Spatial stochastic models for seabed object detection

Brian R. Calder, Laurie M. Linnett, D. R. Carmichael

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

We introduce two statistical models designed to detect discrete objects in sidescan SONAR which consider complimentary approaches to the problem. The first considers a complex textural model for the objects and implements detection through a dual hypothesis on texture class presence, while the second implements a complex Gibbs field model of the image and utilizes prior knowledge of typical object morphologies to support its detection rate. The models are demonstrated on examples of different seabed sediments and object types, and are shown to be reliable in operation. The common theme of the two models is use of spatial context in analysis, which, we argue, is a very powerful technique for improving the flexibility and reliability of any analysis system.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Pages172-182
Number of pages11
Volume3079
Publication statusPublished - 1997
EventDetection and Remediation Technologies for Mines and Minelike Targets II - Orlando, FL, USA
Duration: 21 Apr 199724 Apr 1997

Conference

ConferenceDetection and Remediation Technologies for Mines and Minelike Targets II
CityOrlando, FL, USA
Period21/04/9724/04/97

Fingerprint Dive into the research topics of 'Spatial stochastic models for seabed object detection'. Together they form a unique fingerprint.

  • Cite this

    Calder, B. R., Linnett, L. M., & Carmichael, D. R. (1997). Spatial stochastic models for seabed object detection. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 3079, pp. 172-182)