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

Constrained Superpixel Tracking.

Lijun Wang, Huchuan Lu, Ming-Hsuan Yang

    IEEE Transactions on Cybernetics
    |April 1, 2017
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel constrained graph labeling algorithm for visual tracking. The method effectively combines spatial, temporal, and appearance constraints for robust and accurate object tracking.

    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

    Aggregating global-scale pixel-wise forgery cues within a graph.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    DiMuS: Disentangled Multi-Signal Learning for Weakly Supervised Point-Based 3D Object Detection.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Visual-Textual Information-Driven Tactile Data Generation Method.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Class Sensitive Calibration and Discrepancy-Aware Synthesis for Semi-Supervised Medical Image Segmentation.

    IEEE journal of biomedical and health informatics·2026
    Same author

    Diffusion-based cross-staining feature transformation for whole slide image analysis: From H&E to IHC representation learning.

    Medical image analysis·2026
    Same author

    SD-ReID: View-Aware Stable Diffusion for Aerial-Ground Person Re-Identification.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    A New Human-Likeness and Comfort Index for Robot Movements Along Prescribed Paths.

    IEEE transactions on cybernetics·2026
    Same journal

    Robust Semiglobal and Global Stabilization for Nonlinear Normal Form Systems by Time-Varying Feedback.

    IEEE transactions on cybernetics·2026
    Same journal

    Adaptive Global Asymptotic Output Stabilization of Uncertain Nonlinear Systems Under Dynamic State/Input Quantization.

    IEEE transactions on cybernetics·2026
    Same journal

    Accelerated Distributed Gradient Tracking for Constrained Aggregative Optimization Over Time-Varying Digraphs.

    IEEE transactions on cybernetics·2026
    Same journal

    Small-Gain-Based Plug-and-Play Distributed Control Framework for DC Microgrids With Decentralized Reconfiguration.

    IEEE transactions on cybernetics·2026
    Same journal

    Prescribed-Time Impulsive Control of High-Order Integrator Systems.

    IEEE transactions on cybernetics·2026
    See all related articles

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Visual tracking is crucial for many applications.
    • Existing methods struggle with drastic appearance changes and complex scenes.
    • Robust appearance modeling and efficient spatial-temporal reasoning are key challenges.

    Purpose of the Study:

    • To propose a constrained graph labeling algorithm for robust visual tracking.
    • To integrate spatial, temporal, and appearance constraints for improved tracking accuracy.
    • To develop an algorithm that handles drastic appearance changes and facilitates online updates.

    Main Methods:

    • A constrained graph labeling algorithm is proposed, with nodes representing superpixels and edges encoding constraints.
    • Spatial smoothness is enforced using transductive learning on unlabeled superpixels.

    Related Experiment Videos

  • Appearance fitness and temporal smoothness constraints are developed for short- and long-term appearance modeling.
  • Induction and transduction methods are combined within the graph labeling framework.

    • Main Results:

    • The algorithm successfully integrates diverse constraints for effective visual tracking.
    • Foreground regions inferred by the graph labeling guide the tracking process.
    • Tracking results improve online updates by filtering contaminated training samples.
    • Evaluations demonstrate superior performance compared to state-of-the-art methods on challenging datasets.

    Conclusions:

    • The proposed constrained graph labeling algorithm offers a robust solution for visual tracking.
    • The integration of multiple constraints leads to improved accuracy and resilience.
    • The method shows significant potential for real-world visual tracking applications.