A POMDP for multi-view target classification with an autonomous underwater vehicle

Vincent Myers, David P. Williams

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

12 Scopus citations

Abstract

A partially observable Markov decision process (POMDP) is proposed to perform multi-view classification of underwater objects. The model allows one to adaptively determine which additional views of an object would be most beneficial for reducing classification uncertainty. Acquiring additional views is made possible by employing a sonar-equipped autonomous underwater vehicle (AUV) for data collection. The POMDP model is validated using real synthetic aperture sonar (SAS) data collected at sea, with promising results. The approach provides an elegant way to fully exploit multi-view information in a methodical manner.

Original languageEnglish (US)
Title of host publicationMTS/IEEE Seattle, OCEANS 2010
DOIs
StatePublished - 2010
EventMTS/IEEE Seattle, OCEANS 2010 - Seattle, WA, United States
Duration: Sep 20 2010Sep 23 2010

Publication series

NameMTS/IEEE Seattle, OCEANS 2010

Other

OtherMTS/IEEE Seattle, OCEANS 2010
Country/TerritoryUnited States
CitySeattle, WA
Period9/20/109/23/10

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Ocean Engineering

Fingerprint

Dive into the research topics of 'A POMDP for multi-view target classification with an autonomous underwater vehicle'. Together they form a unique fingerprint.

Cite this