[1]钟必能,陈雁,沈映菊,等.在线机器学习跟踪算法的研究进展[J].华侨大学学报(自然科学版),2014,35(1):41-46.[doi:10.11830/ISSN.1000-5013.2014.01.0041]
　ZHONG Bi-neng,CHEN Yan,SHEN Ying-ju,et al.Research Progress on Visual Tracking Algorithms Based on Online Machine Learning[J].Journal of Huaqiao University(Natural Science),2014,35(1):41-46.[doi:10.11830/ISSN.1000-5013.2014.01.0041]
点击复制

在线机器学习跟踪算法的研究进展()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第35卷
期数:
2014年第1期
页码:
41-46
栏目:
出版日期:
2014-01-20

文章信息/Info

Title:
Research Progress on Visual Tracking Algorithms Based on Online Machine Learning
文章编号:
1000-5013(2014)01-0041-06
作者:
钟必能;  陈雁;  沈映菊;  陈锻生;  陈维斌
华侨大学 计算机科学与技术学院, 福建 厦门 361021
Author(s):
ZHONG Bi-neng;  CHEN Yan;  SHEN Ying-ju;  CHEN Duan-sheng;  CHEN Wei-bin
College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China
关键词:
目标跟踪算法;  在线机器学习;  目标漂移;  多跟踪器
Keywords:
target tracking algorithms;  online machine learning;  target drifting;  multiple trackers
分类号:
TP391.41
DOI:
10.11830/ISSN.1000-5013.2014.01.0041
文献标志码:
A
摘要:
分类介绍在线机器学习跟踪算法的研究现状,比较各种算法的优缺点.研究表明:每一种跟踪算法都有其自身的优点和缺点,通常情况下只能处理某一些特定类型的变化,很难确保某一特定类型的跟踪算法能够处理复杂跟踪场景中的所有不确定因素.最后,针对在线学习算法容易产生误差积累,最终发生目标漂移的问题,提出使用多跟踪器的融合,实现鲁棒跟踪等相应的解决方案.
Abstract:
In this paper, the tracking algorithms based on online learning are reviewed, and the advantages and disadvantages of various tracking algorithms are compared. It is found that each kind of tracking method has its strengths and weaknesses and is applicable for handling one or a few types of challenges, it is difficult, if not impossible, for a single tracking method to work under a variety of tracking scenarios. Finally, to address the target drifting problem caused by the error accumulation, we propose a fusion strategy using multiple trackers to achieve robust tracking results.

参考文献/References:

