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: May 6, 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

1.3K

Topology-Preserving Deep Hashing for Ultrafast Drone-Dominated Object Detection.

Luming Zhang, Guifeng Wang, Zhiming Wang

    IEEE Transactions on Neural Networks and Learning Systems
    |May 4, 2026
    PubMed
    Summary

    This study introduces a fast deep hashing framework for object detection in drone images. The method robustly identifies objects across scales and altitudes, even with low-quality data.

    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

    Sex differences in the predictive value of insulin resistance surrogate indicators for prediabetes among Chinese adults aged 18-45 years: a multicenter cohort study.

    Frontiers in endocrinology·2026
    Same author

    The HD-Zip IV gene ZmHB118 is required for basal endosperm transfer layer formation and maternal-to-filial nutrient allocation during maize seed filling.

    The Plant journal : for cell and molecular biology·2026
    Same author

    Impact of adjuvant breast radiotherapy on the risk and the survival of second primary lung cancer: a large population-based study.

    Japanese journal of clinical oncology·2026
    Same author

    Non-redundant functions of three CRM proteins in mitochondrial group II intron splicing and maize seed development.

    Journal of genetics and genomics = Yi chuan xue bao·2026
    Same author

    High-throughput screening of EGFR/Ca<sup>2+</sup> signaling modulators in cardiac hypertrophy using a tetrahedral DNA nanostructure-based hESC platform.

    Journal of pharmaceutical analysis·2026
    Same author

    EMM-Det: Energy-Efficient Multidrone Tiny Object Detection by Memory-Enhanced Spiking Neural Networks.

    IEEE transactions on neural networks and learning systems·2026

    Area of Science:

    • Artificial Intelligence
    • Computer Vision
    • Machine Learning

    Background:

    • Drones (unmanned aerial vehicles) are increasingly used in AI systems.
    • Efficient object detection in drone imagery presents unique challenges due to varying viewpoints and altitudes.
    • Existing methods may struggle with low-quality images and noisy labels.

    Purpose of the Study:

    • To develop a novel deep hashing framework for rapid object detection from drone-captured images.
    • To enable view- and altitude-invariant multiscale object discovery.
    • To enhance robustness against low-quality images and contaminated semantic labels.

    Main Methods:

    • A deep hashing framework utilizing graphlet construction to encode object topological structures.
    • Binary matrix factorization (MF) for hierarchical semantic exploitation, incorporating hash code learning, denoising, and adaptive graph updating.

    More Related Videos

    Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
    08:16

    Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

    Published on: October 24, 2025

    926

    Related Experiment Videos

    Last Updated: May 6, 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

    1.3K
    Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
    08:16

    Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

    Published on: October 24, 2025

    926
  • Manifold-regularized feature selection for discriminative deep hash codes.

    • Main Results:

    • The proposed method achieves competitive speed and accuracy in object discovery from drone images.
    • Demonstrated robustness to low-quality drone pictures and potentially contaminated semantic labels through collaborative $l_{F}$ and $l_{1}$ norms.
    • Effective multiscale object discovery in a view- and altitude-invariant manner.

    Conclusions:

    • The novel deep hashing framework offers a fast and accurate solution for object detection in drone imagery.
    • The method's ability to handle topological structures and noise makes it suitable for real-world drone applications.
    • Experimental validation on multiple datasets confirms the framework's effectiveness.