Non-sparse linear representations for visual tracking with online reservoir metric learning
Non-sparse linear representations for visual tracking with online reservoir metric learning
复制标题
DOI：
10.1109/cvpr.2012.6247872
复制
发表时间：
2012-04
期刊：
影响因子：
--
通讯作者：
Xi Li;Chunhua Shen;Javen Qinfeng Shi;A. Dick;A. Hengel
中科院分区：
文献类型：
--
作者：
Xi Li;Chunhua Shen;Javen Qinfeng Shi;A. Dick;A. Hengel
大多数基于稀疏线性表示的跟踪器需要解决一个计算代价昂贵的li-正则化优化问题。为了解决这个问题，我们提出了一种基于非稀疏线性表示的视觉跟踪器，它在不牺牲精度的情况下提供了有效的封闭形式解决方案。此外，为了捕获不同特征维之间的相关信息，我们在线学习了马氏距离度量，并将学习到的度量纳入到优化问题中以获得线性表示。我们表明，使用接近比较的在线度量学习显着提高了跟踪的鲁棒性，特别是在那些表现出剧烈外观变化的序列上。此外，为了防止度量学习训练样本数量的无界增长，我们设计了一种时间加权水库采样方法来维护和更新有限大小的前景和背景样本缓冲区，以平衡样本多样性和适应性。挑战性视频的实验结果证明了该跟踪器的有效性和鲁棒性。
Most sparse linear representation-based trackers need to solve a computationally expensive li-regularized optimization problem. To address this problem, we propose a visual tracker based on non-sparse linear representations, which admit an efficient closed-form solution without sacrificing accuracy. Moreover, in order to capture the correlation information between different feature dimensions, we learn a Mahalanobis distance metric in an online fashion and incorporate the learned metric into the optimization problem for obtaining the linear representation. We show that online metric learning using proximity comparison significantly improves the robustness of the tracking, especially on those sequences exhibiting drastic appearance changes. Furthermore, in order to prevent the unbounded growth in the number of training samples for the metric learning, we design a time-weighted reservoir sampling method to maintain and update limited-sized foreground and background sample buffers for balancing sample diversity and adaptability. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker.