A real time, webcam based, driver attention state detection/monitoring system in Python3 using OpenCV and Mediapipe

Real-time drowsiness detection using Python, MediaPipe, and EAR to monitor driver fatigue and prevent accidents.

Python-based Fleet Management System with real-time automotive telematics: OBD-II diagnostics, GPS tracking, CAN bus decoding, DTC analysis, driver behavior monitoring, fuel analytics & live dashboard. Built with FastAPI + SQLAlchemy.

MVP for detecting drowsiness of driver using the eye lids of the driver, if the driver seems to be drowsy it gives an alarm

Convolutional Neural Network for predicting driver attention based on a front-facing image of the driver 🚘

While drunk or drowsy people can’t react to stimuli efficiently in the environment, thus we intend to check for a verbal response from the driver upon detecting anomalous driving patterns. IMU tracker upon detecting frequent changes in acceleration and sharp turns triggers the voice assistant, checking up on the driver’s state and takes further …

Driver Behaviour Analysis System (DBAS) is a ROS-based driver monitoring system utilizing OpenCV, Dlib, and YOLOv5 to detect and alert on drowsiness, device usage, and other behaviors during driving.

IoT-based system for real-time driver drowsiness detection using ESP32 and cloud services for monitoring and alerts.

Real-time driver drowsiness detection using OpenCV Haar Cascades and a CNN trained on eye-state images. Triggers an audio alarm and saves a snapshot when prolonged eye closure is detected via webcam.

Jetson Nano Drowsiness Detection - SUSTech Project of CS324: Deep Learning in Fall 2025 - Score: 95/100

A real-time driver fatigue detection system using computer vision. This project monitors eye movements to detect drowsiness and alerts the driver with a visual and audible warning when fatigue is detected. Built with OpenCV, dlib, and Python, it's designed for enhancing driver safety.

This Arduino-based system enhances driver safety by using sensors to monitor for drowsiness and detect alcohol on the driver's breath. It provides real-time alerts to prevent accidents caused by fatigue or impairment, promoting safer roads for everyone.

Driver drowsiness detection using YOLOv8n face ROI, a CNN classifier, Grad-CAM explainability, and fuzzy risk mapping.

Real-time drowsiness & yawn detection via Eye Aspect Ratio (EAR), dlib 68-point landmarks, and an optional CNN classifier. Supports live webcam and headless video modes.

The AI-powered driver safety system integrates deep learning models to enhance road safety. Features include Traffic Sign Recognition (CNN-based), Pedestrian Detection (YOLO-based), Driver Monitoring (drowsiness detection), and Speed Control & Auto-Braking (AI & IoT) to prevent accidents and ensure safer driving.

Real-time driver drowsiness detection using OpenCV and MediaPipe with EAR and MAR based voice alerts

Real-time driver drowsiness detection using MediaPipe face landmarks and Eye Aspect Ratio (EAR)

Analyzing large-scale vehicle camera datasets using Convolutional Neural Networks to classify distracted driving behaviors and evaluate trends in driver position change for road safety applications.