Driver Drowsiness Detection System
- Version
- Download 2
- File Size 599.32 KB
- File Count 1
- Create Date 4 June 2025
- Last Updated 4 June 2025
Driver Drowsiness Detection System
Authors:
Prof. Pranjali Deshmukh
Department of Computer Engineering
Marathwada Mitra Mandal’s Institute of Technology
Pune, India
Mr. Aryan Siddhodhan Kamble
Department of Computer Engineering
Marathwada Mitra Mandal’s Institute of Technology
Pune, India aryankamble9000@gmail.com
Mr. Rushikesh Sanjay Patil
Department of Computer Engineering
Marathwada Mitra Mandal’s Institute of Technology
Pune, India
Ms. Sakshi Suresh More
Department of Computer Engineering
Marathwada Mitra Mandal’s Institute of Technology
Pune, India
Mr. Nishad Jadhav
Department of Computer Engineering
Marathwada Mitra Mandal’s Institute of Technology
Pune, India
nishadjadhav16@gmailcom
Abstract: This system is designed to enhance road safety by detecting and preventing accidents caused by driver drowsiness, a leading cause of traffic incidents. Using computer vision, the system monitors the driver's facial features, such as the eyes and mouth, to identify signs of fatigue like blinking patterns and yawning.
The detection uses Haar cascade classifiers to track these features, while a Convolutional Neural Network (CNN) identifies complex patterns, distinguishing between normal behavior and drowsiness. This deep learning technique helps adapt to various driving conditions, ensuring accurate monitoring.
The system calculates a driver alertness score based on eye closure percentage (PERCLOS) and other factors. If it detects a significant drop in alertness, an alert is triggered to warn the driver.
This system is particularly useful for long-distance drivers of trucks and buses, who are more prone to fatigue. By offering continuous monitoring, it helps reduce accidents and improve road safety.
Keywords—Eye Detection, Mouth Detection, Haar cascade, Convolutional Neural Network (CNN), Driver Alertness Monitoring, Drowsiness Detection, Fatigue Prevention, Road Safe
Download