Preliminary Results of an Algorithm for Automatic Detection of Minelike Objects in Sidescan Sonar Images

PDF

Authors
  1. Fawcett, J.A.
Corporate Authors
Defence Research Establishment Atlantic, Dartmouth NS (CAN)
Abstract
In this paper we investigate the detection of possible targets in sidescan sonar images using the two-dimensional convolutions of filters with the sidescan image. The filters are designed to reflect the highlight/shadow features of targets. A high convolution value indicates a possible target. Two data sets, one from the SQS-511 sonar and one from a Klein 5000 sonar towed by an autonomous vehicle are analyzed. The results are encouraging and indicate that this method may provide a robust method for automated target detection.
Keywords
Convolutions;Highlight/shadow;Target identification;Classification algorithms;Target shapes;Automatic target detection
Report Number
DREA-TM-2000-013 — Technical Memorandum
Date of publication
01 Feb 2000
Number of Pages
34
DSTKIM No
CA001523
CANDIS No
513475
Format(s):
Hardcopy;Document Image stored on Optical Disk

Permanent link

Document 1 of 1

Date modified: