Automatic interpretation of sonar imagery using qualitative feature matching

David M. Lane, John P. Stoner

Research output: Contribution to journalArticle

Abstract

A system capable of carrying out classifications of observed objects based on available features is used to determine feature measures invariant to changes in sonar setting, object position/orientation and noise character. Invariance is achieved through selection of threshold values used to map numerical feature values from the image data of these qualitative measures descriptions are maintained as examples to be matched with available object description for recognition. Descriptions based on the stated variables are presented showing an overall success of 86%.

Original languageEnglish
Pages (from-to)391-405
Number of pages15
JournalIEEE Journal of Oceanic Engineering
Volume19
Issue number3
DOIs
Publication statusPublished - Jul 1994

Fingerprint Dive into the research topics of 'Automatic interpretation of sonar imagery using qualitative feature matching'. Together they form a unique fingerprint.

  • Cite this