Accident Prevention System for Drivers Safety

Garje, Avantika · 2025 · Crossref

DOI: 10.22214/ijraset.2025.69552

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper addresses the critical safety issue of driver drowsiness, a leading cause of road accidents, particularly during long-distance travel and night driving. The authors propose a real-time Driver Drowsiness Detection System designed to identify early signs of fatigue and issue timely alerts to prevent crashes. The motivation stems from the gradual and often unrecognized nature of driver fatigue, which poses significant risks to drivers and other road users. The system aims to enhance road safety by providing proactive intervention through the monitoring of physiological and behavioral indicators. The proposed system utilizes a Raspberry Pi (3B+ or 4) as the central processing unit, integrated with a camera module for real-time video capture. The technical implementation relies on computer vision techniques, specifically using Python libraries such as OpenCV and Dlib for facial landmark detection. The core detection algorithm calculates the Eye Aspect Ratio (EAR) to monitor eye closure duration and analyzes facial movements, including yawning frequency and head position. The system distinguishes between alert and drowsy states by comparing these metrics against predefined thresholds. When drowsiness is detected—defined as eyes remaining closed for a specific number of frames—the system triggers an alert mechanism, which includes audio warnings via a buzzer and visual signals via an LED. The authors also note the potential for integration with vehicle systems to slow down the car or vibrate the seat. The system was initially implemented and tested on a laptop equipped with a webcam operating at 15 frames per second. The results demonstrate the system’s ability to detect facial landmarks and calculate EAR values in real-time. Visual outputs confirmed the detection of open eyes versus drowsy states, with corresponding audio alerts generated when the subject exhibited signs of sleepiness, such as yawning or prolonged eye closure. The system successfully displayed status updates and triggered alarms based on the computed metrics. The authors conclude that this technology offers a promising solution for reducing fatigue-related accidents by providing non-intrusive, real-time monitoring. While challenges regarding cost, privacy, and integration with existing vehicle infrastructure remain, the potential benefits in saving lives and reducing accident-related costs are significant. The paper suggests that future iterations could incorporate additional sensors, such as heart rate monitors or EEG data, to improve detection accuracy. The system is positioned for application in both personal vehicles and commercial fleets, contributing to broader efforts in intelligent transportation and driver safety.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• drowsiness detection algorithms