Using wavelet analysis to classify and segment sonar signals scattered from underwater sea beds

$61.20 plus tax (Refund Policy)

Buy Article:

Abstract:

This work is concerned with the automatic characterization and classification of sea-bed sediments of using wavelet transform techniques to analyse the incoming one-dimensional signals from both sidescan and sidescan bathymetric sonars. This method studies the sum of energies at different scales of the wavelet transform of the signal then uses these sums as features to classify different types of sediment. The method uses both dyadic and discrete wavelet transforms, and several types of wavelet. The results are presented as scatter plots with wavelet-window energy sums as the axes. These sums are then given to a neural network for classification. Three datasets were provided, one sidescan sonar dataset and two sidescan bathymetric sonar datasets. The method is also tried on the same sediment type (mud) from the two sidescan bathymetric sonar datasets. Wavelet energies were also used to find the boundary between two different sediment types in the one-dimensional sidescan sonar signals. Compared to only using properties from the power spectrum to classify sediments the method provides the user with an efficient tool to observe features of sediments in both time and scale. It is a fast method that can be applied online, and presents good rates of correct classification.

Document Type: Research Article

DOI: http://dx.doi.org/10.1080/0143116021000035012

Affiliations: Department of Engineering Science University of Oxford Parks Road Oxford OX1 3PJ UK louis, Email: pjp@robots.ox.ac.uk

Publication date: November 1, 2003

More about this publication?
Related content

Share Content

Access Key

Free Content
Free content
New Content
New content
Open Access Content
Open access content
Subscribed Content
Subscribed content
Free Trial Content
Free trial content
Cookie Policy
X
Cookie Policy
ingentaconnect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more