In:
The Journal of the Acoustical Society of America, Acoustical Society of America (ASA), Vol. 136, No. 4_Supplement ( 2014-10-01), p. 2112-2112
Abstract:
Strategies for the automated detection and classification of underwater unexploded ordnance (UXO), based upon structural acoustics derived features, are currently being transitioned to autonomous underwater vehicle based sonar systems. The foundation for this transition arose, in part, from extensive laboratory investigations conducted at the Naval Research Laboratory. We discuss the evolution of structural acoustic based methodologies, including research into understanding the free-field scattering response of UXO and the coupling of these objects, under varying stages of burial, to water-saturated sediments. In addition to providing a physics-based understanding of the mechanisms contributing to the scattering response of objects positioned near the sediment–water interface, this research supports the validation of three-dimensional finite-element-based models for large-scale structural–acoustics problems. These efforts have recently culminated with the successful classification of a variety of buried UXO targets using a numerically trained relevance vector machine (RVM) classifier and the discrimination of these targets, under various burial orientations, from several objects representing both natural and manmade clutter. We conclude that this demonstration supports the transition of structural acoustic processing methodologies to maritime sonar systems for the classification of challenging UXO targets. [Work supported by ONR and SERDP.]
Type of Medium:
Online Resource
ISSN:
0001-4966
,
1520-8524
Language:
English
Publisher:
Acoustical Society of America (ASA)
Publication Date:
2014
detail.hit.zdb_id:
1461063-2
Permalink