驾驶辅助系统中人脸检测方法研究  

Study on Face Detection Methods in Driver Assistance System

作　　者：张文霞[1] 王旭 

机构地区：[1]长春汽车工业高等专科学校,吉林长春130000

出　　处：《汽车实用技术》2017年第18期83-84,共2页Automobile Applied Technology

摘　　要：文章从车辆的主动安全角度出发,利用Adaboost算法训练人脸分类器,然后进行人脸检测,从而确定人脸区域。文章采集了大量驾驶室环境样本进行人脸分类器的训练,还对提出的方法进行了对比分析,实验说明提出的人脸姿态估计方法具有高速、精确的特性。这项技术可以应用于驾驶辅助系统的开发。In this paper, the Adaboost algorithm is used to train the face classifier from the point of view of active safety of the vehicle, and then face detection is carried out to determine the face area. In this paper, a large number of cab environment samples are collected for human face classifier training, and the proposed method is compared and analyzed. The experimental results show that the proposed method has high speed and accurate characteristics. This technology can be applied to the development of driving assistance systems.

关 键 词：ADABOOST算法 人脸分类器 样本 人脸检测 

分 类 号：V448.151[航空宇航科学与技术—飞行器设计]