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...

融合检测和跟踪的实时人脸跟踪

DOI: 10.11834/jig.20151106

Keywords: 人脸检测,跟踪,控制,AdaBoost,随机蕨

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的在实时人脸跟踪过程中,因光照变化、目标被遮挡以及跟踪时间长等因素,导致的误差累积都会影响系统的整体性能。针对这些问题,提出一种融合检测和跟踪技术的方法,其中包含了检测、控制和跟踪3个模块(简称DCT)。方法在检测模块中,利用AdaBoost算法提取人脸的相关信息,并将信息传递给跟踪模块进行跟踪处理;在跟踪模块中,采用在线随机蕨和SURF(speededuprobustfeatures)算法对目标进行跟踪。同时,在每次检测到目标之后,会通过控制模块对当前跟踪目标准确性进行判断。结果选取国际标准数据组并与LBP+Camshift+Kalman滤波算法、SEMI算法、TLD(tracking-learning-detection)算法比较,实验结果表明,DCT方法在目标发生尺度较大变化、目标遮挡、旋转、形变以及光照发生变化时都具有良好的跟踪识别效果,DCT方法识别准确率在95%以上,平均误识别率和漏识别率分别为0.86%和0.78%。结论DCT方法具有消除误差累积,跟踪失败后自动恢复等特点,同时可以消除环境中光照、遮挡和仿射变换的影响并满足系统跟踪的实时性要求,运用于视频人脸跟踪系统中能够提高系统的实时性及鲁棒性。

References

[1]  Li W W, Zhang C B, Chen Z H, et al. Particle filter tracking based on feature-learning and feature-memory template update mechanism[J]. Journal of University of Science and Technology of China, 2014, 44(4):292-302.[李维维, 张陈斌, 陈宗海,等.基于特征学习与特征记忆模板更新机制的粒子滤波跟踪[J]. 中国科学技术大学学报, 2014, 44(4):292-302.]
[2]  Wu J Z, Chen F L, Hu D W. A detection-based person tracking algorithm[J]. Journal of National University of Defense Technology, 2014,(2):113-117.[吴建宅, 陈芳林, 胡德文. 基于检测的人体跟踪算法[J]. 国防科技大学学报, 2014,(2):113-117.]
[3]  Kalal Z, Mikolajczyk K, Matas J. Face-TLD:tracking-learning-detection applied to faces[C]//Proceedings of the 17th International Conference on Image Processing. Washington DC:IEEE, 2010:3789-3792.
[4]  Chu H X, Qin J P, Xie Z Y, et al. Multi-target tracking of Adaboost detection combining with hybrid particle filtering[J]. Journal of Huazhong University of Science and Technology:Natural Science Edition, 2013, 41(7):76-81.[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.]
[5]  Bay H, Tuytelaars T, Van G L. Surf:speeded up robust features[M]. Computer Vision-ECCV 2006. Berlin Heidelberg:Springer, 2006:404-417.
[6]  Chen Z L, Cai M G, Liu F X. Face detection combining skin and face-like feature[J]. Computer Engineering and Applications, 2013,49(3):194-197.[陈章乐, 蔡茂国, 刘凡秀. 一种结合肤色及类人脸特征的人脸检测[J]. 计算机工程与应用, 2013,49(3):194-197.]
[7]  Chang W C, Cho C W. Online boosting for vehicle detection[J]. IEEE Transactions on Systems Man and Cybernetics-Part B:Cybernetics, 2010, 3:892-902 .
[8]  Wanjale K H, Bhoomkar A, Kulkarni A, et al. Use of haar cascade classifier for face tracking system in real time video[J]. International Journal of Engineering Research & Technology, 2013, 4(2):2348-2353.
[9]  Ozuysal M, Calonder M, Lepetit V, et al. Fast keypoint recognition using random ferns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(3):448-461.
[10]  Ji Q G, Zhang P, Du J H. Robust vision tracking by online random ferns and template library[J]. Signal Processing:Image Communication, 2014, 29(5):590-598.
[11]  Dinh T B, Vo N, Medioni G. Context tracker:exploring supporters and distracters in unconstrained environments[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Colorado, USA:IEEE, 2011:1177-1184.
[12]  Kalal Z, Matas J, Mikolajczyk K. P-N learning:bootstrapping binary classifiers by structural constraints[C]//Proceedings of Conference on Computer Vision and Pattern Recognition. Boston, USA:IEEE, 2010:49-56.
[13]  Cai C H, Cui X L, Zhu J Q, et al. Camishift face tracking with adaptive MB-LBP pre-filter[J]. Journal of Signal Processing, 2013, 29(11):1540-1546.[蔡灿辉, 崔晓琳, 朱建清,等. 具有自适应 MB-LBP前置滤波的Camshift人脸跟踪算法[J]. 信号处理,2013, 29(11):1540-1546.]
[14]  Stalder S, Grabner H, Gool L V. SemiBoost:boosting for semi-supervised learning[C]//Proceedings of ICCV\'09 WS on On-line Learning for Computer Vision. Kyoto, Japan:IEEE, 2009:1203-1213.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133