Skip to content

Getting Started

Kait Frasier edited this page Apr 1, 2022 · 51 revisions

The DetEdit repository contains two dataset examples of odontocete acoustic data for testing and learning how to use the interface.

  1. Case Study: Sperm Whale
  2. Case Study: Dolphins' Species
  3. What Is The Next Step?

Sample DetEdit files can be found at Test datasets Drive folder.

Case Study: Sperm Whale (Physeter macrocephalus)

The following steps will guide you through an example of sperm whale detections and how to annotate embedded dolphin detections as false positive detections. You can get a quick view of the Editing tools that are available for annotating detections.

  1. Specify your data settings
  2. Launch the interface
  3. Scan bouts of detections
  4. Inspect acoustic parameters from batches of detections
  5. Annotate batches of detections as false positives
  6. Annotate batches of detections as true positives (misidentified)

1. Specify your data settings

An example data setting script to demonstrate the parameters used to annotate sperm whale acoustic data is provided in DetEdit\Settings folder.

Open spermwhaleSettings or use the Command Window in MATLAB as follows:

>> edit spermwhaleSettings

and modify the directory tpwsDir corresponding to your folder location:

tpwsDir = 'E:\detEditexamples\Spermwhale_Test_Set'; % identify  folder containing TPWS files

2. Launch the interface

Invoke the interface as follows:

>> detEdit(@spermwhaleSettings)

Progress information will be displayed in the Command Window and you will be asked to specify the Starting session, press 1 to start with the first bout.

Once the different panels of the interface are open, you can arrange them as you wish for better visualization.

brushing_typing

3. Scan bouts of detections

Once the interface is open, you can move from one bout to another by using the keyboard shortcut: space

brushing_move_window

4. Inspect acoustic parameters from batches of detections

Select batches of detections using the MATLAB's brushing tool as follows:

  • activate the brush by selecting Brush button Brush_icon_default.
  • select detections by flagging the area of interest (highlighted in yellow).
  • press y to display parameters of highlighted detections. Selected detections will be highlighted in black, as well as averaged sound pressure waveform and power spectra of the selected batch of detections.
  • press u again to update window and selection is removed.

brushing_highlight

5. Annotate batches of detections as false positives

A specified threshold for peak frequencies and RMS is displayed, which automatically annotates data lower than the specified values as false positive detections.

Annotate batches of detections as false positives using the MATLAB's brushing tool as follows:

  • activate the brush by selecting Brush button Brush_icon_default.
  • select detections by flagging the area of interest (highlighted in yellow).
  • press r to annotate selection as false positive, detections will be displayed in red as well as averaged sound pressure waveform and power spectra of the annotated detections. Detection times will be automatically saved in the corresponding *FD.mat file.

brushing_redflag

6. Annotate batches of detections as true positives (misidentified)

While brushing for false detections, few detections a the beginning of the bout have been annotated as false. It is possible to reverse the annotation to true positives as follows:

  • activate the brush by selecting Brush button Brush_icon_default.
  • select detections by flagging the area of interest (highlighted in yellow).
  • press g to annotate selection as true positive, detections will be displayed in blue again. Detection times will be automatically saved again in the corresponding *TD.mat file.

brushing_trueflag

Once the data has been annotated, detections can be cleaned or parsed out into sets using modDet or custom scripts. See End-to-End examples section for more details.

Case Study: Dolphins' Species

The following steps will guide you through an example of different species of dolphin detections and how to classify the different species using the Editing tools that are available for annotating and classifying detections.

  1. Specify your data settings
  2. Launch the interface
  3. Annotate batches of detections with the ID color code

1. Specify your data settings

An example data setting script to demonstrate the parameters used to annotate sperm whale acoustic data is provided in DetEdit\Settings folder.

Open dolphinSettings or use the Command Window in MATLAB as follows:

>> edit dolphinSettings

and modify the directory tpwsDir corresponding to your folder location:

tpwsDir = 'E:\detEditexamples\Dolphin_Test_Set'; % identify  folder containing TPWS files

2. Launch the interface

Invoke the interface as follows:

>> detEdit(@dolphinSettings)

3. Annotate batches of detections with ID color code

Select batches of detections using the MATLAB's brushing tool as follows:

  • activate the brush by selecting Brush button Brush_icon_default.
  • select detections by flagging the area of interest (highlighted in yellow).
  • press y to display parameters of highlighted detections. Selected detections will be highlighted in black, as well as averaged sound pressure waveform and power spectra of the selected batch of detections.
  • the previous step is repeated to inspect acoustic features from another batch of detections. Notice that the second selection has a different spectral shape.
  • select the color from the dropdown menu of the brushing tool: color_type9. See ID Color Legend plot for reference.
  • brush data and selection will be annotated as color type 9: color_type9 that corresponds to Stenella spp. species as following the ID color legend (shown in the image below). Start times and color type ID of the annotated detections will be stored automatically to ID.mat file.
  • select the color from the dropdown menu of the brushing tool: color_type2.
  • brush data and selection will be annotated as color type 2: color_type2 that corresponds to Dolphin, in this case, Risso's dolphin (Grampus griseus).

brushing_colors

Alternative, annotate detections with ID colors using the ID Labels code shortcuts:

  • activate the brush by selecting Brush button Brush_icon_default.
  • select detections by flagging the area of interest (highlighted in yellow).
  • press 9 to annotated as color type 9: color_type9 that corresponds to Stenella spp. species as following the ID color legend (shown in the image below). Start times and color type ID of the annotated detections will be stored automatically to ID.mat file.
  • select detections by flagging the area of interest (highlighted in yellow).
  • press 2 to annotated as color type 2: color_type2 that corresponds to Dolphin, in this case, Risso's dolphin (Grampus griseus).

brushing_colors_numbers

Alternatively, if using automated detectors that label different species acoustic detections, these detections can be evaluated by creating an ID.mat file using a custom script to display the labels in the interface as different ID color codes.

What Is The Next Step?

Familiarize yourself with the different functions and files used by the interface. See How it works to learn how to create the TPWS.mat and LTSA.mat files and the other capabilities that the interface offers you to evaluate your data. End-To-End Example are provided to guide you through the processing pipeline.