Jove
Visualize
Contact Us

Related Experiment Video

Updated: Jul 7, 2026

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes
06:25

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

Published on: February 23, 2024

Automatic target recognition by matching oriented edge pixels.

C F Olson1, D P Huttenlocher

  • 1Dept. of Comput. Sci., Cornell Univ., Ithaca, NY.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|January 1, 1997
PubMed
Summary

This study introduces efficient target recognition using edge maps and orientation data for complex shapes. It employs a modified Hausdorff measure to accurately locate targets in 3D space, reducing false alarms in infrared and intensity images.

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

Perceived mother-daughter relations in a pregnant and nonpregnant adolescent sample.

Adolescenceยท1984
See all related articles
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

Area of Science:

  • Computer Vision
  • Image Processing
  • Pattern Recognition

Background:

  • Accurate target recognition is challenging in complex environments, especially for small, irregularly shaped objects.
  • Existing methods often struggle with 3D object representation and efficient matching against large model catalogs.

Purpose of the Study:

  • To develop efficient and accurate techniques for target recognition in difficult domains.
  • To model 3D objects using 2D views and incorporate orientation data for improved recognition.
  • To minimize false alarms and enhance computational efficiency during object matching.

Main Methods:

  • Representing targets and images using edge maps with local orientation information.
  • Modeling 3D objects via a set of 2D views allowing for translation, rotation, and scaling.

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jul 7, 2026

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes
06:25

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

Published on: February 23, 2024

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • Utilizing a modified Hausdorff measure incorporating location and orientation for target detection.
  • Employing hierarchical cell decomposition of transformation space for efficient search pruning.
  • Developing methods for estimating and utilizing false alarm probability at runtime.

    • Main Results:

    • Demonstrated efficient and accurate target recognition in infrared and intensity images.
    • Successfully modeled 3D objects and their motion using 2D views and orientation.
    • Achieved efficient matching against object model catalogs by pruning transformation space.
    • Provided methods for maintaining low false alarm rates and ranking detection hypotheses.

    Conclusions:

    • The proposed edge-based approach with orientation information and a modified Hausdorff measure enables robust and efficient 3D target recognition.
    • Hierarchical decomposition and false alarm probability estimation significantly improve computational performance and reliability.
    • The techniques are effective for real-world applications, as shown by results in infrared and intensity imagery.