Share Email Print
cover

Proceedings Paper

Mine detection using model-trained multiresolution neural networks and variational methods
Author(s): William G. Szymczak; Weiming Guo
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Even under ideal conditions side-scan sonar (SSS) images of targets can vary greatly depending on the target range and orientation, even if their geometries are identical. This complicates target classification algorithms since typically only a small samples of targets are available for training purposes. This under-representation of targets can cause missed classifications and a higher false alarm ratio in the presence of clutter. This problem is addressed by using a priori information about the targets as well as the imaging system embedded in a model for simulating target images. These simulated target images can be added to the training set for a more complete target representation. Another important aspect of this research includes the use of multiple channels extracted from the images using a multi- resolution wavelet decomposition. This multi-resolution analysis is used to first provide for an efficient detection strategy, by filtering the images over the lower resolution channels. Furthermore, providing target features at different scales improves the performance of the neural network classifier. The dependence of the classifier on local image enhancement provided by total variation minimization and Mumford-Shah segmentation is also studied.

Paper Details

Date Published: 2 August 1999
PDF: 11 pages
Proc. SPIE 3710, Detection and Remediation Technologies for Mines and Minelike Targets IV, (2 August 1999); doi: 10.1117/12.357078
Show Author Affiliations
William G. Szymczak, Naval Research Lab. (United States)
Weiming Guo, SFA, Inc. (United States)


Published in SPIE Proceedings Vol. 3710:
Detection and Remediation Technologies for Mines and Minelike Targets IV
Abinash C. Dubey; James F. Harvey; J. Thomas Broach; Regina E. Dugan, Editor(s)

© SPIE. Terms of Use
Back to Top