Driver Drowsiness Alert System using Machine Learning and Autonomous Car Parking

This research tackles some of the critical challenges in vehicle safety and convenience by developing an integrated driver drowsiness alert and auto-parking system. Driver fatigue is one of the major causes of accidents, hence the need for real-time drowsiness detection. The proposed solution uses state-of-the-art computer vision techniques in the Python IDE to monitor driver alertness through the detection of prolonged closure of eyes for more than five seconds. Upon the detection of drowsiness, an alert is transmitted to the vehicle via the Blynk app. The vehicle, which is equipped with an ESP32 microcontroller, ultrasonic sensors for parking assistance, and an L298 motor driver for controlling movement, responds autonomously. It adjusts its trajectory by steering left and moving straight until it receives a stop signal from an RF transmitter connected to another ESP32 microcontroller. This system increases safety by preventing accidents due to drowsiness and improves convenience through automated parking. The integration of real-time communication and automation offers a robust solution to modern driving challenges.