[1] 韩崇昭,侯志强.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617.
[2] 谭铁牛,王亮,胡卫明.人运动的视觉分析综述[J].计算机学报,2002,25(3):225-237.
[3] 章毓晋,贾慧星.车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述[J].自动化学,2007,33(1):84-90.
[4] YILMAZ A,JAVED O,SHAH M.Object tracking: A survey[J].ACM Computing Surveys,2006,38(4):13-20.
[5] YANG Han-xuan,SHAO Ling,ZHENG Feng,et al.Recent advances and trends in visual tracking: A review[J].Neurocomputing,2011,74(18):3823-3831.
[6] COLLINS R T,LIU Yan-xi,LEORDEANU M.Online selection of discriminative tracking features[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1631-1643.
[7] GRABNER H, MATAS J, VAN G L. Tracking the invisible: Learning where the object might be[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition.San Francisco:IEEE Press,2010:1285-1292.
[8] KALAL Z,MATAS J,MIKOLAJCZYK K.PN learning: Bootstrapping binary classifiers by structural constraints[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition.San Francisco:IEEE Press,2010:49-56.
[9] BABENKO B, YANG M H, BELONGIE S. Visual tracking with online multiple instance learning[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition.Colorado:IEEE Press,2009:983-990.
[10] GRABNER H,LEISTNER C,BISCHOF H.Semi-supervised on-line boosting for robust tracking[C]//Proceedings of the Europe Conference on Computer Vision.Marseille:Springer Press,2008:234-247.
[11] KIM T K,WOODLEY T,STENGER B,et al.Online multiple classifier boosting for object tracking[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition Workshops.San Francisco:IEEE Press,2010:1-6.
[12] SANTNER J,LEISTNER C,SAFFARI A,et al.Prost: Parallel robust online simple tracking[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition.San Francisco:IEEE Press,2010:723-730.
[13] ZHONG Bi-neng,YAO Hong-xun,CHEN Sheng,et al.Visual tracking via weakly supervised learning from multiple imperfect oracles[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition.San Francisco:IEEE Press,2010:1323-1330.
[14] SAFFARI A,LEISTNER C,SANTNER J,et al.On-line random forests [C]//Proceedings of the International Conference on Computer Vision Workshops(ICCV Workshops).Kyoto:IEEE Press,2009:1393-1400.
[15] ISARD M,BLAKE A.Condensation: Conditional density propagation for visual tracking[J].International Journal of Computer Vision,1998,29(1):5-28.
[16] LU L,DAI X T,HAGER G.A particle filter without dynamics for robust 3d face tracking[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition Workshop.Washington:IEEE Press,2004:70.
[17] AVIDAN S.Ensemble tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(2):261-271.
[18] OZA N C,RUSSELL S.Online bagging and boosting[C]//Proceedings of the International Conference on Artificial Intelligence and Statistics.Florida:IEEE Press,2001:2340-2345.
[19] GRABNER H,BISCHOF H.On-line boosting and vision[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2006:260-267.
[20] LIU Xiao-ming,YU Ting.Gradient feature selection for online boosting[C]//Proceedings of the International Conference on Computer Vision.Rio de Janeiro:IEEE Press,2007:1-8.
[21] SAFFARI A,GODEC M,POCK T,et al.Online multi-class lpboost[C]//Proceedings of the International Conference of Computer Vision and Pattern Recognition.San Francisco:IEEE Press,2010:3570-3577.
[22] DEMIRIZ A,BENNETT K P,SHAWE T J.Linear programming boosting via column generation[J].Machine Learning,2002,46(1):225-254.
[23] LEISTNER C,GRABNER H,BISCHOF H.Semi-supervised boosting using visual similarity learning[C]//Proceedings of the International Conference of Computer Vision and Pattern Recognition.Alaska:IEEE Press,2008:1-8.
[24] SCHULTER S,LEISTNER C,ROTH P M,et al.Online hough forests[C]//Proceedings of British Machine Vision Conference.Dundee:Springer Press,2011:1-11.
[25] GALL J,YAO A,RAZAVI N,et al.Hough forests for object detection, tracking, and action recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(11):2188-2202.
[26] GODEC M,ROTH P M,BISCHOF H.Hough-based tracking of non-rigid objects [C]//Proceedings of International Conference of Computer Vision.Barcelona:IEEE Press,2011:81-88.
[27] BLUM A,MITCHELL T.Combining labeled and unlabeled data with co-training [C]//Proceedings of the eleventh Annual Conference on Computational Learning Theory.Madison:ACM Press,1998:92-100.
[28] TANG Feng,BRENNAN S,ZHAO Qi.Co-tracking using semi-supervised support vector machines[C]//Proceedings of the International Conference of Computer Vision.Rio de Janeiro:IEEE Press,2007:1-8.
[29] LIU Rong,CHENG Jian,LU Han-qing.A robust boosting tracker with minimum error bound in a co-training framework[C]//Proceedings of the International Conference on Computer Vision.Kyoto:IEEE Press,2009:1459-1466.
[30] DASGUPTA S,LITTMAN M L,MCALLESTER D.Pac generalization bounds for co-training[C]//Proceedings of the Advances in Neural Information Processing Systems.Whistler:MIT Press,2002:375-382.
[31] LEISTNER C,GODEC M,SAFFARI A,et al.Online multi-view forests for tracking[J].Pattern Recognition,2010,6327(10):493-502.
[32] STALDER S,GRABNER H,VAN G L.Beyond semi-supervised tracking: Tracking should be as simple as detection, but not simpler than recognition[C]//Proceedings of the International Conference on Computer Vision Workshops.Kyoto:IEEE Press,2009:1409-1416.
[33] STENGER B,WOODLEY T,CIPOLLA R.Learning to track with multiple observers[C]//Proceedings of the International Conference on Computer Vision and Pattern Recognition.Florida:IEEE Press,2009:2647-2654.

相似文献/References:

[1]谢维波,夏远祥,刘文.采用互补特征的核相关滤波目标跟踪算法[J].华侨大学学报(自然科学版),2018,39(3):429.[doi:10.11830/ISSN.1000-5013.201611030]
　XIE Weibo,XIA Yuanxiang,LIU Wen.Target Tracking Algorithm Using Complementary Features of Kernelized Correlation Filter[J].Journal of Huaqiao University(Natural Science),2018,39(1):429.[doi:10.11830/ISSN.1000-5013.201611030]

备注/Memo

备注/Memo:
收稿日期: 2012-12-24
通信作者: 钟必能(1981-),男,讲师,博士,主要从事计算机视觉和视频跟踪的研究.E-mail:bnzhong@gmail.com.
基金项目: 国家自然科学基金资助项目(61202299); 华侨大学高层次人才科研启动项目(11BS109, 11BS213)
更新日期/Last Update: 2014-01-20