Clutter Reduction for ASW using Automatic Aural Classification with a Coherent Source – FY2010 Report

Authors
  1. Murphy, S.M.
  2. Hines, P.C.
Corporate Authors
Defence R&D Canada - Atlantic, Dartmouth NS (CAN)
Abstract
This report presents the results from the second year of a three year research grant from the US Office of Naval Research (ONR). The project’s aim is to develop a robust classifier using aural-based features that can discriminate active sonar target echoes from unwanted clutter echoes. A secondary objective is to develop an integrated tracker-classifier methodology with a prototype implementation in the Integrated Tracker and Aural Classifier (ITAC) software to demonstrate the potential for improvement over conventional kinematic trackers. The role of signal-to-noise ratio (SNR) in echo classification is also considered. During the first year of the project, an experiment was conducted in NRV ALLIANCE as part of the NURC Clutter09 sea trial. This enabled temporal robustness of the aural classifier to be examined by training the classifier using data collected during a 2007 field trial (Clutter07) and testing on data collected during Clutter09. In classifying the Clutter09 echoes, a performance metric of AROC = 0.903 was achieved, which is indicative of a very successful, and temporally robust classifier. In order to support the second objective (ITAC), an echo repeater was towed by ITN LEVANZO to approximate a target during the Clutter09 sea trial. This data was used to test a classifier-tracker integration algorithm. In the algorithm, the contact-track association weighting for the tracking algorithm is adjusted based on the classifier decision; in the limit, th
Report Number
DRDC-ATLANTIC-ECR-2010-206 — External Client Report
Date of publication
01 Oct 2010
Number of Pages
31
DSTKIM No
CA038503
CANDIS No
538569
Format(s):
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: