TY - GEN
T1 - A POMDP for multi-view target classification with an autonomous underwater vehicle
AU - Myers, Vincent
AU - Williams, David P.
PY - 2010
Y1 - 2010
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/78651286576
UR - https://www.scopus.com/pages/publications/78651286576#tab=citedBy
U2 - 10.1109/OCEANS.2010.5664609
DO - 10.1109/OCEANS.2010.5664609
M3 - Conference contribution
AN - SCOPUS:78651286576
SN - 9781424443321
T3 - MTS/IEEE Seattle, OCEANS 2010
BT - MTS/IEEE Seattle, OCEANS 2010
T2 - MTS/IEEE Seattle, OCEANS 2010
Y2 - 20 September 2010 through 23 September 2010
ER -