全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于贝叶斯网络增强预测模型的人脸多特征跟踪

DOI: 10.11834/jig.20050234

Keywords: 人脸,特征跟踪,贝叶斯网络,计算机视觉,集成,跟踪算法,快速性,准确,难题,实验结果

Full-Text   Cite this paper   Add to My Lib

Abstract:

人脸多特征跟踪是当前计算机视觉中的一个难题,其中一个难点是需要尽可能准确地预测出下一帧中人脸多个特征轮廓的位置。提出了一个基于多重提示预测模型的跟踪算法,将基于二阶自回归过程的动力学模型的快速性特点与基于图模型(贝叶斯网络)动力学模型的准确性特点结合起来,得到融合的预测结果。多重提示的预测模型与观测模型可以方便地集成在卡尔曼滤波框架中。实验结果表明本文算法可以较准确地同时跟踪具有丰富表情的人脸多个特征。

References

[1]  Kass M, Witkin A, Terzopoulos D. Snakes: active contour models [J]. International Journal of Computer Vision, 1987,1(4) :321 -331.
[2]  Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift[ A]. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition ( CVPR\\' 00 ) [ C ]. Hilton Head Island, SC, USA, 2000:142 - 149.
[3]  Yedidia J S, Freeman W T. Understanding Belief Propagation and its Generalizations [ R]. TR-2001-22, Cambridge, MA: Mitsubishi Electric Research Laboratories, 2002.
[4]  Press W, Teukolsky S, Vetterling W, et al. Numerical Recipes in C (2nd edition)[ M]. Cambridge: Cambridge University Press, 1992.
[5]  谢存 孔祥维.利用光流预测Snakes模型初期轮廓的动态图象轮廓追迹方法[J].中国图象图形学报:A辑,2000,(8):666-669,.
[6]  孙家广.计算机图形学(第3版)[M].北京:清华大学出版社,1998..
[7]  Edwards G J, Taylor C J, Cootes T F. Learning to identify and track faces in image sequences[ A]. In: Proceedings of 6th International Conference on Computer Vision[ C], Bombay, India, 1998: 317 -322.
[8]  Haykin S. Adaptive Filter Theory (4th edition) [ M ]. Upper Saddle River, NJ: Prentice Hall, 2001.
[9]  Bishop C M. Neural Networks for Pattern Recognition [ M ]. Oxford:Oxford University Press, 1995.
[10]  Kanade T, Cohn J, Tian Y L. Comprehensive database for facial expression analysis [ A ]. In Proceedings of 4th IEEE International Conference on Automatic Face and Gesture Recognition (FG\\'00)[ C ] , Grenoble, France, 2000:46 - 53.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133