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

luvHarris: A Practical Corner Detector for Event-Cameras.

Arren Glover, Aiko Dinale, Leandro De Souza Rosa

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |December 15, 2021
    PubMed
    Summary

    This study introduces luvHarris, a novel corner detection method for event cameras. It achieves high accuracy and over 2.6x faster real-time performance than existing methods.

    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

    An event-based opto-tactile skin.

    Frontiers in neuroscience·2026
    Same author

    Cranioplasty complications in severe traumatic brain injury: implications of timing of surgery, implant material and incidence of vetriculomegaly versus Post-Traumatic hydrocephalus.

    Neurosurgical review·2025
    Same author

    Event-driven figure-ground organisation model for the humanoid robot iCub.

    Nature communications·2025
    Same author

    Editorial: Women in neuroengineering and neurotechnologies.

    Frontiers in neuroscience·2025
    Same author

    The neurobench framework for benchmarking neuromorphic computing algorithms and systems.

    Nature communications·2025
    Same author

    Reach&Grasp: a multimodal dataset of the whole upper-limb during simple and complex movements.

    Scientific data·2025

    Area of Science:

    • Computer Vision
    • Robotics
    • Event-based Sensing

    Background:

    • Event cameras offer advantages in dynamic scenes but require efficient processing.
    • Existing corner detection methods for event cameras lack sufficient accuracy or real-time performance for practical applications.
    • Unconstrained environments and random camera motion pose challenges for current algorithms.

    Purpose of the Study:

    • To develop a high-accuracy, real-time corner detection method for event cameras.
    • To improve upon the speed and robustness of state-of-the-art event-based corner detection.
    • To address the limitations of current methods in practical, unconstrained scenarios.

    Main Methods:

    • Introduced a novel "threshold ordinal event-surface" to simplify parameter tuning for Harris operations.

    Related Experiment Videos

  • Implemented the Harris algorithm with minimized computational load per event.
  • Optimized computationally intensive convolutions to run "as-fast-as-possible" based on available resources.

    • Main Results:

    • The proposed look-up event-Harris (luvHarris) method achieves practical, real-time, and robust corner detection.
    • luvHarris demonstrates over 2.6x speed improvement compared to current state-of-the-art methods.
    • The method maintains high accuracy suitable for high-resolution event cameras.

    Conclusions:

    • luvHarris offers a significant advancement in real-time event-based corner detection.
    • The novel event-surface and optimized Harris implementation provide a practical solution for dynamic vision tasks.
    • The approach is validated for its effectiveness and efficiency in real-world event camera applications.