One of the main technical goals in the automotive industry is to provide and increase vehicle safety. The traffic accidents are increasing day by day due to a diminished driver's vigilance level and it became a serious problem for the society. By monitoring the fatigue of the driver, the vehicle safety can be improved. Eye detection is an important initial step in Driver Fatigue Detection System. This feature can be used for developing 'Driver fatigue detection system' by monitoring attention or drowsiness of the driver. Robust non-intrusive eye tracking is a crucial step for vision based man-machine interaction technology which is widely accepted in common environments. Eye detection and tracking is an integral part of attentive user interfaces. To detect human eyes, face has to be detected initially. This is done using Open CV face Haar-cascade classifier. After obtaining successful face detection, the location of the eyes is estimated and eye detection is performed using eye haar-cascade classifier. The work aims at development of a driver safety system with visual aid to prevent accidents. The vehicle is equipped with USB web camera interfaced to the system. Here the camera is used for tracking the eyes of driver to detect fatigue. The driver assistance system unit consists of a BEAGLE BOARD with a DM3730 processor in it. The system runs on an embedded operating system called Angstrom. The system architecture deals with the development of device driver for USB web camera and DM3730 processor in standard Linux kernel. Open CV package is installed to interface USB web camera with the navigation system. Open CV package consists of various image processing functions, which are useful for identification of driver fatigue. Open CV is used as a platform to develop a code for eye detection in real time. The code is then implemented on the Beagle board (Ported with Angstrom Operating System) installed with Open CV software. (Author/publisher)
Samenvatting