Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Correlation Filter Learning Toward Peak Strength for Visual Tracking.

Yao Sui, Guanghui Wang, Li Zhang

    IEEE Transactions on Cybernetics
    |April 20, 2017
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Development and validation of survival nomograms in elder triple-negative invasive ductal breast carcinoma patients.

    Expert review of anticancer therapy·2024
    Same author

    Macrophage-Related Gene Signatures for Predicting Prognosis and Immunotherapy of Lung Adenocarcinoma by Machine Learning and Bioinformatics.

    Journal of inflammation research·2024
    Same author

    [The correlation between preoperative neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio and postoperative recurrence of chronic rhinosinusitis].

    Lin chuang er bi yan hou tou jing wai ke za zhi = Journal of clinical otorhinolaryngology head and neck surgery·2024
    Same author

    Levitated 2D manipulation on dielectric metasurface by the tuning of polarization states.

    Optics letters·2024
    Same author

    Clinical considerations of CDK4/6 inhibitors in HER2 positive breast cancer.

    Frontiers in oncology·2024
    Same author

    Oxidation of p-toluenesulfonic acid fractionated hybrid Pennisetum by different methods for carboxylated nanocellulose preparation: The evaluation of efficiency and sustainability.

    Bioresource technology·2024
    Same journal

    Relaxed Stability Conditions for Model Predictive Control of Hybrid Dynamical Systems Using Hybrid Recurrent Neural Networks.

    IEEE transactions on cybernetics·2026
    Same journal

    An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models.

    IEEE transactions on cybernetics·2026
    Same journal

    A Quantum Self-Attention Neural Network Model on Quantum Circuits.

    IEEE transactions on cybernetics·2026
    Same journal

    Semi-Explicit Solution of Some Discrete-Time Higher-Order-Cost Mean-Field-Type Control.

    IEEE transactions on cybernetics·2026
    Same journal

    A Novel One-Step Small Object Detector for Autonomous Aerial Vehicles.

    IEEE transactions on cybernetics·2026
    Same journal

    Online Data-Driven-Based Optimal Output Tracking Control Without Initial Stabilizing Policy.

    IEEE transactions on cybernetics·2026
    See all related articles

    This study introduces a new visual tracking method using correlation filters that adaptively remove distracting features. This approach enhances correlation response peak strength for more stable and accurate object tracking.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Signal Processing

    Background:

    • Traditional visual tracking methods often use all target and background features.
    • Distractive features like occlusion and deformation can lead to unstable tracking.
    • Existing correlation filter learning methods may not effectively handle these challenges.

    Purpose of the Study:

    • To propose a novel algorithm for learning correlation filters that adaptively eliminate distractive features.
    • To enhance the peak strength of the correlation response for improved discriminative capability.
    • To achieve more stable and accurate visual tracking performance.

    Main Methods:

    • Developed a novel algorithm for correlation filter learning.
    • Imposed an elastic net constraint on the filter to adaptively eliminate distractive features.

    Related Experiment Videos

  • Introduced a new peak strength metric to evaluate the learned filter's discriminative capability.

    • Main Results:

    • The proposed approach adaptively eliminates distractive features, strengthening the correlation response peak.
    • The new peak strength metric effectively measures filter discriminative capability.
    • Experimental results show improved discriminative performance compared to previous methods.

    Conclusions:

    • The novel correlation filter learning approach effectively strengthens the peak of the correlation response.
    • The proposed tracker demonstrates superior performance on challenging visual tracking benchmarks.
    • This method offers a more robust solution for visual object tracking, outperforming state-of-the-art techniques.