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

A neuromorphic depth-from-motion vision model with STDP adaptation.

Zhijun Yang1, Alan Murray, Florentin Wörgötter

  • 1Department of Computer Science, Nanjing Normal University, Nanjing 210097, China. zhijun.yang@ed.ac.uk

IEEE Transactions on Neural Networks
|March 29, 2006
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

Joint Associations of Plasma Nutritional Biomarkers and Uterine Fibroids with Hypertensive Disorders of Pregnancy.

medRxiv : the preprint server for health sciences·2026
Same author

PriMAT: Robust multi-animal tracking of primates in the wild.

PloS one·2026
Same author

Surgical protocol for precise and high-throughput viral injections in rhesus monkey brain.

STAR protocols·2026
Same author

Kinematic modulation across the ontogenetic transition to active social engagement.

Early human development·2026
Same author

A pipeline to characterize spinal cord pathology in neurological disorders combining magnetic resonance microscopy and histopathology.

Communications medicine·2026
Same author

Analyzing gaze and hand movement patterns in leader-follower interactions during a time-continuous cooperative manipulation task.

Frontiers in psychology·2026
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a novel depth-from-motion vision model using leaky integrate-and-fire (LIF) neurons for edge detection and depth recovery. The model encodes depth through spike timing correlations, enhanced by spike-timing-dependent plasticity for robustness.

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Robotics

Background:

  • Depth perception is crucial for autonomous systems.
  • Traditional depth recovery methods often require complex computations or multiple cameras.
  • Biologically inspired models offer alternative approaches to visual processing.

Purpose of the Study:

  • To develop a simplified, biologically plausible model for depth-from-motion.
  • To utilize leaky integrate-and-fire (LIF) neurons for edge detection and depth estimation.
  • To enhance model robustness using spike-timing-dependent plasticity.

Main Methods:

  • Employing LIF neurons to detect irradiance edges in optical flow fields.
  • Encoding depth information through the timing of neuronal spikes and synaptic transmission.

Related Experiment Videos

  • Implementing spike-timing-dependent plasticity to mitigate errors from spurious edge propagation.
  • Evaluating the algorithm on synthetic and real-world image sequences.

    • Main Results:

    • Demonstrated successful edge detection and 2D depth recovery using the proposed model.
    • Showcased depth encoding through spike correlations and time-of-travel information transfer.
    • Validated the algorithm's robustness against noise and inaccuracies via synaptic adaptation.

    Conclusions:

    • The proposed LIF neuron-based model offers an efficient and robust approach to depth-from-motion.
    • Spike-timing correlations provide a viable mechanism for encoding depth in artificial vision systems.
    • The model's principles are suitable for implementation in analog very large scale integrated (aVLSI) circuits.