Learning Scale-Adaptive Tight Correlation Filter for Object Tracking

@article{Zhang2020LearningST,
  title={Learning Scale-Adaptive Tight Correlation Filter for Object Tracking},
  author={Shunli Zhang and Wei Lu and Weiwei Xing and Li Zhang},
  journal={IEEE Transactions on Cybernetics},
  year={2020},
  volume={50},
  pages={270-283}
}
In this paper, we propose a novel tracking method by formulating tracking as a correlation filtering as well as a ridge regression problem. First, we develop a tight correlation filter-based tracking framework from the signal detection perspective. In this formulation, the correlation filter is set as the same size as the target, which can make full use of the relations of the adjacent image patches and effectively exclude the influence of the background. Specifically, we point out that the… 
Multi-pattern correlation tracking
A Multi-Information Fusion Correlation Filters Tracker
TLDR
Results from extensive experiments show that the proposed multi-information fusion correlation filter tracker, with only directional gradient histogram (HOG) and color name (CN) features, performs favorably against the state-of-the-art trackers in terms of tracking precision, tracking success rate, tracking accuracy, and A-R rank.
Multi-Channel Feature Dimension Adaption for Correlation Tracking
TLDR
Adimension adaption correlation filters (DACF) is proposed, which adopts the multi-channel deep CNN features to obtain a discriminative sample appearance model, resisting the background clutters, and tackles the issue of over-fitting.
A KCF-Based Incremental Target Tracking Method With Constant Update Speed
TLDR
The proposed IKPCA-KCF tracker is competitive with state-of-the-art trackers on eight challenging video datasets and solves the tracking stability problem.
Cascaded Correlation Refinement for Robust Deep Tracking
TLDR
A cascaded correlation refinement approach that cascades multiple stages of correlation refinement to progressively refine target localization so that the localized object could be used to learn an accurate on-the-fly model for improving the reliability of model update.
Target Tracking Method Based on Adaptive Structured Sparse Representation With Attention
TLDR
The proposed target tracking method based on adaptive structured sparse representation with attention, under the framework of particle filtering, has a strong performance when dealing with motion blur, fast motion, partial occlusion and fast motion in target tracking.
Object tracking with collaborative extreme learning machines
TLDR
A novel collaborative discriminative model based on extreme learning machine (ELM) for object tracking that can achieve comparable performance to many state-of-the-art tracking approaches is proposed.
ESTHER: Joint Camera Self-Calibration and Automatic Radial Distortion Correction From Tracking of Walking Humans
TLDR
This paper presents a novel framework for camera self-calibration and automatic radial distortion correction that starts with the reliable human body segmentation that is facilitated by robust object tracking and uses an evolutionary optimization scheme to optimize the camera parameters and the distortion coefficients.
Fuzzy Least Squares Support Vector Machine With Adaptive Membership for Object Tracking
TLDR
A novel tracking method based on fuzzy least squares support vector machine with adaptive membership (FLS-SVM-AM) is proposed, which addresses the issue of fixed membership in existing methods and can better measure the importance of the training samples.
...
...

References

SHOWING 1-10 OF 68 REFERENCES
Robust Visual Tracking using 1 Minimization
TLDR
This paper proposes a robust visual tracking method by casting tracking as a sparse approximation problem in a particle filter framework and introduces a dynamic template update scheme that keeps track of the most representative templates throughout the tracking procedure.
Robust visual tracking using ℓ1 minimization
  • Xue MeiHaibin Ling
  • Computer Science
    2009 IEEE 12th International Conference on Computer Vision
  • 2009
TLDR
This paper proposes a robust visual tracking method by casting tracking as a sparse approximation problem in a particle filter framework and introduces a dynamic template update scheme that keeps track of the most representative templates throughout the tracking procedure.
A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration
TLDR
This paper presents a very appealing tracker based on the correlation filter framework and suggests an effective scale adaptive scheme to tackle the problem of the fixed template size in kernel correlation filter tracker.
Robust object tracking via sparsity-based collaborative model
TLDR
A robust appearance model that exploits both holistic templates and local representations is proposed and the update scheme considers both the latest observations and the original template, thereby enabling the tracker to deal with appearance change effectively and alleviate the drift problem.
Scalable Kernel Correlation Filter with Sparse Feature Integration
TLDR
A fast scalable solution based on the Kernalized Correlation Filter (KCF) framework that integrates the fast HoG descriptors and Intel's Complex Conjugate Symmetric (CCS) packed format to boost the achievable frame rates.
High-Speed Tracking with Kernelized Correlation Filters
TLDR
A new kernelized correlation filter is derived, that unlike other kernel algorithms has the exact same complexity as its linear counterpart, which is called dual correlation filter (DCF), which outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite being implemented in a few lines of code.
Transfer Learning Based Visual Tracking with Gaussian Processes Regression
TLDR
This paper directly analyze this probability of target appearance as exponentially related to the confidence of a classifier output using Gaussian Processes Regression (GPR), and introduces a latent variable to assist the tracking decision.
Robust Object Tracking with Online Multiple Instance Learning
TLDR
It is shown that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks.
Tracking-Learning-Detection
  • Zdenek Kalal
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2012
TLDR
A novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection, and develops a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: P-expert estimates missed detections, and N-ex Expert estimates false alarms.
Visual object tracking using adaptive correlation filters
TLDR
A new type of correlation filter is presented, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame, which enables the tracker to pause and resume where it left off when the object reappears.
...
...