视频序列图像中的人脸检测与跟踪  

Face Detection and Tracking in Video Sequences

作　　者：潘杰[1] 熊惠霖[1] 

机构地区：[1]上海交通大学电子信息与电气工程学院

出　　处：《微型电脑应用》2010年第10期33-36,2,共4页Microcomputer Applications

基　　金：国家高科技发展规划项目("863"计划)(项目编号:2007AA1Z196)

摘　　要：目标检测与跟踪是计算机视觉领域最普遍和关键的问题之一。基于级联结构的AdaBoost算法和基于色彩的Camshift算法,目前被认为是较有效的检测和跟踪算法,结合AdaBoost、Camshift算法和Kalman滤波器实现,对视频序列图像中多角度人脸的实时检测与跟踪,并针对AdaBoost训练耗时问题提出了改进。Object detection and tracking is one of the most popular and important issues in the domain of computer vision. The AdaBoost algorithm based on cascade structure and the Camshift algorithm based on color feature are recognized as one of the most effective approaches for face detection and traction.This paper propose to combine the AdaBoost algorithm, Camshift algorithm with the Kalman filtering algorithm to implement multi-view face detection and tracking in video sequences. A modified AdaBoost algorithm was proposed to reduce the training time, and meanwhile, guaranteed the detection accuracy.

关 键 词：ADABOOST CAMSHIFT 卡尔曼滤波器 肤色特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]