Seaclass, Lass, Odule – Triton Perspective User Manual
Page 183: Reate, Raining, 1 seaclass module, 2 create training set
175 |
P a g e
F e b r u a r y 2 0 1 1
8: SeaClass
8.1 SeaClass Module
SeaClass is an add-on to MosaicOne which allows users to classify sediment types based on a
neural net training set created from bottom sample information and select points or other
ground truth methods.
Supported Formats
.TMAP_MOZ (Perspective Sidescan mosaic)
.DDS_VIF (Triton Map Visual Information File)
.TIF (GeoTIFF)
The procedure works with the above file formats and is the same for any of these file types.
Classification Process
Create Training Set: Using known bottom types at discreet locations, the user can create the
training set. Details of the Create Training Set process are described in Section 8.2.
Neural Net Training: This process uses the training set created in the previous step to train
the neural net. Details of the Neural Net Training process are described in Section 8.4.
Classify: The neural net is used to determine the bottom type throughout the image or mosaic
layer. Details of the Classify process are described in Section 8.3.
Available Options
Edit Training Set: Allows the user to edit a training set. Details of the Edit Training Set
process are described in Section 8.5.
Quick Classify: Allows users to get a preview of the classification results without having to
create the classification grid. Details of the Quick Classification process are described in
Section 8.6.
8.2 Create Training Set
The first step in the classification process is to enter ground truth information in order to
generate a set of data points to be used in the neural net training process. This can originate
from multiple sources including bottom grab samples, diver inspections and video surveys,
and must include a location and bottom type information.