Hardware Implementation of Driver Fatigue Detection System

An efficient hardware for detecting driver Fatigue is implemented using non-intrusive vision based approach and DM3730 Processor. In this system a Logitech USB camera is fixed at a distance of 30cm which points towards driver's face and monitors face and eyes to detect driver fatigue. The entire system works on Linux operating system and uses DM3730 processor as hardware. An image processing algorithm is developed to estimate whether eyes are open or closed and fatigue is estimated using PERCLOS method. Eye blink rate for normal human being is 12 times per minute. In this algorithm if eyes are closed for 15 consecutive frames in a minute or if PERCLOS > 80% than system issues warning to stop the vehicle. The system is tested on 45 different persons i.e., 15 women, 15 men and 15 persons wearing spectacles and the detection rate is 99.2%. The time taken by the system to detect driver fatigue and issuing warning is less than 5ms. The entire system can be easily placed inside vehicle as hardware used is small in size and easily implementable without distracting the driver.