob/main/images/WhatsApp%20Image%202024-06-29%20at%2016.25.00_30454b32.jpg)

## Requirements

- Python 3.x

- OpenCV

- dlib

- imutils

- scipy

- numpy

## Installation

1. **Clone the repository**:

   ```sh

   git clone [email protected]:sanskaryo/Drowsiness_detection_using_dlib_and_cv.git

   cd drowsiness-detection-system

   python drowsiness_detection.py --webcam 0

### Download the Pre-trained Shape Predictor:

1. **Download the shape predictor and extract the .dat file.**

2. **Place the `shape_predictor_68_face_landmarks.dat` file in the project directory.**

This version includes structured sections, improved readability, and direct instructions for installation and usage. Adjust paths and details as necessary for your specific setup.