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: Apr 1, 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

Kernelized Saliency-Based Person Re-Identification Through Multiple Metric Learning.

Niki Martinel, Christian Micheloni, Gian Luca Foresti

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |October 10, 2015
    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

    Validation of Synthetic Megavoltage Computed Tomography (MVCT) for Dose Calculation in Radiotherapy Treatment Planning.

    Cancers·2026
    Same author

    Real-world road damage dataset with potholes, cracks, and maintenance holes.

    Scientific reports·2026
    Same author

    Data-related Ablation for Reinforcing Deep Learning in Explaining Complex Phenomena.

    International journal of neural systems·2026
    Same author

    From Wearable Sensor Networks to Markerless Motion Capture for Instrumental-Based Biomechanical Risk Assessment in Lifting Activities.

    Sensors (Basel, Switzerland)·2025
    Same author

    Correction: A Benchmark Dataset for Radio Signal Image-based Person Re-Identification.

    Scientific data·2025
    Same author

    A Benchmark Dataset for Radio Signal Image-based Person Re-Identification.

    Scientific data·2025
    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
    Same journal

    GoP-based Quality Enhancement on Video Compression.

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

    Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

    Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

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

    This study introduces a novel kernelized saliency-based approach for person re-identification in non-overlapping camera systems. By mimicking human visual attention, it significantly improves recognition accuracy in challenging scenarios.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Person re-identification (re-ID) in non-overlapping multi-camera systems is a significant challenge for automated surveillance.
    • Human observers excel at re-ID by focusing on salient person details, a capability not yet fully replicated by machines.

    Purpose of the Study:

    • To develop a person re-identification method inspired by human visual attention mechanisms.
    • To improve the accuracy of person re-identification in challenging, non-overlapping multi-camera environments.

    Main Methods:

    • A kernelized graph-based approach was employed to identify salient regions of a person's appearance.
    • These salient regions were used to weight feature extraction for person representation.
    • A pairwise multiple metric learning framework was utilized, combining visual features with and without saliency information.

    Related Experiment Videos

    Last Updated: Apr 1, 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
  • Non-Euclidean metrics learned for each feature were fused for final person re-identification.

    • Main Results:

    • The proposed kernelized saliency-based method demonstrated superior performance compared to state-of-the-art approaches.
    • Achieved a rank 1 correct recognition rate of 42.41% on the VIPeR dataset.
    • Evaluated on four public benchmark datasets, confirming its effectiveness.

    Conclusions:

    • The integration of saliency information significantly enhances person re-identification capabilities.
    • The proposed method offers a promising direction for improving automated surveillance and security systems.