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

Extraction of visual motion and optic flow.

Kunihiko Fukushima1

  • 1Kansai University, Takatsuki, Osaka 569-1095, Japan. fukushima@m.ieice.org

Neural Networks : the Official Journal of the International Neural Network Society
|February 19, 2008
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

Efficient IntVec: High recognition rate with reduced computational cost.

Neural networks : the official journal of the International Neural Network Society·2019
Same author

Introduction.

International journal of neural systems·2018
Same author

Margined winner-take-all: New learning rule for pattern recognition.

Neural networks : the official journal of the International Neural Network Society·2017
Same author

Training multi-layered neural network neocognitron.

Neural networks : the official journal of the International Neural Network Society·2013
Same author

Artificial vision by multi-layered neural networks: neocognitron and its advances.

Neural networks : the official journal of the International Neural Network Society·2012
Same author

Increasing robustness against background noise: visual pattern recognition by a neocognitron.

Neural networks : the official journal of the International Neural Network Society·2011
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a novel neural network for extracting local velocity from retinal images, enhancing previous optic flow models. The new mechanism improves the analysis of visual motion perception and object tracking.

Area of Science:

  • Computational neuroscience
  • Computer vision
  • Artificial intelligence

Background:

  • Previous work proposed a neural network for optic flow extraction based on the vector field hypothesis.
  • The prior model assumed local velocities were already extracted, limiting its scope.

Purpose of the Study:

  • To propose a new mechanism for extracting local velocity from retinal images.
  • To integrate this new mechanism into an existing neural network for optic flow analysis.
  • To enhance the understanding of visual motion perception.

Main Methods:

  • A hierarchical multilayered neural network architecture was developed.
  • Retinal X- and Y-cells were used to extract spatial and temporal contrast.
  • V1 cells (S-, C-, V-cells), MT cells, and MST cells were incorporated to process visual information.

Related Experiment Videos

Main Results:

  • The network successfully extracts local velocities from retinal images.
  • MT cells compute relative velocities between adjacent visual fields.
  • MST cells integrate MT cell responses to extract specific optic flows like rotation and expansion/contraction.

Conclusions:

  • The proposed mechanism effectively extracts local velocity, forming a more complete optic flow model.
  • The architecture allows for the extraction of complex optic flows through hierarchical processing.
  • Receptive field properties in MT cells can be modulated to generate diverse optic flow patterns.