DEVELOPMENT OF ANTI DROWSINESS AND ALERT SYSTEM FOR AUTOMOBILE DRIVERS

Drowsy Driving has been one of the leading causes of traffic and road accidents. According to the National Safety Council (2021), sleepy driving causes 100,000 collisions and 71,0 injuries, including 1,550 deaths per year. The researcher developed an automated automobile system that prevents drivers from drowsy driving. The proposed methodology is divided into the following stages: face detection, eye detection, as well as steering wheel interactions. First, the Raspberry Pi camera streams, then the video data will be analyzed with an object detection algorithm and classifies using the Haar Cascade Classifier technique. As the result it detects areas of the face and eyes to determine drowsiness. In addition, the force sensor monitored the driver's steering wheel interactions, such as hand grip strength. Furthermore, the alert will be activated if two parameters, including Eye Aspect Ratio and Hand Grip Strength, drop below a certain threshold. On several test footage, the average accuracy rate for drowsiness detection without glasses was 96.94 %, whereas it was 92.29 % with glasses. Generally, the drowsiness detection system achieves 94.61 % accuracy in detecting the drowsiness of the driver's eyes in real-time. The proposed method was implemented using a Raspberry Pi 4 Model B with 8GB RAM plus Raspberry Pi NOIR Camera and an Arduino Mega 2560 with a force-sensing resistor. Sensor performance is expected to expand as technological advancement initiatives continue. As an outcome, it is possible to conclude that the provided method is an efficient solution to detect driver drowsiness.