摘要
以驾驶员疲劳检测为背景,针对灰度投影算法对人脸戴眼镜、姿态变化敏感,以及模板匹配算法计算量过大的问题,提出基于积分投影和模板匹配的人眼定位算法.利用图像网络分析算法检测出人脸区域,再对人脸区域进行灰度积分投影,并结合人脸结构特征实现眼睛的粗定位,然后采用模板匹配算法精确定位人眼.仿真结果表明此算法相较于传统的模板匹配算法对戴眼镜、姿态变化的人脸图像可快速地实现较好地人眼定位.
Under the background of driver fatigue detection,aiming at the problems that gray projection algorithm is sensitive to posture change and the complex calculation of template matching,eye location algorithm based on integral projection and template matching is proposed.Face region is detected by using image network analysis algorithm,the eye area is roughly located through the method of gray-level integral projection and face geometry character,then precisely located by using template matching.Simulation shows that this algorithm has good location effect for wearing glasses and posture change image compared with the traditional template matching algorithm.
引文
[1]Peng Yan,Zhou Tian,Wang Shaopeng,et al.Implementation of a real-time eye tracking system[J].The Journal of China Universities of Posts and Telecommunications,2013,20(S1):1-5.
[2]Song Fengyi,Tan Xiaoyang,Liu Xue,et al.Eyes closeness detection from still images with multi-scale histograms of principal oriented gradients[J].Pattern Recognition,2014,47(9):2 825-2 838.
[3]牛清宁,周志强,金立生,等.基于眼动特征的疲劳驾驶检测方法[J].哈尔滨工程大学学报,2015,36(3):394-398.
[4]Liu Chunsheng,Chang Faliang,Chen Zhenxue,et al.Improved gaussian skin color model and its application in face detection[J].Chinese Journal of Scientific Instrument,2012,33(5):1 117-1 121.
[5]李玲玲.基于多视觉信息融合的驾驶员疲劳检测方法研究与实现[D].北京:北方工业大学,2012.
[6]张文聪,邓宏平,李斌,等.基于径向对称变换的眼睛闭状态检测[J].中国科学技术大学学报,2013,40(5):460-465.
[7]R.Barea,L.Boquete,S.Ortega,et al.EOG-based eye movements codification for human computer interaction[J].Expert Systems with Applications,2012,39(3):2 677-2 683.
[8]张伟.基于机器视觉的驾驶人疲劳状态识别关键问题研究[D].北京:清华大学,2011.
[9]吴强,任琳,张杰.快速归一化互相关算法及DSP优化实现[J].电子测量与仪器学报,2011,25(6):495-499.
[10]刘莎.基于最小值区域的人眼定位新算法[J].微型机与应用,2011,30(20):37-43.
[11]Jesorsky O,Kirchberg J,Frishholz R W.Robust face detection using the hausdorff distance,audio and video based persion authentication[J].Lecture Notes in Computer Science,2001,47(9):90-95.