[1]苏景龙,林天威,王科俊,等.视频流下的人脸检测与跟踪[J].应用科技,2011,38(03):5-11.[doi:10.3969/j.issn.1009-671X.2011.03.002]
 SU Jinglong,LIN Tianwei,WANG Kejun,et al.Face detection and tracking in video[J].Applied science and technology,2011,38(03):5-11.[doi:10.3969/j.issn.1009-671X.2011.03.002]
点击复制

视频流下的人脸检测与跟踪(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第38卷
期数:
2011年03期
页码:
5-11
栏目:
自动化技术
出版日期:
2011-03-05

文章信息/Info

Title:
Face detection and tracking in video
文章编号:
1009- 671X(2011)03- 0005- 07
作者:
苏景龙1林天威2王科俊3贲晛烨4
(1. 哈尔滨商业大学 德强商务学院,黑龙江 哈尔滨 150028; 2.上海通用东岳汽车有限公司 涂装生产部,山东 烟台 264100; 3.哈尔滨工程大学 自动化学院,黑龙江 哈尔滨 150001; 4.哈尔滨工业大学 交通科学与工程学院, 黑龙江 哈尔滨 150090)
Author(s):
SU Jinglong1LIN Tianwei1WANG Kejun2BEN Xianye3
(1. Tek keung Commerce Business School,Harbin University of Commerce,Harbin 150028,China; 2. SGM Dong Yue Motorcars Co.,Ltd.,Yantai 264100,China; 3.College of Automation,Harbin Engineering University,Harbin 150001,China; 4. School of Transportation Science and Engineering,Harbin Institute of Technology,Harbin 150090,China)
关键词:
人脸检测人脸跟踪AdaBoost均值移动算法
Keywords:
face detection face tracking AdaBoost Meanshift
分类号:
TP391.41
DOI:
10.3969/j.issn.1009-671X.2011.03.002
文献标志码:
A
摘要:
研究了基于AdaBoost算法的人脸检测、级联分类器,讨论了Haar-Like特征及其积分图的计算方法,以及微结构特征的详细定义和表示方式,并给出4种不同矩形特征的计算方法.以色彩直方图为跟踪特征,将基于AdaBoost的人脸检测算法与CamShift跟踪算法进行了有效的结合,并给出视频下的人脸检测与跟踪实验结果.实验结果表明,在尺度变化、角度变化以及有遮挡的情况下都得到了很好的检测、跟踪效果.
Abstract:
Face detection based on Adaboost and cascade classifier are studied in this paper. Haar-Like features,computing method of integral image,detail definition of micro structural features and their description modes are discussed. The computing methods of four different kinds of rectangle features are also given. Moreover,color histogram is the feature of tracking,and face detection based on Adaboost which is combined effectively with tracking algorithm based on CamShift is proposed. To evaluate the performance of the proposed method,experiments have been conducted on video sequences. Experimental results show this proposed method can operate successfully detection and tracking in scale variation,view variation or occlusion.

参考文献/References:

[1]SCHAPIRE R E. The strength of weak learn ability [J]. Machine Learning,1990,5(2):197-227.
[2]KEARNS M,VALIANT L G. Cryptographic limitations on learning Boolen formulae and finite automata[J]. Journal of the ACM,1994,41(1):67-95.
[3]FREUND Y,SCHAPIRE R E. A decision-theoretic generalization of on-line learning and an application to boosting[C]//Computational Learning Theory: Eurocolt’95. Barcelona,Spain,1995.
[4]VIOLA P,JONES M. Robust real time object detection [C]//8th IEEE International Conference on Computer Vision (ICCV). Vancouver,Canada,2001.
[5]WANG Kejun,HOU Benbo. A survey of gait recognition[J]. Journal of Image and Graphics,2007,12(7):1152-1160.
[6]李全利,何世民. 基于DM642的AdaBoost人脸检测算法优化与实现[J].自动化技术与应用,2009,28(10):79-82.
[7]林天威.基于视频流下的人脸识别系统研究[D]. 哈尔滨:哈尔滨工程大学自动化学院,2010.
[8]张利伟,张航,张玉英.面部表情识别方法综述[J].自动化技术与应用,2009,28(1):93-97.
[9]高建坡,王煜坚,杨浩,等.以颜色和形状直方图为线索的粒子滤波人脸跟踪[J].中国图像图形学报,2007,12(3):466-473.

相似文献/References:

[1]王宝玉,等.融合人脸与步态周期模式的行人检测[J].应用科技,2012,39(01):44.[doi:10.3969/j.issn.1009-671X.201110010]
 WANG Baoyu,BEN Xianye,WANG Kejun.A pedestrian detection method integrating face information and gait period pattern[J].Applied science and technology,2012,39(03):44.[doi:10.3969/j.issn.1009-671X.201110010]
[2]孔凡芝,张兴周,谢耀菊.基于Adaboost的人脸检测技术[J].应用科技,2005,32(06):7.
[3]潘晓宏1,赵龙1,2.基于Unscented 卡尔曼滤波算法在海底地形辅助导航中的应用[J].应用科技,2015,42(01):49.[doi:10.3969/j.issn.1009671X.201312017]
 WU Xian,LIU Qifeng.A method of selecting source data ofpictures in the modeling of face detection[J].Applied science and technology,2015,42(03):49.[doi:10.3969/j.issn.1009671X.201312017]
[4]吴限,刘崎峰.人脸检测建模源照片筛选方法[J].应用科技,2015,42(01):33.[doi:10.3969/j.issn.1009671X.201312017]
 WU Xian,LIU Qifeng.A method of selecting source data ofpictures in the modeling of face detection[J].Applied science and technology,2015,42(03):33.[doi:10.3969/j.issn.1009671X.201312017]

备注/Memo

备注/Memo:
基金项目:国家“863”高科技基金资助项目(2008AA01Z148).
作者简介:苏景龙(1988-),男,本科生,主要研究方向:模式识别在管理方面的应用,E-mail:joexying@126.com.
更新日期/Last Update: 2011-04-12