基于红外光源的驾驶员眼睛特征提取

Driver Eye Feature Extraction Based on Infrared illuminator

驾驶员疲劳与精神分散是引发夜间行车交通安全事故的主要因素之一,驾驶员眼睛位置的快速准确定位是利用视觉方法对驾驶员的夜间驾驶状态进行监测和预警的前提。文中利用Otsu阈值方法分割驾驶员人脸,根据分割后的二值化图像进行水平和垂直方向投影确定人脸位置,并在可靠定位人脸区域的基础上,建立了眼睛位置检测的感兴趣区域。采用Harris角点特征提取的方法在感兴趣区域内进行眼睛位置的快速有效定位。实验结果表明,该算法具有很好的可靠性和实时性,为后续夜间驾驶员状态研究奠定了良好基础。

Driver fatigue and distraction at night is a major factor in the night-time traffic accident. Eye location is the precondition to monitor driver＇s fatigue state with the help of image processing technique. Based on Otsu threshold segmentation method, and with the help of horizontal projection in gray image and vertical projection in binary image, the paper located the driver face region accurately and established the AOI for eye location. The method of Harris corner detection was used to efficiently and accurately locate the eye position. Experiments prove its reliability and validity.