基于人脸检测和CAMSHIFT算法的人脸跟踪系统

针对彩色视频序列,本文提出一种基于检测和彩色直方图的人脸跟踪系统,首先利用Adaboost算法进行快速人脸检测和定位,然后通过Canny滤波获取精确的人脸区域建立肤色直方图模型,在CAMSHIFT算法的基础上运用人脸形态约束,Kalman滤波进行实时的人脸跟踪,实验证明该系统具有较好的实时性并能很好的解决遮挡,类肤色干扰和快速移动的问题.

A Face Tracking System Based on Face Detection and CAMSHIFT Algorithm

In order to track the face in colored video sequence, a tracking system is presented based on face detection and color histogram. First we detect and focus on the face area using Adaboost algorithm. Then a color histogram model is constructed after the more precise area of the face is getted due to the Canny filter. Besides the CAMSHIFT algorithm, Kalman filter and human's face feature is also used in our system. The experiment results demonstrate that the system is not only real time but also handle well the complex situation such as occlusion, disturbing by skin colored object and fast moving.