摘要
在分析和总结国内外对人脸检测与跟踪的相关研究成果的基础上,研究提出了在Viola-Jones人脸检测算法中引入运动区域检测和人脸肤色检测以缩小人脸检测的搜索区域,有效地提高了人脸检测的帧处理速度,并降低了人脸检测的误检率。对基于Meanshift算法和基于光流法的人脸跟踪方法进行了研究与分析,分析了各算法的优缺点,利用各算法之间性能上的互补性,通过各模块之间的协同合作设计并实现了一个实时人脸检测与跟踪系统,并设定了相应的评价参数,通过实验室录制视频和NRC-IIT视频人脸数据库对系统进行了性能测试。
The Viola-Jones face detection algorithm has been analyzed in detail. And motion detection and skin color detection are used to improve the face detection speed and reduce the false acceptance rate. The face tracking algorithm based on Meanshifl and optical flow has been researched. Real-time face detecting and tracking system is established and the complementarity between different algorithms is utilized to obtain good detecting and tracking performance. Extensive tests were carried out in the Laboratory enjoinment, using both self-collected video databases and third party testing materials.
出处
《电子器件》
CAS
北大核心
2013年第3期304-308,共5页
Chinese Journal of Electron Devices
基金
国家自然科学基金项目(51075068)
