Advanced driver monitoring utility.
-
Updated
Jul 8, 2026 - C
Advanced driver monitoring utility.
A curated list of peer-reviewed papers on theoretical and practical aspects of drivers' attention used for paper "Attention for Vision-Based Assistive and Automated Driving: A Review of Algorithms and Datasets" and report on "Behavioral research and practical models of drivers' attention".
Intelligent Driver Monitoring system for Autonomous Vehicles
The "Driver Coach" system is based on a camera, sensors and machine learning algorithms. It monitors car driver behaviour and provides feedback to improve road safety. The system can be part of a larger Road Safety ECO system sharing data between driver and organisations (Smart City).
Mobile app for driver monitoring using computer vision
An unofficial PyTorch implementation of the 3MDAD dataset
RoadGuard — 5G ve Yapay Zekâ ile Akıllı Yol Güvenliği Sistemi (TEKNOFEST 2026): YOLO26 araç/plaka/sürücü-davranışı/hız tespiti + CAMARA QoD/NV 5G entegrasyonu
AI-powered Driver Monitoring and Vehicle Anomaly Detection System using ESP32, OpenCV, MediaPipe Face Landmarker, EAR-based drowsiness detection, and real-time RPM anomaly monitoring.
Mobile app for driver monitoring using computer vision (by Popcorn Racers)
Upon sleep detection, the code will trigger notifications that include a combination of gentle vibrations on the watch and an escalating audio alert on the phone. This approach provides a multi-sensory wake-up cue to increase the user's chance of being roused from sleep.
AI-Powered Driver Monitoring System.
A computer vision library for detecting gaze, emotions, and drowsiness in a browser in real time using state-of-the-art strategies and neural networks.
Driver fatigue & dangerous-behavior detection with Python/OpenCV: frame pipeline, state recognition, and alert flow (graduation project)
A Driver-Monitoring TinyML system-on-chip: RISC-V CPU + a quantized neural-network accelerator that classifies driver state (ALERT/DROWSY/DISTRACTED). Full train->quantize->silicon->verify flow. Self-checking testbenches + CI.
A real-time driver monitoring and risk assessment system using YOLO, MediaPipe, and computer vision to detect driver drowsiness, distraction, phone usage, and other risky behaviors.
Real-time facial expression and driver fatigue monitoring with MiniXception architecture, Grad-CAM interpretability, active learning photo booth, and edge-optimized inference.
Real time, on device driver drowsiness detection from a cabin camera, running at real time frame rates on a Raspberry Pi 4B.
A basic driver monitoring system using cv2 and mediapipe, written in python
AI-powered driver drowsiness detection system using OpenCV, MQTT, and ESP32.
To associate your repository with the driver-monitoring topic, visit your repo's landing page and select "manage topics."