基于活动摄像头的人脸定位跟踪系统

Face detection and tracking system design based on rotatable camera

针对固定摄像头无法自动跟踪拍摄运动目标的缺陷,设计了基于舵机的活动摄像系统,以实现活动人脸的定位与跟踪。在adaboost人脸检测算法的基础上,结合计算机视觉类库OpenCV与图形界面开发框架Qt在VS2010开发环境下,设计并实现了人脸检测-定位-跟踪系统。测试结果表明,在明亮环境条件下识别准确率达到100%,在昏暗条件下准确率为95%,对于人脸的部分遮挡以及上、下、左、右侧脸都能被检测到。本文方法可广泛应用于安防等领域。

For the restrictions that the fixed camera cannot automatically track the moving target,a rotatable camera system was designed based on the steering engine,in order to position and track the moving face.The Adaboost algorithm was used to detect and track the face.The face detection-positioning–tracking system was designed under the development environment of Visual studio 2010 with the computer vision class library OpenCV and the graphical interface development framework Qt.The test results show that the accuracy rate for tracing face is 100%in the bright environment,and 95%in the dim environment.And it is also effective to tract the partially occluded face.This system can also be applied for security and other fields.