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: Jun 27, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Object segmentation from motion discontinuities and temporal occlusions--a biologically inspired model.

Cornelia Beck1, Thilo Ognibeni, Heiko Neumann

  • 1Institute for Neural Information Processing, University of Ulm, Ulm, Germany. cornelia.beck@uni-ulm.de

Plos One
|December 2, 2008
PubMed
Summary

This study introduces a novel model for object detection using optic flow, improving motion boundary detection by integrating motion discontinuities and occlusion cues. The model enhances object segmentation by combining these elements, inspired by primate visual cortex mechanisms.

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

Dynamic sensor adaptation based on efferent feedback for adaptive bio-inspired sound source localization.

Frontiers in neuroscience·2026
Same author

A model of thalamo-cortical interaction for incremental binding in mental contour-tracing.

PLoS computational biology·2025
Same author

Teaching deep networks to see shape: Lessons from a simplified visual world.

PLoS computational biology·2024
Same author

Canonical circuit computations for computer vision.

Biological cybernetics·2023
Same author

Listen to the Brain-Auditory Sound Source Localization in Neuromorphic Computing Architectures.

Sensors (Basel, Switzerland)·2023
Same author

Computational principles of neural adaptation for binaural signal integration.

PLoS computational biology·2020

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Visual Perception

Background:

  • Optic flow is a critical cue for object detection, enabling perception through kinetic boundaries.
  • Human vision utilizes motion discontinuities and temporal occlusions for object recognition, even without other shape cues.

Purpose of the Study:

  • To develop a robust model for detecting motion boundaries and object occlusion using optic flow.
  • To improve object segmentation by integrating mechanisms inspired by the human visual system.

Main Methods:

  • A novel computational model integrating mechanisms from visual areas V1, MT, and MSTl.
  • Separate detection mechanisms for motion discontinuities and occlusion regions based on neural response properties.
  • Biologically inspired architecture with feedback connections for information integration.

Related Experiment Videos

Last Updated: Jun 27, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Main Results:

  • The model achieves robust detection of motion boundaries by combining motion discontinuity and occlusion detection.
  • Mutual interactions between discontinuity and occlusion detection significantly improve kinetic boundary detection.
  • Successful testing with both artificial and real-world motion sequences.

Conclusions:

  • A new model effectively uses optic flow for detecting motion discontinuities and object occlusion.
  • Combining these cues enhances object segmentation, with potential applications in other models.
  • The model aligns with neurophysiological findings and demonstrates robust performance.