Robust Visual Tracking by Exploiting the Historical Tracker Snapshots

Li, Jiatong; Hong, Zhibin; Zhao, Baojun

doi:10.1109/iccvw.2015.82

Cited by 11 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Figure 11, we observed that the target in the MotorRolling sequence flipped in plane, and the scale also changed dramatically over time. The STRCF [31] and ASRCF [11] both lost the target, while our approach can successfully track the target among most of the frames and obtain relative high AUC score. Furthermore, our tracker achieves promising performance and is on par with the ATOM tracker.…”

Section: Qualitative Resultsmentioning

confidence: 93%

“…(MEEM) restoration scheme to address the model drift problem. Li et al [31] extended the MEEM to multi-expert in a collaborative way, instead of the independent entropy computation in MEEM. Similarly, Li et al [32] utilized the unified discrete graph to model the relationship of multi-expert, while the computation load of dynamic programming increased significantly with a larger number of experts.…”

Section: Zhang Et Al Proposed a Ensemble Tracker Based On Multi-expert Entropy Minimizationmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Spatial-Temporal Regularization for Correlation Filters Based Visual Object Tracking

Chen

Wang

2021

Symmetry

View full text Add to dashboard Cite

Recently, Discriminative Correlation Filters (DCF) have shown excellent performance in visual object tracking. The correlation for a computing response map can be conducted efficiently in Fourier domain by Discrete Fourier Transform (DFT) of inputs, where the DFT of an image has symmetry on the Fourier domain. To enhance the robustness and discriminative ability of the filters, many efforts have been devoted to optimizing the learning process. Regularization methods, such as spatial regularization or temporal regularization, used in existing DCF trackers aim to enhance the capacity of the filters. Most existing methods still fail to deal with severe appearance variations—in particular, the large scale and aspect ratio changes. In this paper, we propose a novel framework that employs adaptive spatial regularization and temporal regularization to learn reliable filters in both spatial and temporal domains for tracking. To alleviate the influence of the background and distractors to the non-rigid target objects, two sub-models are combined, and multiple features are utilized for learning of robust correlation filters. In addition, most DCF trackers that applied 1-dimensional scale space search method suffered from appearance changes, such as non-rigid deformation. We proposed a 2-dimensional scale space search method to find appropriate scales to adapt to large scale and aspect ratio changes. We perform comprehensive experiments on four benchmarks: OTB-100, VOT-2016, VOT-2018, and LaSOT. The experimental results illustrate the effectiveness of our tracker, which achieved a competitive tracking performance. On OTB-100, our tracker achieved a gain of 0.8% in success, compared to the best existing DCF trackers. On VOT2018, our tracker outperformed the top DCF trackers with a gain of 1.1% in Expected Average Overlap (EAO). On LaSOT, we obtained a gain of 5.2% in success, compared to the best DCF trackers.

show abstract

Section: Qualitative Resultsmentioning

confidence: 93%

Section: Zhang Et Al Proposed a Ensemble Tracker Based On Multi-expert Entropy Minimizationmentioning

confidence: 99%

Adaptive Spatial-Temporal Regularization for Correlation Filters Based Visual Object Tracking

Chen

Wang

2021

Symmetry

View full text Add to dashboard Cite

show abstract

“…Therefore, the correlation‐guided motion model can be represented as

q_{i} false(X_{t}^{i false(r + 1 false)} falsefalse| X_{t}^{i false(r false)} false) = ({, \begin{matrix} 1em4pt \\ \frac{1}{falsefalse| L_{t}^{i} falsefalse|}, & if X_{t}^{i false(r + 1 false)} \in L_{t}^{i} \\ 0, & otherwise . \end{matrix})

In detail, the target candidate set is generated as follows: since the CF updates each frame, it is prone to drift as the tracking time goes by. Therefore, we preserve both the current CF and its historical tracker snapshots to constitute a CF ensemble [29, 30]. At each time step, the local maxima of the CF ensemble response maps are generated using non‐maxima suppression as the initial candidates.…”

Section: Multi‐object Tracking Frameworkmentioning

confidence: 99%

“…In detail, the target candidate set is generated as follows: since the CF updates each frame, it is prone to drift as the tracking time goes by. Therefore, we preserve both the current CF and its historical tracker snapshots to constitute a CF ensemble [29,30]. At each time step, the local maxima of the CF ensemble response maps are generated using non-maxima suppression as the initial candidates.…”

Section: Correlation-guided Proposalmentioning

confidence: 99%

Correlation‐guided multi‐object tracking with correlation feature transfer

Zhao

Jiang

2019

IET Computer Vision

Self Cite

View full text Add to dashboard Cite

Here, the authors propose a correlation-guided Monte Carlo Markov chain (MCMC) solver to promote the efficiency for tracking multiple objects under recursive Bayesian filtering framework. Instead of randomly proposing the target location according to certain distribution, the authors' method guides the MCMC solver to sample among locations that the targets are more likely to appear. The high possible locations for each target are obtained using its corresponding response map by evaluating the correlation between the target appearance and its online model. Furthermore, the proposed tracking framework is natural to transfer the rich domain-specific offline correlation features into the target online model. With the calculation in the Fourier domain and the reversible jump strategy for MCMC, the correlation-guided method is able to track variable multiple objects with high efficiency. At the same time, the correlation feature transfer strategy is capable of improving tracking precision with easy offline training. The proposed method is evaluated by both the synthetic and real scenario videos. The experimental results demonstrate the effectiveness of the proposed method and its superior performance against its counterparts.

show abstract

“…Higher update rates capture the rapid target changes but is prone to occlusions, whereas slower update paces provide a long memory for the tracker to handle temporal target variations but lack the flexibility to accommodate permanent target changes. To this end, researchers try to combine long-and short-term memories [62] and role-back improper updates [57] or utilize different temporal snapshots of the classifier to overcome non-stationary distribution of the target's appearance [63]. This pipeline, however, was altered in some studies to introduce desired properties, e.g., to avoid label noise by merging sampling and labeling steps [15].…”

Section: Estimatingmentioning

confidence: 99%

Active Collaboration of Classifiers for Visual Tracking

Meshgi¹,

Oba²

2018

Human-Robot Interaction - Theory and Application

View full text Add to dashboard Cite

Recently, discriminative visual trackers obtain state-of-the-art performance, yet they suffer in the presence of different real-world challenges such as target motion and appearance changes. In a discriminative tracker, one or more classifiers are employed to obtain the target/nontarget label for the samples, which in turn determine the target's location. To cope with variations of the target shape and appearance, the classifier(s) are updated online with different samples of the target and the background. Sample selection, labeling, and updating the classifier are prone to various sources of errors that drift the tracker. In this study, we motivate, conceptualize, realize, and formalize a novel active co-tracking framework, step by step to demonstrate the challenges and generic solutions for them. In this framework, not only classifiers cooperate in labeling the samples but also exchange their information to robustify the labeling, improve the sampling, and realize efficient yet effective updating. The proposed framework is evaluated against state-of-the-art trackers on public dataset and showed promising results.

show abstract

Robust Visual Tracking by Exploiting the Historical Tracker Snapshots

Cited by 11 publications

References 30 publications

Adaptive Spatial-Temporal Regularization for Correlation Filters Based Visual Object Tracking

Adaptive Spatial-Temporal Regularization for Correlation Filters Based Visual Object Tracking

Correlation‐guided multi‐object tracking with correlation feature transfer

Active Collaboration of Classifiers for Visual Tracking

Contact Info

Product

Resources

About