REAL-TIME DRIVER EYE DETECTION METHOD USING SUPPORT VECTOR MACHINE WITH HU INVARIANT MOMENTS

摘要：

In the development of advanced vehicle safety systems, monitoring the drivers vigilance level and issuing an alert when he is not paying enough attention to the road is a promising way to reduce the road accidents. In such driver monitoring systems, developing a reliable real-time driver eye detection method is a crucial part. In this paper, a rear-time eye detection method using Support Vector Machine (SVM) with Hu invariant moments is proposed. In the method binaryzation and heuristic rules to screen the contour are firstly used to find the Region Of Interest (ROI) of the drivers eye. Then the Hu invariant moments of the ROI are calculated and further used in developing the SVM model. The test sets from the experiment were used to validate the classification results. The validation results and conclusions about the performance of the method are presented.

关键词： Non-intrusive Real-time Eye detection Support Vector Machine Hu Moment invariant

作者: GUANG-YUAN ZHANG BO CHENG RUI-JIA FENG JIA-WEN LI

作者单位: State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, 100084, China Sc State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, 100084, China

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 2999-3004

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）