Stereo Image Correspondence Methods for Efficient Hardware Implementation

Abstract

In this thesis, depth information extraction via ordinal measures for logical pattern correlation is investigated, along with matching techniques that translate well into hardware implementations. First, the ordinal correspondence metric is evaluated for complexity and performance using traditional correspondence matching techniques. The results show that the ordinal measures are very robust in stereo correspondence when paired with modest error handling techniques. Second, the ordinal measures are applied to an efficient dynamic programming matching algorithm to produce highquality disparity maps. It is shown that ordinal measures are demonstrably fast in software and that they can be adapted to an extremely fast hardware implementation to produce high quality disparity maps for very high resolution images in real time.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2010
Accession Number
ADA524718

Entities

People

  • Bradley J. Ulis

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Advanced Electronics
  • Autonomy
  • C4I
  • Materials and Manufacturing Processes
  • Sensors
  • Space

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Artificial Intelligence
  • Computational Complexity
  • Computer Programming
  • Computer Science
  • Computer Stereo Vision
  • Computer Vision
  • Computers
  • Dynamic Programming
  • Field Programmable Gate Arrays
  • High Resolution
  • Image Processing
  • Operating Systems
  • Pattern Recognition
  • Three Dimensional
  • United States Naval Academy

Readers

  • Computer Vision.
  • Psychometric Testing or Psychological Assessment.

Technology Areas

  • AI & ML