摘要
主要研究驾驶人的面部定位设计,可以限定图像采集的背景,引入了帧间信息处理技术,采用差分分析方法并利用二值化进行图像相关处理,利用水平和垂直投影方法进行粗略的头肩定位.依据直方图均衡化与原图像的差值二值化进一步精确定位人脸.该算法运算速度快、定位准确,试验效果好,达到了实时性的目的.
Concerning that this article mainly studies the driver＇s face-location design and we can limit the background image acquisition, therefore, this artical introduces interframe information technology with the differential analysis methods and taking use of two binary images related, re-use horizontal and vertical projection methods for rough positioning of the head and shoulder. Again based on histogram equalization and the original image value of the margin two further precision positioning face. The algorithm show itself with high speed, accurate positioning, test results prove good, and achieves a certain purpose.
出处
《北京工商大学学报（自然科学版）》
CAS
2008年第2期23-26,30,共5页
Journal of Beijing Technology and Business University:Natural Science Edition
基金
国家"863"高技术研究发展计划资助项目(2006AA11Z213)
关键词
驾驶人行为监测
差分算法
阈值法
滤除噪声
投影
surveillance of driver＇ s action
differential algorithm
threshold method
filtering noise
projection
