Robust visual tracking via identifying multi-scale patches
Robust visual tracking via identifying multi-scale patches
复制标题
通过识别多尺度斑块进行稳健的视觉跟踪
DOI：
10.1007/s11042-018-6760-4
复制
发表时间：
2018-11
影响因子：
3.6
通讯作者：
Lin Chen
中科院分区：
文献类型：
--
作者：
Liang Yun;Li Ke;Zhang Jian;Wang Meihua;Lin Chen
目标及其周围环境的复杂变化给跟踪带来了诸如遮挡、变形等挑战。许多挑战并存于一段视频中，这使得跟踪仍然没有成功地解决。目前的追踪器在一个共同模式中处理目标所有组成部分的共存挑战。然而，不同的部件往往同时面临不同的挑战，有些部件会变形，有些部件会遮挡。共同的模式不能同时适应这些挑战。一种有效的方法是分开应对挑战。本文提出了一种新的稳健跟踪器，通过分别跟踪和识别目标的多尺度块来应对共存的挑战。这是通过三个方面实现的。首先，将高斯混合模型引入到核化相关滤波器(KCF)中，定义了一种新的基本跟踪器。针对KCF对相似环境非常敏感的特点，利用高斯混合模型构造正则项和损失函数对KCF构成的分类器进行优化。其次，定义了一种新的基于多尺度块的目标外观表示模型。为了处理不同变化的面片，我们分别构造和更新了它们的外观表示。第三，根据基本跟踪器计算出的每个块的跟踪结果，利用结构信息和霍夫投票来确定目标。然后，我们的方法通过剔除失败的跟踪块来提高精度。在跟踪基准上进行了大量的实验，定量和定性评估表明，该跟踪器的性能优于现有的大多数跟踪器。
The complex changes of target and its surroundings introduce several tracking challenges, such as occlusion, deformation and so on. Many challenges coexist in a video which makes tracking still under successfully solved. The present trackers deal with coexisting challenges in a common model for all components of target. However, different components often undergo different challenges at the same time, while some with deformation and others with occlusion. The common model cannot adapt to these challenges simultaneously. An effective method is to separately deal with the challenges. This paper proposes a new robust tracker via separately tracking and identifying the multi-scale patches of target to cope with the coexisting challenges. It is achieved by three respects. Firstly, we define a new basic tracker by introducing the gaussian mixture model into Kernelized Correlation Filters (KCF). For the KCF is very sensitive to the similar surroundings, we construct a regular term and a loss function via the gaussian mixture model to optimize the classifier formed by KCF. Secondly, we define a new appearance representation model of target by multi-scale patches. To deal with the different variations of patches, we separately construct and update their appearance representations. Thirdly, with the tracked result of each patch computed by our basic tracker, we use the structure information and the Hough Vote to decide the target. Then, our method improves the accuracy by rejecting the failed tracked patches. Many experiments have been achieved on the Tracking Benchmark, and the quantitative and qualitative evaluations show that the proposed tracker performs better than most of the present trackers.
登录
查看更多内容
影响因子：
10.6
作者：
Yang, Fan;Lu, Huchuan;Yang, Ming-Hsuan
通讯作者：
Yang, Ming-Hsuan
DOI：
10.1023/b:visi.0000029664.99615.94
发表时间：
2004-11-01
影响因子：
19.5
作者：
Lowe, DG
通讯作者：
Lowe, DG
DOI：
10.5244/c.25.57
发表时间：
2013-02
期刊：
IEEE Transactions on Systems, Man, and Cybernetics: Systems
影响因子：
--
作者：
Yuandong Xu;J. Cui;Huijing Zhao;H. Zha
通讯作者：
Yuandong Xu;J. Cui;Huijing Zhao;H. Zha
DOI：
--
发表时间：
--
期刊：
--
影响因子：
--
作者：
João F. Henriques;Rui Caseiro;P. Martins;Jorge Batista
通讯作者：
João F. Henriques;Rui Caseiro;P. Martins;Jorge Batista
DOI：
10.1109/tpami.2013.32
发表时间：
2013-10
影响因子：
23.6
作者：
Junseok Kwon;Kyoung Mu Lee
通讯作者：
Junseok Kwon;Kyoung Mu Lee