Abstract

Bathymetric data depicts the geomorphology of the seabottom and allows characterization of spatial distributions of apparent benthic habitats. The variability of seafloor topography can be defined as a texture. This prompts for the application of well developed image processing techniques for automatic delineation of regions with clucially different physiographic characteristics. In the present paper histograms of biologically motivated invariant image attributes are used for characterization of local geomorphological feahires. This technique can be naturally applied in a range of spatial scales. Local feature vectors are then submitted to a procedure which divides the set into a number of clusters each representing a distinct type of the seafloor. Prior knowledge about benthic habitat locations allows the use of supervised classification, by training a Suppolt Vector Machine on a chosen data set, and then applying the developed model to a full set. The classification method is shown to perform well on the multibeam echosounder (MBES) data from Piscataqua River, New Hampshire, USA.

Publication Date

2003

Journal or Conference Title

International Symposium on Signal Processing and Its Applications (SPIA)

Volume

1

Pages

529-532

Conference Date

Jul 1 - 4, 2003

Publisher Place

Paris, France

Publisher

IEEE

Digital Object Identifier (DOI)

10.1109/ISSPA.2003.1224756

Document Type

Conference Proceeding

Share

COinS