Deteksi Kantuk Pada Pengemudi Mobil Menggunakan Eye Aspect Ratio Dengan Metode Facial Landmark

Abstract

The number of traffic accidents in Indonesia is increasing. One of the main factors causing an accident is the driver's drowsiness. In general, drowsiness appears at night when the body needs rest. However, some of them appear due to fatigue during activities, situations like this need to be considered when we are driving so that the number of accidents caused by drowsiness can be avoided. From these problems, we need a tool that can automatically detect whether the car driver is sleepy or conscious using a facial landmark method. Where in the early stages it starts with taking pictures using the Raspberry Pi camera which will be processed by the Raspberry Pi 3b to detect facial areas using the eye aspect ratio then the algorithm on the eye aspect ratio is used to detect sleepy eyes with the output in the form of speakers and water pumps, where the speakers will emits a sound that can be changed according to the wishes of the driver. After the speaker sounds, the water pump will spray water on the face to react so that the driver doesn't get sleepy.