项目中需要做人眼检测,目前主要有adaboost,,svm,基于相关算法的人眼检测,肤色分割瞳孔定位等算法。由于人眼特征数目比较少, adaboost的误检率和精准度都不行,而SVM比较慢,肤色空间等瞳孔定位太不稳定,反倒像ASEF,MOSSE等算法测试的效果还比较好,但是在闭眼,眼镜遮挡上还是不行,但是由于相关算法在频域中处理速度较快,因此可以考虑多训练几个模板。
参考文章:
PTIMIZED CORRELATION FILTERS FOR SIGNAL PROCESSING
DS Bolme, JR Beveridge, BA Draper
US Patent App. 12/797,241
Theory and applications of optimized correlation output filters
DS Bolme, Ph.D. Dissertation
COLORADO STATE UNIVERSITY
Average of synthetic exact filters
DS Bolme, BA Draper, JR Beveridge
Computer Vision and Pattern Recognition, 2009. CVPR 2009.
Visual object tracking using adaptive correlation filters
DS Bolme, JR Beveridge, BA Draper, YM Lui
Computer Vision and Pattern Recognition (CVPR), 2010
Simple real-time human detection using a single correlation filter
DS Bolme, YM Lui, BA Draper, JR Beveridge
Performance Evaluation of Tracking and Surveillance (PETS-Winter), 2009
原作者使用python代码实现的asef,mosse 算法地址:
http://www.cs.colostate.edu/~vision/ocof_toolset_2012/index.php