Design a Landmark Facial-Based Drowsiness Detection Using Dlib And Opencv For Four-Wheeled Vehicle Drivers

Drowsiness harms motorists because it can cause microsleep. A landmark facial-based drowsiness detection application is required for monitoring motorists while driving. Drowsiness detection applications are designed based on face recognition methods that have an advantage in face detection. Several facial detection methods such as computer vision, dlib face detector, dlib facial landmark, and eye aspect ratio (EAR) are combined to design drowsiness detection applications. Application Design uses python 3.6.8, which has a supporting library in designing applications. The library used in designing the drowsiness detection application is openCV to process images and videos in real-time, Dlib for face detectors, Tkinter to build GUI applications. Input drowsiness detection application in the form of real-time video taken through a webcam. The app will activate alarm sounds and warning posts when a person is detected as drowsiness. Drowsy detection application testing is done using machine learning, confusion matrix, real-time testing, and evaluation of consumption of resources such as power, memory, and CPU. The accuracy value of testing using machine learning and confusion matrix is 97%, and Real-time testing accuracy is 96%. When used, the CPU usage percentage of drowsiness detection applications is 30.8%, memory usage is about 130.4 MB, and power consumption measured using Open Hardware Monitor is 5.09 W when the application is working.