눈 움직임 검출 및 눈 폐쇄 상태 인지 기반의 운전자 졸음 감지 시스템

Abstract

In this paper, we describe a real-time prototype driver-fatigue monitor. It uses remotely located normal CCD camera to acquire video images of the driver. The system relies on multiple visual cues to characterize the level of alertness of the driver. The parameters used for monitoring drowsiness are: eye blinking frequencies and eye closure durations. Initially, the captured image is converted to gray scale to detect the face in video frame. Then, an eye region is extracted from the face region and used to identify closure state. Finally, the display of the video is updated with embedded rectangles to mark detected face and eye and visually indicate drowsiness states.