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

A matching algorithm based on hybrid matrices consisting of reference differences and disparities.

Ye-Peng Guan1, Wei-Kang Gu

  • 1Dept. of Information Science and Electronics Engineering, Zhejiang University, Hangzhou 310027, China. seugyp@sohu.com

Journal of Zhejiang University. Science
|October 21, 2004
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

Enhanced facial texture illumination normalization for face recognition.

Applied optics·2015
Same author

Structural compensation enhancement method for nonuniform illumination images.

Applied optics·2015
Same author

[A pilot study on the quality management system of in-vitro diagnostic reagents].

Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation·2006
Same author

[Studies on administration of in-vitro diagnostic reagents].

Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation·2005
Same author

A simple rectification method for linear multi-baseline stereovision system.

Journal of Zhejiang University. Science·2004

This study introduces an improved stereo matching algorithm that combines gray correlation with disparity gradient constraints for accurate feature point correspondence. The method enhances precision in stereo vision applications by refining initial matches.

Area of Science:

  • Computer Vision
  • Image Processing
  • Stereo Vision

Background:

  • Traditional gray correlation methods for stereo matching offer limited accuracy due to unilateral feature point analysis.
  • Existing techniques struggle to achieve unique and correct correspondence solely through basic gray correlation.

Purpose of the Study:

  • To develop a novel stereo matching algorithm that overcomes the limitations of the standard gray correlation technique.
  • To enhance the accuracy and uniqueness of feature point correspondence in stereo image pairs.

Main Methods:

  • Utilizing gray correlation to extract a coarse matching set (multi-peak set) of feature points.
  • Applying the disparity gradient limited constraint to optimize the initial multi-peak set.
  • Calculating correlations of hybrid matrices (reference differences and disparities) for unique correspondence determination.

Related Experiment Videos

  • Employing a iterative reference point strategy for comprehensive feature point processing.

    • Main Results:

    • The proposed algorithm successfully refines the multi-peak set, leading to unique matches.
    • Experimental results demonstrate the feasibility and accuracy of the enhanced stereo matching approach.
    • The method effectively determines unique correspondences by integrating multiple constraints.

    Conclusions:

    • The developed algorithm provides a more robust and accurate solution for stereo matching compared to traditional gray correlation.
    • The combination of gray correlation peaks and disparity gradient constraints significantly improves correspondence accuracy.
    • The iterative reference point method ensures complete and reliable feature matching across stereo images.