Underwater Unexploded Ordnance (UXO) Classification Using a Matched Subspace Classifier With Adaptive Dictionaries

Autor:	Yinghui Zhao, Mahmood R. Azimi-Sadjadi, Steven G. Kargl, John J. Hall, Kevin L. Williams
Rok vydání:	2019
Předmět:	Reverberation business.industry Computer science Mechanical Engineering Supervised learning Ocean Engineering Pattern recognition Sonar Data modeling Unexploded ordnance Synthetic aperture sonar Artificial intelligence Electrical and Electronic Engineering Underwater Target strength business
Zdroj:	IEEE Journal of Oceanic Engineering. 44:739-752
ISSN:	2373-7786 0364-9059
DOI:	10.1109/joe.2018.2835538
Popis:	This paper is concerned with the development of a system for the discrimination of military munitions and unexploded ordnance (UXO) in shallow underwater environments. Acoustic color features corresponding to calibrated target strength as a function of frequency and look angle are generated from the raw sonar returns for munition characterization. A matched subspace classifier (MSC) is designed to discriminate between different classes of detected contacts based upon the spectral content of the sonar backscatter. The system is exclusively trained using model-generated sonar data and then tested using the measured Target and Reverberation Experiment 2013 (TREX13) data sets collected from a synthetic aperture sonar system in a relatively low-clutter environment. A new in situ supervised learning method is also developed to incrementally train the MSC using a limited number of labeled samples drawn from the TREX13 data sets. The classification results of the MSC are presented using standard performance metrics, such as receiver operating characteristic curve and confusion matrices.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::8622b65170217f2c6a7ea940278e1f86 https://doi.org/10.1109/joe.2018.2835538 Zobrazit plný text záznamu