Loading repository data…
chetanwakde / repository
Architected a privacy-first Edge AI driver safety system on Raspberry Pi 4 using 3 real-time data streams (vision, steering, vitals). Built a Python pipeline with 6+ features including PERCLOS, yawning, and gaze detection for fatigue/distraction monitoring. Integrated ESP32 alerts with GPS-based emergency notifications.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
Driver fatigue, distraction, and sudden medical emergencies are major causes of road accidents worldwide. Traditional safety systems are either reactive (like airbags) or rely on a single data source (like vision-only alerts), which limits their effectiveness.
This project introduces a multi-modal AI-powered system that continuously monitors the driver using three key inputs:
All processing is performed on-device, ensuring privacy, low latency, and offline functionality.
Selected from shared topics, language and repository description—not editorial ratings.
Architected a privacy-first Edge AI driver safety system on Raspberry Pi 4 using 3 real-time data streams (vision, steering, vitals). Built a Python pipeline with 6+ features including PERCLOS, yawning, and gaze detection for fatigue/distraction monitoring. Integrated ESP32 alerts with GPS-based emergency notifications.
59/100 healthgit clone https://github.com/your-username/driver-wellness-ai.git
cd driver-wellness-ai
▶️ How It Works
1 The camera captures real-time video of the driver
2 AI models analyze facial features to detect fatigue indicators:
3 Eye closure
4 Yawning
5 Head movement
6 Steering behavior and vitals data are collected
7 A fusion engine evaluates the driver’s condition
8 Alerts are triggered based on severity
9 In critical situations, the system slows down or stops the vehicle and sends emergency alerts