当前位置: X-MOL 学术IEEE Trans. Pattern Anal. Mach. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence ( IF 23.6 ) Pub Date : 2018-12-21 , DOI: 10.1109/tpami.2018.2889070
Jin Gao , Qiang Wang , Junliang Xing , Haibin Ling , Weiming Hu , Stephen Maybank

This paper presents a new Gaussian Processes (GPs)-based particle filter tracking framework. The framework non-trivially extends Gaussian process regression (GPR) to transfer learning, and, following the tracking-by-fusion strategy, integrates closely two tracking components, namely a GPs component and a CFs one. First, the GPs component analyzes and models the probability distribution of the object appearance by exploiting GPs. It categorizes the labeled samples into auxiliary and target ones, and explores unlabeled samples in transfer learning. The GPs component thus captures rich appearance information over object samples across time. On the other hand, to sample an initial particle set in regions of high likelihood through the direct simulation method in particle filtering, the powerful yet efficient correlation filters (CFs) are integrated, leading to the CFs component. In fact, the CFs component not only boosts the sampling quality, but also benefits from the GPs component, which provides re-weighted knowledge as latent variables for determining the impact of each correlation filter template from the auxiliary samples. In this way, the transfer learning based fusion enables effective interactions between the two components. Superior performance on four object tracking benchmarks (OTB-2015, Temple-Color, and VOT2015/2016), and in comparison with baselines and recent state-of-the-art trackers, has demonstrated clearly the effectiveness of the proposed framework.

中文翻译:

通过高斯过程回归的融合跟踪扩展到了转移学习

本文提出了一个新的基于高斯过程(GPs)的粒子过滤器跟踪框架。该框架非平凡地扩展了高斯过程回归(GPR)以转移学习,并且遵循融合跟踪策略,紧密集成了两个跟踪组件,即GP组件和CF组件。首先,GP组件通过利用GP对对象外观的概率分布进行分析和建模。它将标记的样本分类为辅助样本和目标样本,并在迁移学习中探索未标记的样本。因此,GPs组件会随时间捕获对象样本上丰富的外观信息。另一方面,要通过粒子滤波中的直接模拟方法对高可能性区域中的初始粒子集进行采样,则需要集成功能强大而高效的相关滤波器(CF),导致CFs组件。实际上,CFs组件不仅提高了采样质量,还受益于GPs组件,它提供了重新加权的知识作为潜在变量,用于确定辅助样本中每个相关滤波器模板的影响。这样,基于转移学习的融合实现了两个组件之间的有效交互。在四个对象跟踪基准(OTB-2015,Temple-Color和VOT2015 / 2016)上,以及与基准和最新的最新跟踪器相比,其卓越的性能清楚地证明了所提出框架的有效性。它提供了重新加权的知识作为潜在变量,用于确定来自辅助样本的每个相关性过滤器模板的影响。这样,基于转移学习的融合实现了两个组件之间的有效交互。在四个对象跟踪基准(OTB-2015,Temple-Color和VOT2015 / 2016)上,以及与基准和最新的最新跟踪器相比,其卓越的性能清楚地证明了所提出框架的有效性。它提供了重新加权的知识作为潜在变量,用于确定来自辅助样本的每个相关性过滤器模板的影响。这样,基于转移学习的融合实现了两个组件之间的有效交互。在四个对象跟踪基准(OTB-2015,Temple-Color和VOT2015 / 2016)上,以及与基准和最新的最新跟踪器相比,其卓越的性能清楚地证明了所提出框架的有效性。
更新日期:2020-03-06
down
wechat
bug