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 Video

Updated: Mar 12, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K

Moving Object Detection Using Tensor-Based Low-Rank and Saliently Fused-Sparse Decomposition.

Wenrui Hu, Yehui Yang, Wensheng Zhang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |November 17, 2016
    PubMed
    Summary

    This study introduces a novel tensor-based model for moving object detection. It effectively separates background and foreground using low-rank and sparse representations, outperforming existing methods in complex scenarios.

    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

    Surface reconstruction of metal halides for S-site shielding toward long-cycle all-solid-state lithium batteries.

    Chemical science·2026
    Same author

    Machine learning for prediction and experimental validation of hydrochar characteristics via co-hydrothermal carbonization of sewage sludge and pomelo peel.

    Bioresource technology·2026
    Same author

    A fully integrated microfluidic device for cell electrofusion and quick acquisition of hybridoma cells with high production of monoclonal antibody.

    Biosensors & bioelectronics·2026
    Same author

    Machine learning estimation of FVIII pharmacokinetic parameters in Chinese children with severe Hemophilia A.

    NPJ systems biology and applications·2026
    Same author

    Corrigendum to "Indirect estimation of pediatric reference interval via density graph deep embedded clustering" [Comput. Biol. Med. 169 (2024) 107852].

    Computers in biology and medicine·2026
    Same author

    Aging of Citri Reticulatae pericarpium: Flavonoid metabolite dynamics, fungal community succession, and functional analysis of key transformation strains.

    Food research international (Ottawa, Ont.)·2026

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Signal Processing

    Background:

    • Moving object detection is crucial for video analysis.
    • Existing methods struggle with complex scenarios and preserving spatio-temporal structures.
    • Low-rank and sparse representations offer a promising direction for background-foreground decomposition.

    Purpose of the Study:

    • To propose a novel tensor-based low-rank and sparse representation model for moving object detection.
    • To enhance the accuracy and robustness of moving object detection in complex video sequences.
    • To leverage the spatio-temporal structure of videos for improved decomposition.

    Main Methods:

    • Representing video sequences as three-way tensors to preserve space-time structure.
    • Employing tensor nuclear norm for low-rank background decomposition using circulant algebra.

    More Related Videos

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.4K

    Related Experiment Videos

    Last Updated: Mar 12, 2026

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    1.2K
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.4K
  • Utilizing a saliently fused-sparse regularizer (SFS) with 3D locally adaptive regression kernel (3D-LARK) for adaptive foreground constraints.
  • Incorporating spatio-temporal smoothness and motion saliency into the foreground regularizer.
  • Solving the model with a globally optimal guarantee.

    • Main Results:

    • The proposed model effectively decomposes video sequences into low-rank background and sparse foreground components.
    • The SFS regularizer, enhanced by 3D-LARK, adaptively constrains foreground with spatio-temporal smoothness and motion saliency.
    • Experiments demonstrate significant performance improvements over state-of-the-art methods on challenging datasets.
    • The method proves effective across a wide range of complex scenarios.

    Conclusions:

    • The proposed tensor-based low-rank and sparse representation model offers a robust and effective solution for moving object detection.
    • The novel SFS regularizer significantly enhances foreground extraction by incorporating geometric structure and motion saliency.
    • The method achieves superior performance compared to existing approaches, particularly in complex and challenging video environments.