基于颜色和边缘特征自适应融合的人脸跟踪算法

doi:10.3969/j.issn.0253-2778.2017.10.005

中国科学技术大学学报 ›› 2017, Vol. 47 ›› Issue (10): 837-842.DOI: 10.3969/j.issn.0253-2778.2017.10.005

基于颜色和边缘特征自适应融合的人脸跟踪算法

周平平，万洪林，刘慧，李天平

1.山东师范大学物理与电子科学学院，山东济南 250358；2.山东财经大学计算机科学与技术学院，山东济南 250014

收稿日期:2017-05-16 修回日期:2017-06-22 出版日期:2017-10-31 发布日期:2017-10-31
通讯作者: 李天平
作者简介:周平平，女，1991年，硕士生.研究方向：视频图像处理. E-mail: 285048768@qq.com
基金资助:
山东省科技发展计划项目（2014gsf116004）资助.

Face tracking algorithm of color and edge features based adaptive fusion

ZHOU Pingping, WAN Honglin, LIU Hui, LI Tianping

1. School of Physics and Electronics, Shandong Normal University, Jinan 250358， China；
2. Department of Computer Science & Technology， Shandong University of Finance and Economics， Jinan 250014， China）

Received:2017-05-16 Revised:2017-06-22 Online:2017-10-31 Published:2017-10-31

摘要/Abstract

摘要： 针对传统的基于颜色直方图跟踪算法不能精确跟踪的缺陷，提出了一种基于粒子滤波的自适应融合多特征的人脸跟踪算法.该方法首先在视频序列中提取人脸的肤色和边缘特征，并以加权颜色直方图和边缘直方图描述人脸特征；然后采用自适应融合方法计算粒子集权重.这种自适应融合方法，有效地增强了人脸跟踪的可靠性.实验结果表明，在视频人脸存在类肤色以及光照变化等复杂背景下，该方法改善了跟踪效果并且具有较强的鲁棒性.

关键词: 人脸跟踪, 粒子滤波, 加权颜色直方图, 边缘方向直方图, 自适应融合方法

Abstract: In view of the imprecision of traditional tracking algorithms based on color histogram, a face tracking algorithm combining face multiple features based on adaptive fusion in the basic frame of particle filtering was presented.First, the color and edge features of the human face were extracted in the video sequence, while the weighted color histogram and edge orientation histogram(EOH) described facial features.Then, a self-adaptive features fusion strategy was employed to calculate particle set weight.The reliability of face tracking was enhanced by the self-adaptive features fusion strategy.Experimental results show that in the cases of complex backgrounds such as similar skin color, illumination change and so on, the proposed approach improves the tracking effect and has strong robustness.

Key words: face tracking, particle filtering, weighted color histogram, edge orientation histogram, self-adaptive features fusion

中图分类号:

TP391

周平平，万洪林，刘慧，李天平. 基于颜色和边缘特征自适应融合的人脸跟踪算法[J]. 中国科学技术大学学报, 2017, 47(10): 837-842.

ZHOU Pingping, WAN Honglin, LIU Hui, LI Tianping. Face tracking algorithm of color and edge features based adaptive fusion[J]. Journal of University of Science and Technology of China, 2017, 47(10): 837-842.

参考文献

［1］
王新红,王晶, 田敏, 等. 基于空间边缘方向直方图的Mean Shift跟踪算法[J].中国图象图形学报，2008, 13(3): 586-592.
WANG Xinhong WANG Jing, TIAN Min, et al. Mean shift tracking algorithm based on spatial edge orientation histograms[J]. Journal of Image and Graphics, 2008, 13(3): 586-592.
[2] WELCH G, BISHOP G. An Introduction to the Kalman Filter[M]// University of North Carolina at Chapel Hill, 2001, 8 (7): 127-132.
[3] ANDERSON B D, MOORE J B. Optimal Filtering[M]. New Jersey: Prentice-Hall, 1979.
[4] JULIER S J, UHLMANN J K A. New extension of the Kalman filter to non linear systems[C]// Proceedings of Aero Sense: The 11th International Symptom on Aero space/Defense Sensing, Simulation and Controls. SPIE, 1997: 182-193.
[5] ISARD M, BLAKE A. Condensation-conditional density propagation for visual tracking[J]. International Journal of Computer Vision, 1998, 29(1): 5-28.
[6] YANG D L，ZHANG Y L, JI R D, et al. An improved spatial histogram and particle filter face tracking[C]// Proceedings of the 8th International Conference on Genetic and Evolutionary Computing. Nanchang, China: Springer, 2014:257-267.
[7] DOU J F，LI J X，ZHANG Z，et al. Face tracking with an adaptive Adaboost-based particle filter[C]// 24th Chinese Control and Decision Conference. Taiyuan, China: IEEE, 2012, 23(1): 3626-3631.
[8] CHEN W M, LIN Y L, HSIEH Y H. An adaptive particle filter based method for real time face tracking[J]. Journal of Software Engineering and Applications, 2016, 6(5): 1-5.
[9] 田天，陈刚.基于肤色和Gabor 纹理的粒子滤波人脸跟踪[J].计算机工程，2014, 40(7): 123-127.
TIAN Tian, CHEN Gang. Face tracking using particle filtering based on skin color and Gabor texture[J]. Computer Engineering, 2014, 40(7): 123-127.
[10] SWAIN M J，BALLARD D H. Color indexing[J]. International Journal of Computer Vision, 1991, 7(1): 11-32.
[11] VALISKA J，MARCHEVSKY S， KOKOSKA R. Object tracking by color-based particle filter techniques in video sequences[C]// 24th International Conference Radioelektronika. Bratislava, Slovakia: IEEE, 2014:1-4.
[12] ZHU W，LEVINSON S. Edge orientation-based multi-view object recognition[J]. International Conference on Pattern Recognition，2000, 1(1): 1936-1939.
[13] KAILATH T. The divergence and Bhattacharyya distance measures in signal selection[J]．IEEE Transaction on Communication Technology, 1967, 15(1): 52-60.
[14] ZHOU S K，MOGHADDAM B. Appearance tracking using adaptive models in a particle filter[R]. Proceedings of Asian Conference Computer Vision, 2004.

()
(

基于颜色和边缘特征自适应融合的人脸跟踪算法

Face tracking algorithm of color and edge features based adaptive fusion

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价