Inverse Sparse Tracker With a Locally Weighted Distance Metric

Inverse Sparse Tracker With a Locally Weighted Distance Metric
复制标题

具有局部加权距离度量的逆稀疏跟踪器

DOI:
10.1109/tip.2015.2427518
复制
发表时间:
2015-04
期刊:
IEEE Transaction on Image Processing
影响因子:
--
通讯作者:
Ming-Hsuan Yang
Ming-Hsuan Yang
中科院分区:
其他
文献类型:
--
作者:
Dong Wang;Huchuan Lu;Ziyang Xiao;Ming-Hsuan Yang

文献摘要

参考文献

被引文献

相似文献

稀疏表示最近已被广泛研究的视觉跟踪,一般有利于更准确的跟踪结果比经典的方法。在本文中,我们提出了一种基于稀疏性的跟踪算法,其特征在于两个组成部分:1)一个逆稀疏表示公式和2)一个局部加权距离度量。在逆稀疏表示公式中,用粒子重构目标模板,这使得跟踪器仅通过求解一个最小1优化问题来计算所有粒子的权重,从而提供了一个非常有效的模型。这与大多数以前的稀疏跟踪器形成了直接对比,后者需要为每个粒子解决一个优化问题。然而,我们注意到,这个公式与正常的欧几里德距离度量是敏感的部分噪声,如闭塞和照明变化。为此,我们设计了一个局部加权的距离度量来代替欧几里德距离度量。类似的使用局部特征的想法出现在其他作品中,但只有得到流行假设的支持,如局部模型可以比整体模型更好地处理部分噪声,而没有任何坚实的理论分析。在本文中,我们试图明确地解释它从数学的观点。在此基础上,我们进一步提出了一种方法来分配局部权重,利用时间和空间的连续性。在所提出的方法中,外观变化引起的部分遮挡和形状变形进行了仔细考虑,从而促进准确的相似性度量和模型更新。实验验证主要从两个方面进行:1)关键部件的自验证和2)与其他算法的比较。对15个具有挑战性的序列的跟踪结果表明,所提出的跟踪算法的性能优于现有的基于稀疏性的跟踪器和其他国家的最先进的方法。
Sparse representation has been recently extensively studied for visual tracking and generally facilitates more accurate tracking results than classic methods. In this paper, we propose a sparsity-based tracking algorithm that is featured with two components: 1) an inverse sparse representation formulation and 2) a locally weighted distance metric. In the inverse sparse representation formulation, the target template is reconstructed with particles, which enables the tracker to compute the weights of all particles by solving only one ℓ1 optimization problem and thereby provides a quite efficient model. This is in direct contrast to most previous sparse trackers that entail solving one optimization problem for each particle. However, we notice that this formulation with normal Euclidean distance metric is sensitive to partial noise like occlusion and illumination changes. To this end, we design a locally weighted distance metric to replace the Euclidean one. Similar ideas of using local features appear in other works, but only being supported by popular assumptions like local models could handle partial noise better than holistic models, without any solid theoretical analysis. In this paper, we attempt to explicitly explain it from a mathematical view. On that basis, we further propose a method to assign local weights by exploiting the temporal and spatial continuity. In the proposed method, appearance changes caused by partial occlusion and shape deformation are carefully considered, thereby facilitating accurate similarity measurement and model update. The experimental validation is conducted from two aspects: 1) self validation on key components and 2) comparison with other state-of-the-art algorithms. Results over 15 challenging sequences show that the proposed tracking algorithm performs favorably against the existing sparsity-based trackers and the other state-of-the-art methods.
具有遮挡检测功能的高效最小误差有界粒子重采样 L1 跟踪器
DOI: 10.1109/tip.2013.2255301
发表时间: 2013-07-01
影响因子: 10.6
作者:
Mei, Xue;Ling, Haibin;Bai, Li
通讯作者: Bai, Li
DOI: 10.1109/tip.2014.2300823
发表时间: 2014-04-01
影响因子: 10.6
作者:
Yang, Fan;Lu, Huchuan;Yang, Ming-Hsuan
通讯作者: Yang, Ming-Hsuan
DOI: --
发表时间: 2009
期刊: --
影响因子: --
作者:
Xue Mei;Haibin Ling
通讯作者: Xue Mei;Haibin Ling
DOI: 10.1109/tip.2010.2050625
发表时间: 2010-11-01
影响因子: 10.6
作者:
Yang, Jianchao;Wright, John;Ma, Yi
通讯作者: Ma, Yi
DOI: --
发表时间: 2004-06
期刊: --
影响因子: --
作者:
J. G. Allen;R. Xu;Jesse S. Jin
通讯作者: J. G. Allen;R. Xu;Jesse S. Jin