辅助驾驶系统中驾驶员头部姿态估计关键问题研究李荣刘坤高文鹏( 150020 , 300019 , 150001 ) 摘要: 智能交通系统中对驾驶员的行为监测具有重要的研究价值, 本文针对驾驶员的头部姿态监测问题进行了研究, 实现了基于计算机视觉的动态头部姿态估计算法。算法首先检测视频中的正面人脸,并作为基准,在此基础上对视频序列中人脸特征进行匹配与跟踪,计算不同视角下的头部姿态角度。考虑累计误差的影响,提出了一种矫正累积误差的方法。实验表明本文算法可以较准确地估计视频中的驾驶员头部姿态角度。关键词: 头部姿态估计;人脸检测;误差消除中文分类号: TP391 文献标识码: A Research on Key Issues of Driver ’s Head Pose Estimation in Driving Assistant System Li Rong1 Liu Kun2 Gao Wenpeng3 ( 1 Heilongjiang Institute of Technology School of automobile and traffic engineering harbin 150001,China; 2 HEBEI University of Technology 300019 , china; 3. Harbin Institute of Technology School harbin 150001,China ) Abstract : It is import to research the driver ’sb ehavior consciousness in the intelligent traffic system. In this paper, driver ’s head pose estimation is researched, and a vision-based scheme of estimating the driver ’s head pose is realized. F irstly, the driver ’s front face is detected from the video image, and the result is used as criterion. T hen corresponding feature points between two adjacent views are match to the points, the driver ’s head pose is estimat ed. We also bring forward a method to capture the key frames online through fusing the smoothness assumption of head ’s motion and other prior motion information , in order to eliminate the accumulating errors during continuous pose accumulation.
