摘要
介绍了一种能够自适应各种光照变化的疲劳驾驶检测系统的设计方案。首先利用YCbCr色彩空间中肤色的聚类特性受光照明暗条件影响的性质来进行光照强弱的判断,划分为弱、中、强3种情况,由系统自适应地选择相应的处理措施,旨在鲁棒地检测到人的双眼。完成上述人眼区域的粗定位后,在人脸五官几何结构的先验知识约束下,根据区域生长及形态学运算精确定位眼睛位置。最后通过计算PERCLOS值来判断是否疲劳。实验证明该方法准确率高,能在各种光照情况下进行实时疲劳检测。
A design of adaptive illumination detection system for fatigue driving is introduced in the paper.Firstly the surrounding lightening is classified into weak,medium,strong conditions based on analyzing human skin region in YCbCr space.And the system can adaptively select the appropriate strategies.This strategy aims at robustly locating human eye regions.Then the accurate eye positioning is performed under the geometric constraints with region growing and morphology operating.Finally the fatigue degree is calculated by PERCLOS value.The experiments show that this framework has high accuracy under different lighting situation in real-time fatigue detection.
出处
《电子测量与仪器学报》
CSCD
2012年第1期60-66,共7页
Journal of Electronic Measurement and Instrumentation
基金
安徽省自然科学基金(070412035)
合肥工业大学校重大项目预研专项(2010HGZY0003)
关键词
自适应疲劳检测
光照强度判断
人眼定位
疲劳判决
Adaptive fatigue detection
judgment of illumination intensity
positioning of human eye
fatigue decision
