二颜色空间中CamShift人脸跟踪CamShift algorithm of face tracking in two color spaces
王俊南,赖惠成
摘要(Abstract)：
针对CamShift算法在对人脸跟踪时容易受到肤色背景的影响,且当跟踪环境中背景较为复杂时易失败的问题,提出一种二颜色空间中CamShift人脸跟踪算法。该算法首先在YCgCr与YCgCb空间中进行肤色分割,将每一视频帧中的肤色区域与非肤色区域有效地分隔开来;然后对保留的肤色区域进行形态学操作,并在经过形态学处理所得的肤色区域中引入人脸几何特征,规定只有当肤色区域的长宽比为0.5~1.0或肤色区域面积大于5 000像素的部分方为人脸;最后使用CamShift算法在规定的肤色区域中跟踪人脸。同时为了自动检测目标人脸以初始化搜索窗口,减少算法的处理时间,提高算法的性能,又引入改进的AdaBoost算法检测人脸。实验结果显示,该算法可以获得有效且可靠的跟踪结果。
关键词(KeyWords)： YCgCr颜色空间;YCgCb颜色空间;肤色分割;AdaBoost算法;CamShift算法;人脸跟踪
基金项目(Foundation): 国家自然科学基金资助项目(61561048);; 新疆维吾尔自治区科学基金资助项目(2015211C257)~~
作者(Author): 王俊南,赖惠成
DOI: 10.16652/j.issn.1004-373x.2018.21.009
参考文献(References)：
- [1] BRADSKI G R. Real time face and object tracking as a component of a perceptual user interface[C]//Proceedings of 1998IEEE Workshop Applications of Computer Vision. Princeton,NJ:IEEE,1998:214-221.
- [2]刘士荣,姜晓艳.一种改进的CamShift/Kalman运动目标跟踪算法[J].控制工程,2010,17(4):470-474.LIU Shirong,JIANG Xiaoyan. A moving object tracking algorithm based on modified CamShift/Kalman filter[J]. Control engineering of China,2010,17(4):470-474.
- [3]朱承志.基于OpenCV的人脸检测与跟踪[J].计算机工程与应用,2012,48(26):157-161.ZHU Chengzhi. Face detection and tracking based on OpenCV[J].Computer engineering and applications,2012,48(26):157-161.
- [4] WU S Q,NAGAHASHI H. Parameterized AdaBoost:introducing a parameter to speed up the training of real AdaBoost[J].IEEE signal processing letters,2014,21(6):687-691.
- [5]初红霞,秦进平,谢忠玉,等.AdaBoost检测和混合粒子滤波融合的多目标跟踪[J].华中科技大学学报(自然科学版),2013,41(7):76-81.CHU Hongxia,QIN Jinping,XIE Zhongyu,et al. Multi-target tracking of AdaBoost detection combining with hybrid particle filtering[J]. Journal of Huazhong University of Science and Technology(nature science edition),2013,41(7):76-81.
- [6]张江鑫,陈林,吴佳颖.一种基于CamShift聚类的粒子滤波人脸跟踪算法[J].浙江工业大学学报,2017(2):168-172.ZHANG Jiangxin,CHEN Lin,WU Jiaying. A particle filter algorithm for face tracking based on CamShift clustering[J]. Journal of Zhejiang University of Technology,2017(2):168-172.
- [7]胡章芳,秦阳鸿.基于图割理论的尺度自适应人脸跟踪算法[J].计算机应用,2017,37(4):1189-1192.HU Zhangfang,QIN Yanghong. Scale-adaptive face tracking algorithm based on graph cuts theory[J]. Journal of computer applications,2017,37(4):1189-1192.
- [8]余佳伟.基于视频的人脸检测与跟踪技术的研究及应用[D].成都:电子科技大学,2016:24-25.YU Jiawei. The study and application of face detection and tracking based on video[D]. Chengdu:University of Electronic Science and Technology of China,2016:24-25.
- [9]王建玺,李玮瑶.基于改进AdaBoost算法的人脸检测[J].微处理机,2015(5):57-60.WANG Jianxi,LI Weiyao. Face detection based on improved AdaBoost algorithm[J]. Microprocessors,2015(5):57-60.
- [10] DONG C,WANG X,LIN T,et al. Face detection under particular environment based on skin color model and radial basis function network[C]//2015 IEEE Fifth International Conference on Big Data and Cloud Computing. Dalian:IEEE,2015:256-259.
- [11] BAO F,ZHANG Y. Face tracking algorithm based on online random forests detection[C]//2015 14th International Symposium on Distributed Computing and Applications for Business Engineering and Science. Guiyang:IEEE,2015:320-323.
- [12] KEKRE H B,THEPADE S,DAS R K K,et al. Multilevel block truncation coding with diverse color spaces for image classification[C]//2013 International Conference on Advances in Technology and Engineering. Mumbai:IEEE,2013:1-7.
- [13] YADAV N,THEPADE S. Content based video retrieval using self mutated hybrid wavelet transforms with assorted color spaces[C]//2010 International Conference&Workshop on Electronics&Telecommunication Engineering. Mumbai:IEEE,2016:222-227.
- [14] YANG Y B,XIE C G,DU L B,et al. A new face detection algorithm based on skin color segmentation[C]//2015 Chinese Automation Congress. Wuhan:IEEE,2015:523-526.
- [15] KUNCHEVA L I,WHITAKER C J. Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy[J]. Machine learning,2003,51(2):181-207.