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

Semantic-based surveillance video retrieval.

Weiming Hu1, Dan Xie, Zhouyu Fu

  • 1National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China. wmhu@nlpr.ia.ac.cn

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|April 5, 2007
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

Chemotherapy With or Without Anti-EGFR Agents in Left- and Right-Sided Metastatic Colorectal Cancer: An Updated Meta-Analysis.

Journal of the National Comprehensive Cancer Network : JNCCN·2019
Same author

Zscan4c activates endogenous retrovirus MERVL and cleavage embryo genes.

Nucleic acids research·2019
Same author

Kinesin family member C1 accelerates bladder cancer cell proliferation and induces epithelial-mesenchymal transition via Akt/GSK3β signaling.

Cancer science·2019
Same author

MSI2-TGF-β/TGF-β R1/SMAD3 positive feedback regulation in glioblastoma.

Cancer chemotherapy and pharmacology·2019
Same author

METTL3 facilitates tumor progression via an m<sup>6</sup>A-IGF2BP2-dependent mechanism in colorectal carcinoma.

Molecular cancer·2019
Same author

Association between suicide and multiple sclerosis: An updated meta-analysis.

Multiple sclerosis and related disorders·2019
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

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

Semantic Frame Interpolation.

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

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

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

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces a semantic-based video retrieval framework for visual surveillance. It effectively bridges the semantic gap by learning activity models from motion trajectories for enhanced video indexing and querying.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Information Retrieval

Background:

  • Visual surveillance generates vast video data, necessitating efficient indexing and retrieval.
  • Current video retrieval systems face a semantic gap between user needs and system understanding.
  • Visual surveillance platforms offer opportunities for semantic-based video retrieval research.

Purpose of the Study:

  • To propose a novel semantic-based video retrieval framework tailored for visual surveillance.
  • To address the semantic gap in video content representation and retrieval.
  • To enable semantic-level access to video clips and individual objects.

Main Methods:

  • Developed a cluster-based tracking algorithm to extract motion trajectories.
  • Employed hierarchical clustering of trajectories using spatial and temporal information to learn activity models.

Related Experiment Videos

  • Implemented a hierarchical semantic indexing and retrieval structure for object activities.

    • Main Results:

    • The framework supports diverse queries: keywords, multiple objects (considering succession, simultaneity, and order), and sketch-based trajectory matching.
    • Effectiveness and efficiency were validated in a crowded traffic scene.
    • Learned activity models automatically inherit semantic descriptions, enabling semantic-level access.

    Conclusions:

    • The proposed framework successfully enables semantic-based video retrieval in visual surveillance.
    • The hierarchical approach enhances the understanding and accessibility of complex activities within video data.
    • The system demonstrates practical utility for indexing and querying large-scale surveillance video databases.