留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于权值分配及多特征表示的在线多示例学习跟踪

杨红红 曲仕茹 米秀秀

杨红红, 曲仕茹, 米秀秀等 . 基于权值分配及多特征表示的在线多示例学习跟踪[J]. 北京航空航天大学学报, 2016, 42(10): 2146-2154. doi: 10.13700/j.bh.1001-5965.2015.0644
引用本文: 杨红红, 曲仕茹, 米秀秀等 . 基于权值分配及多特征表示的在线多示例学习跟踪[J]. 北京航空航天大学学报, 2016, 42(10): 2146-2154. doi: 10.13700/j.bh.1001-5965.2015.0644
YANG Honghong, QU Shiru, MI Xiuxiuet al. Tracking approach based on online multiple instance learning with weight distribution and multiple feature representation[J]. Journal of Beijing University of Aeronautics and Astronautics, 2016, 42(10): 2146-2154. doi: 10.13700/j.bh.1001-5965.2015.0644(in Chinese)
Citation: YANG Honghong, QU Shiru, MI Xiuxiuet al. Tracking approach based on online multiple instance learning with weight distribution and multiple feature representation[J]. Journal of Beijing University of Aeronautics and Astronautics, 2016, 42(10): 2146-2154. doi: 10.13700/j.bh.1001-5965.2015.0644(in Chinese)

基于权值分配及多特征表示的在线多示例学习跟踪

doi: 10.13700/j.bh.1001-5965.2015.0644
基金项目: 航空科学基金(2012ZC53043);高等学校博士学科点专项科研基金(20096102110027);航天科技创新基金(CASC201104)
详细信息
    作者简介:

    杨红红,女,博士研究生。主要研究方向:目标检测与跟踪。Tel.:029-88431386,E-mail:yanghonghong0615@163.com;曲仕茹,女,博士,教授。主要研究方向:智能系统与信息工程。Tel.:029-88431386,E-mail:qushiru@nwpu.edu.cn;米秀秀,女,硕士研究生。主要研究方向:特征提取与目标跟踪。Tel.:029-88431386,E-mail:mixiuxiu@mail.nwpu.edu.cn

    通讯作者:

    曲仕茹,Tel.:029-88431386,E-mail:qushiru@nwpu.edu.cn

  • 中图分类号: TP391;TP391.4

Tracking approach based on online multiple instance learning with weight distribution and multiple feature representation

Funds: Aeronautical Science Foundation of China (2012ZC53043); Specialized Research Fund for the Doctoral Program of Higher Education of China (20096102110027); Astronautic Science and Technology Innovation Foundation (CASC201104)
  • 摘要: 针对复杂环境下目标跟踪过程中由于遮挡、目标姿势及光照条件变化引起跟踪漂移的问题,提出一种基于多示例学习(MIL)框架的在线视觉目标跟踪算法。该算法针对多示例跟踪算法采用单一haar-like特征不能准确描述目标外观变化及在学习过程中对样本包中各正负样本示例采用相同权值,忽略不同正负样本示例在学习过程中对包的重要性不同的特点,采用多特征联合表示目标外观构造分类器,通过将多特征互补特性融入在线多示例学习过程中,利用多特征的互补属性建立准确的目标外观模型,克服在线多示例跟踪算法对目标外观变化描述不足的问题;同时,依据不同正负样本示例对样本包的重要程度进行权值分配,提高跟踪精度。实验结果表明,本文跟踪算法对场景光线剧烈变化、遮挡、尺度变化及平面旋转等干扰具有较强的跟踪鲁棒性,通过对不同视频序列进行测试,文中算法在5组测试视频序列上的平均中心位置误差远小于对比增量式学习跟踪,仅为10.14像素,其对比算法IVT、MIL和OAB的中心位置误差分别为17.99、20.29和33.64像素。

     

  • [1] YILMAZ A,JAVED O,SHAH M.Object tracking: A survey[J].ACM Computing Surveys,2006,38(4):1-45.
    [2] ROSS D A,LIM J,LIN R S,et al.Incremental learning for robust visual tracking[J].International Journal of Computer Vision,2008,77(1-3):125-141.
    [3] BLACK M,JEPSON A.Eigentracking:Robust matching and tracking of objects using view-based representation[J].International Journal of Computer Vision,1998,26(1):63-84.
    [4] COMANICIU D,RAMESH V,MEER P.Real-time tracking of non-rigid objects using mean shift[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2000:142-149.
    [5] ADAM A,RIVLIN E,SHIMSHONI I.Robust fragments-based tracking using the integral histogram[C]//Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2006:798-805.
    [6] KWON J,LEE K M.Visual tracking decomposition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2010:1269-1276.
    [7] GRABNER H,GRABNER M,BISCHOF H.Real-time tracking via on-line boosting[C]//Proceedings of the British Machine Vision Conference 2006.Edinburgh:British Machine Vision Association,2006:47-56.
    [8] AVIDAN S.Ensemble tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(2):261-271.
    [9] GRABNER H,LEISTNER C,BISCHOF H.Semi-supervised on-line boosting for robust tracking[C]//Proceedings of the 10th European Conference on Computer Vision.New York:Springer Berlin Heidelberg,2008:234-247.
    [10] BABENKO B,YANG M,BELONGIE S.Robust object tracking with online multiple instance learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1619-1632.
    [11] LIN R S,ROSS D A,LIM J,et al.Adaptive discriminative generative model and its applications[C]//Advances in Neural Information Processing Systems 17.Cambridge:MIT Press,2004:801-808.
    [12] VIOLA P,JONES M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2001:511-518.
    [13] ZHANG K,SONG H.Real-time visual tracking via online weighted multiple instance learning[J].Pattern Recognition,2013,46(1):397-411.
    [14] XU C,TAO D C,XU C.A survey on multi-view learning[J/OL].Computer Science,2013.https://arxiv.org/abs/1304.5634.
    [15] MORENO-NOGUER F,SANFELIU A,SAMARAS D.Dependent multiple cue integration for robust tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(4):670-685.
    [16] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2005,886-893.
    [17] KALAL Z,MATAS J,MIKOLAJCZYK K.P-N learning:Bootstrapping binary classifiers by structural constraints[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2010:49-56.
    [18] YOON J H,KIM D Y,YOON K J.Visual tracking via adaptive tracker selection with multiple features[C]//Proceedings of the 12th European Conference on Computer Vision.New York:Springer Berlin Heidelberg,2012:28-41.
    [19] 宁纪锋,赵耀博,石武祯.多通道Haar-like特征多示例学习目标跟踪[J].中国图象图形学报,2014,19(7):1038-1045.NING J F,ZHAO Y B,SHI W Z,et al.Multiple instance learning based object tracking with multi-channel Haar-like feature[J].Journal of Image and Graphics,2014,19(7):1038-1045(in Chinese).
    [20] YOON J,YANG M,YOON K.Interacting multiview tracker[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015(99):1-14.
    [21] DJOUADI A,SNORRASON O,GARBER F.The quality of training sample estimates of the bhattacharyya coefficient[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):92-97.
  • 加载中
计量
  • 文章访问数:  587
  • HTML全文浏览量:  71
  • PDF下载量:  460
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-09-30
  • 网络出版日期:  2016-10-20

目录

    /

    返回文章
    返回
    常见问答