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

Robust physics-based analysis of thermal and visual imagery

N Nandhakumar1

  • 1Department of Electrical Engineering, University of Virginia, Charlottesville 22903-2442.

Journal of the Optical Society of America. A, Optics, Image Science, and Vision
|November 1, 1994
PubMed
Summary

This study enhances physics-based object recognition using thermal and visual imagery. New methods improve analysis of temporal data and robustly estimate object properties, advancing multisensor fusion for reliable feature extraction.

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

Interpretations: How to use faecal elastase testing.

Archives of disease in childhood. Education and practice edition·2010
Same author

A harmonic retrieval framework for discontinuous motion estimation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Robust thermophysics-based interpretation of radiometrically uncalibrated IR images for ATR and site change detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·1997
Same author

Spatiotemporal approach for time-varying global image motion estimation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·1996
Same author

Automatic tachycardia recognition.

Pacing and clinical electrophysiology : PACE·1984

Area of Science:

  • Computer Vision
  • Physics-based Modeling
  • Multisensor Fusion

Background:

  • Existing physics-based approaches analyze thermal and visual imagery for object recognition.
  • These models utilize the principle of conservation of energy for feature computation.

Purpose of the Study:

  • To extend existing physics-based methods for intersensory perception.
  • To analyze temporal sequences of registered thermal and visual imagery.
  • To formulate a robust linear-regression task for estimating object physical properties.

Main Methods:

  • Analyzing temporal sequences of spatially registered thermal and visual imagery.
  • Employing an energy-exchange model to formulate a linear-regression task.
  • Implementing a statistically robust scheme to minimize outlier sensitivity.

Related Experiment Videos

Main Results:

  • The extended model enables simultaneous analysis of temporal thermal and visual data.
  • A robust estimation of physical object properties is achieved.
  • The approach provides reliable physics-based features despite segmentation and registration errors.

Conclusions:

  • The extensions enhance physics-based object recognition capabilities.
  • The robust scheme improves reliability in multisensor fusion applications.
  • This work offers a more comprehensive approach to intersensory perception and object classification.