School of Electrical Engineering, Beijing Jiaotong University, Beijing, China

---

Abstract—Researches on Driver Fatigue Detection System, which aims to ensure the safety of operations and to reduce traffic accidents caused by artificial factors, has been the major research subject in transportation safety. There is an enormous advantage in the method obtaining the driver's image by camera, We propose efficient tracking and detecting algorithm and with an appearance model based on haar-like features, finding out the accuracy and robustness of tracking of eyes movements and the conflict between realtime tracing and accuracy of fatigue detection algorithms systems. First, PERCLOS algorithm is adopted to analyze and determine whether a person is fatigue. Second, AdaBoost algorithm is applied to fast detect and the algorithm is implemented in FPGA. Third, We propose a compressed sample tracking algorithm, which compress samples of image using the sparse measurement matrix and train the classification online. The algorithms runs in realtime and is implemented based on ARM add FPGA platform. Experimental results show that the algorithm has high recognition accuracy and robust performance under real train driving environment, in the case of nonlinear tracking of the human eye, illumination change, multi-scale variations, the driver head movement and pose variation.

Index Terms—PRECLOS, Face Detection, AdaBoost, Compressed sample tracking.

[PDF]

Cite: Zhui Lin, Lide Wang, Jieqiong Zhou, Tao Wang, "The Research on Fatigue Driving Detection Algorithm," Journal of Software vol. 8, no. 9, pp. 2272-2279, 2013.