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

Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement.

Shigang Yue1, F Claire Rind

  • 1School of Biology and Psychology, University of Newcastle upon Tyne, Newcastle upon Tyne NE1 7RU, UK. shigang.yue@ncl.ac.uk

IEEE Transactions on Neural Networks
|May 26, 2006
PubMed
Summary

A new lobula giant movement detector (LGMD) neural network model enhances object edge detection for reliable collision avoidance. This biologically inspired system effectively navigates complex environments without object recognition, demonstrating robust performance in real-time robotics.

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

vSTMD: Visual Motion Detection for Extremely Tiny Target at Various Velocities.

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

A bio-inspired research paradigm of collision perception neurons enabling neuro-robotic integration: the LGMD case.

Journal of the Royal Society, Interface·2026
Same author

Mechanistic Integration of Distal and Proximal Cues in the Rodent Entorhinal-Hippocampal Circuit: Insights From a Biorobotics Model.

The European journal of neuroscience·2026
Same author

I2Bot: an open-source tool for multi-modal and embodied simulation of insect navigation.

Journal of the Royal Society, Interface·2025
Same author

Editorial: Swarm neuro-robots with the bio-inspired environmental perception.

Frontiers in neurorobotics·2024
Same author

Recent advances in insect vision in a 3D world: looming stimuli and escape behaviour.

Current opinion in insect science·2024

Area of Science:

  • Neuroscience
  • Robotics
  • Computer Vision

Background:

  • The lobula giant movement detector (LGMD) neuron in locusts is crucial for detecting approaching objects.
  • Existing computational models struggle in unpredictable environments without specific object recognition.
  • There is a need for robust collision detection systems in complex, dynamic settings.

Purpose of the Study:

  • To propose a novel LGMD-based neural network for enhanced collision detection.
  • To introduce a feature enhancement mechanism for improved edge detection of colliding objects.
  • To evaluate the system's performance in complex backgrounds and real-time robotic applications.

Main Methods:

  • Development of an LGMD-based neural network incorporating a new feature enhancement mechanism.

Related Experiment Videos

  • Utilizing grouped excitation to enhance expanded edges of colliding objects.
  • Filtering isolated excitations caused by background details.

    • Main Results:

    • The proposed LGMD network demonstrated superior performance in complex backgrounds during offline tests.
    • Real-time robotics experiments confirmed reliable system operation across various conditions.
    • Robots successfully navigated arenas with structured surrounds and complex backgrounds using the LGMD network as the sole sensory input.

    Conclusions:

    • The novel LGMD-based neural network effectively enhances collision detection capabilities.
    • The feature enhancement mechanism successfully filters background noise and highlights relevant object edges.
    • The system offers a reliable and adaptable solution for robotic navigation in challenging, unpredictable environments.