Design of ADSP-BF548 fatigue driving detection system based on eye features

To avoid traffic accidents caused by fatigue driving, this paper utilizes fatigue detection algorithm based on eye features to transplant on ADSP-BF548 hardware platform. The camera captures driver´s face video in real time; it localizes driver´s eye position and status via frame-difference projection, template matching and Kalman methods. At last, make a warning if driver´s eye-close time proportion is more than the threshold in a period of time. The experiment shows this driver fatigue detection system based on ADSP-BF548 is of high accuracy and real-time.