Triton Sediment User Manual

Triton Perspective Map

-- SeaClass User Guide --

By:
Tony M. Ramirez
September 2014

Triton Imaging Inc.

Engineering Office

2121 41st Avenue, Suite 211

Capitola, CA 95010

USA
831-722-7373
831-475-8446

[e-mail]

[e-mail]

© 2014 TRITON

This user guide is provided as a means to become familiar with TRITON’s software through an explanation of the

options available for classifying imagery. The user interface presented in this guide is subject to change to
accommodate software upgrades and revisions. While every precaution has been taken to eliminate errors in this
guide, TRITON assumes no responsibility for errors in this document.

Users of this document are required to have a valid license for Perspective and SeaClass in order to activate the

software. TRITON hereby grants licensees of TRITON’s software the right to reproduce this document for

internal use only.

Page ii

Table of Contents

1.0 SeaClass Module ................................................................................. 1

1.1 Supported Formats ............................................................................................................................................. 1

1.2 Classification Process .......................................................................................................................................... 1

1.3 Available Options ................................................................................................................................................ 1

2.0 SeaClass File Tree Options ..................................................................... 2

2.1 Tree Structure ..................................................................................................................................................... 2

2.2 Manual Training .................................................................................................................................................. 2

2.3 Neural Nets ......................................................................................................................................................... 3

2.4 Classification ....................................................................................................................................................... 4

2.0 SeaClass Process ................................................................................ 5

2.1 Prepare Data ....................................................................................................................................................... 5

2.1.1 Bottom Samples ........................................................................................................................................... 5

2.1.2 Load/Create Imagery ................................................................................................................................... 5

2.2 Create Training Set.............................................................................................................................................. 6

3.2 Neural Net Training ........................................................................................................................................... 11

3.3 Classify Bottom Types ....................................................................................................................................... 13

4.0 Edit Training Set ............................................................................... 16

5.0 Quick Classification ............................................................................ 19

6.0 SeaClass Exports ............................................................................... 20

Page iii

1.0 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.

1.1 Supported Formats

 .TMAP_MOZ (Perspective Sidescan mosaic)

 .DDS_VIF (Triton Map Visual Information File)

 .TIF (GeoTIFF)

The classification procedure operates on the above file formats, and works the same for
any of these file types.

1.2 Classification Process

Create Training Set: Using known bottom types at discreet locations, create the

training set.

Neural Net Training: This process uses the training set created in the previous step

to train the neural net.

Classify: The neural net is used to determine the bottom type throughout the image

or mosaic layer.

1.3 Available Options

Edit Training Set: This function allows users to edit an existing training set by adding

data points to existing classes or to add a new class.

Quick Classify: Allows users to get a preview of the classification results without

having to create the classification grid.

Exporting: Results from the classification process can be exported to a vector file or

to a GeoTiff.

Page 1

2.0 SeaClass File Tree Options

2.1 Tree Structure

The SeaClass layer contains three sub-layers as shown in the
image below:

Manual Training - where training data points are stored

Neural Nets - for displaying the neural nets generated

from the training data

Classification - includes the results of the classification

process

2.2 Manual Training

Right-clicking on the Manual Training layer or any of its sub­layers will give the following options:

Color: Available at the class file tree

level. Opens color dialog for
changing the color of the sample
point icons in the map view.

Display All On: Makes all samples in

the selected training set or the
selected sample type visible in the
Perspective map view.

Display All Off: Makes all samples in

the selected training set or the
selected sample type not visible in
the Perspective map view.

Train Neural Net: Initiates the second step in the

classification process using the training set created.

Edit Training Set: Allows user to make changes to training sets by adding or deleting

data points in a class (bottom type) or to add another class with new data points.

Page 2

Resample: If a new sample size was set when editing the training set, selecting this will

resample the training set at the new size.

Remove: Removes the selected layer from the project. This is available at the training

set layer and the class layer nodes.

Remove All: Removes all sub-layers from the current tree node.

Export: Allows users to save the SeaClass training set created.

Create: Launches the

Create Training Set

wizard.

Add: Adds an existing training set to the project and Map View.

Rename: Allows users to rename an existing training set that is in the file tree.

Info: Allows the user to view XML info for the selected file.

2.3 Neural Nets

Right-clicking on the Neural Nets layer or any of its sub-layers will give the following
options:

Move to Top: Moves the selected layer to

the first position within the “Neural
Nets” heading.

Move Up: Moves the selected layer above

the previous file within the “Neural
Nets” heading.

Move Down: Moves the selected layer

below the succeeding file with the “Neural Nets” heading.

Add: Adds an existing neural net to the project and Map View.

Remove: Removes the selected layer from the project.

Remove All: Removes all sub-layers from the current tree node.

Rename: Allows users to rename an existing neural net that is in the file tree.

Edit Color: Opens color dialog for changing the color of the neural net class.

Page 3

2.4 Classification

Right-clicking on the Classification layer or any of its sub-layers will give the following
options:

Color Settings: Opens following

window for changing background
color, opacity, and line drawing
settings.

Display All On: Makes all samples

in the selected training set or
the selected sample type visible
in the Perspective map view.

Display All Off: Makes all samples

in the selected training set or
the selected sample type not
visible in the Perspective map view.

Move to Top: Moves the selected layer to the first position within the “Classification”

heading.

Move Up: Moves the selected layer above the previous file within the “Classification”

heading.

Move Down: Moves the selected layer below the succeeding file with the

“Classification” heading.

Export: This will export the classification results to an AutoCAD DXF file.

Add: Adds an existing classification grid to the project and Map View.

Remove: Removes the selected layer from the project.

Info: Allows the user to view XML info for the selected file.

Zoom to Extents: Quick zoom option to zoom to full extent of selected layer.

Page 4

2.0 SeaClass Process

2.1 Prepare Data

2.1.1 Bottom Samples

One requirement for the classification process using SeaClass is
having bottom information to use for the training set. This
information can come from diver observations, video transects, or
classical sediment sampling programs.

Before beginning the classification process, it is very useful to load
the sample information into Perspective as
sample data in CSV files using Microsoft Excel or a text editor using
the required data format for Features outlined in:

Perspective_PointFeatures_Guide.pdf

available from our downloads webpage. Make one Feature CSV file
for each bottom type and load into unique File Tree groups. In the
example shown to the right, there are three
Sand, and Reef (BR stands for Barrett Reef), with several samples
loaded into each group from the CSV files containing the sample
information.

2.1.2 Load/Create Imagery

The other requirement for the classification process using SeaClass
is having an image to classify. This can be either a GeoTiff file or a
sidescan mosaic created in Perspective or with Isis/TritonMap.

Feature

Feature

files. Format the

groups: Fines,

Note that this imagery data does not have to be in the project during the first two steps
of the classification process. Creating the training set and the neural net are independent
from the imagery and can be added to the project at any time for classification.

If there is no bottom sample information, the user can pick points for the training set
directly from the imagery to be classified. In this case it is essential that the imagery is
either created in Perspective or loaded into Perspective before creating a Training Set so
the imagery can be used as part of the process.

Page 5