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

On motion detection through a multi-layer neural network architecture.

Antonio Fernández-Caballero1, José Mira, Miguel A Fernández

  • 1Departamento de Informática, Universidad de Castilla-La Mancha, Escuela Politecnia Superior, Campus Universitario, 02071 Albacete, Spain. caballer@info-ab.uclm.es

Neural Networks : the Official Journal of the International Neural Network Society
|March 12, 2003
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

For Me, Quality of Life Is When I Get Through the Day Without Thinking: I Won't Make It: A Participatory Qualitative Study of Health-Related Quality of Life in Rare Liver Diseases.

Health expectations : an international journal of public participation in health care and health policy·2026
Same author

A VR obstetric simulator based on the Novint Falcon haptic device: development and evaluation.

International journal of medical informatics·2026
Same author

Fifteen Years of Patient Experience with Hospital Food in a Spanish Long-Term Care Hospital.

Nutrients·2026
Same author

Mathematical Modeling of Photoplethysmography: Model Assessment and Validation.

Cardiovascular engineering and technology·2026
Same author

What outcomes matter to patients having surgical treatment for symptomatic hallux valgus? : a systematic review of qualitative studies.

The bone & joint journal·2026
Same author

Associations of Muscle Mass, Strength, and Power with Falls Among Active Community-Dwelling Older Adults.

Diagnostics (Basel, Switzerland)·2026

This study introduces a novel neural network model for detecting non-rigid objects in image sequences. The model utilizes lateral interaction in accumulative computation and biological inspiration for enhanced object detection.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Biologically Inspired Computing

Background:

  • Object detection in image sequences is challenging, especially for non-rigid objects.
  • Existing methods may struggle with detecting objects based on the motion of their individual parts.

Purpose of the Study:

  • To present a novel neural network model for detecting non-rigid objects using part motion.
  • To introduce a biologically inspired multi-layer neural architecture for this task.

Main Methods:

  • Developed a neural network model featuring lateral interaction in accumulative computation.
  • Designed a four-layer architecture for segmentation, computation, redistribution, and fusion.
  • Introduced an associated learning algorithm for lateral interaction in accumulative computation.

Related Experiment Videos

Main Results:

  • The proposed model effectively detects non-rigid objects from part motion in image sequences.
  • Demonstrated the system's usefulness through illustrative examples.
  • The multi-layer architecture performs key functions including segmentation and object fusion.

Conclusions:

  • The lateral interaction in accumulative computation model offers a promising approach for non-rigid object detection.
  • The biologically inspired architecture provides a robust framework for analyzing motion in image sequences.
  • The system shows potential for various applications requiring dynamic object recognition.