Online Metric-Weighted Linear Representations for Robust Visual Tracking

Online Metric-Weighted Linear Representations for Robust Visual Tracking
复制标题

用于鲁棒视觉跟踪的在线度量加权线性表示

DOI:
10.1109/tpami.2015.2469276
复制
发表时间:
2015-07
期刊:
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
影响因子:
--
通讯作者:
Yueting Zhuang
Yueting Zhuang
中科院分区:
其他
文献类型:
--
作者:
Xi Li;Chunhua Shen;Anthony Dick;Zhongfei Zhang;Yueting Zhuang

文献摘要

参考文献

被引文献

相似文献

在本文中,我们提出了一种基于外观度量加权线性表示的视觉跟踪器。为了捕捉不同特征维度之间的相互依赖关系,我们提出了两种基于邻近度比较信息的在线距离度量学习方法和结构化输出学习方法。然后,将学习到的度量合并到外观的线性表示中。我们表明,在线距离度量学习显著提高了跟踪器的健壮性,特别是在那些外观发生剧烈变化的序列上。为了限制训练样本数量的增长,我们设计了一种时间加权的水库抽样方法。此外,通过引入一组属于多个感兴趣目标类的静态模板样本,使跟踪器能够在目标跟踪过程中自动执行目标识别。通过在每一帧系统地组合跟踪信息和视觉识别来获得整个视频序列的对象识别结果。对具有挑战性的视频序列的实验结果证明了该方法在帧间跟踪和目标识别方面的有效性。
In this paper, we propose a visual tracker based on a metric-weighted linear representation of appearance. In order to capture the interdependence of different feature dimensions, we develop two online distance metric learning methods using proximity comparison information and structured output learning. The learned metric is then incorporated into a linear representation of appearance. We show that online distance metric learning significantly improves the robustness of the tracker, especially on those sequences exhibiting drastic appearance changes. In order to bound growth in the number of training samples, we design a time-weighted reservoir sampling method. Moreover, we enable our tracker to automatically perform object identification during the process of object tracking, by introducing a collection of static template samples belonging to several object classes of interest. Object identification results for an entire video sequence are achieved by systematically combining the tracking information and visual recognition at each frame. Experimental results on challenging video sequences demonstrate the effectiveness of the method for both inter-frame tracking and object identification.
DOI: 10.1145/1141885.1141891
发表时间: 2006-06
期刊: ACM Trans. Math. Softw.
影响因子: --
作者:
M. Kolonko;D. Wäsch
通讯作者: M. Kolonko;D. Wäsch
DOI: 10.1109/cvpr.2012.6247898
发表时间: 2012-06
期刊: 2012 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Dong Woo Park;Junseok Kwon;Kyoung Mu Lee
通讯作者: Dong Woo Park;Junseok Kwon;Kyoung Mu Lee
DOI: 10.1109/cvpr.2012.6247872
发表时间: 2012-04
期刊: 2012 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Xi Li;Chunhua Shen;Javen Qinfeng Shi;A. Dick;A. Hengel
通讯作者: Xi Li;Chunhua Shen;Javen Qinfeng Shi;A. Dick;A. Hengel
DOI: 10.2307/2314680
发表时间: 1964
期刊: --
影响因子: --
作者:
A. Householder
通讯作者: A. Householder
DOI: 10.5555/2503308.2188386
发表时间: 2012
期刊: J. Mach. Learn. Res.
影响因子: --
作者:
Yiming Ying;Peng Li
通讯作者: Yiming Ying;Peng Li