Package rawDeepLearningClassifier.segmenter

Class SegmenterProcess

java.lang.Object

PamguardMVC.PamProcess

rawDeepLearningClassifier.segmenter.SegmenterProcess

All Implemented Interfaces:

PamObserver, ProcessAnnotator

public class SegmenterProcess
extends PamProcess

Acquires raw sound data and then sends off to a deep learning classifier.

Author:

Jamie Macaulay

Field Summary

Fields inherited from class PamguardMVC.PamProcess

outputDataBlocks, parentDataBlock, processName, sampleRate

Constructor Summary

Constructors

Constructor	Description
SegmenterProcess(DLControl pamControlledUnit, PamDataBlock parentDataBlock)

Method Summary

Modifier and Type	Method	Description
ArrayList	getCompatibleDataUnits()	A list of data block class types which are compatible as parent data blocks for the PamProcess.
SegmenterGroupDataBlock	getSegmenteGroupDataBlock()
SegmenterDataBlock	getSegmenterDataBlock()	Get the segmenter data block.
void	masterClockUpdate(long milliSeconds, long sampleNumber)
void	newClickData(PamDataUnit pamRawData)	Process new click data.
void	newClipData(PamDataUnit pamRawData)	Process new clip data.
void	newData(PamDataUnit pamRawData)
void	newData(PamObservable obs, PamDataUnit pamRawData)
boolean	newGroupData(PamDataUnit detection)	A new detection data unit i.e.
void	newRawData(PamDataUnit unit, double[] rawDataChunk, int iChan)	Take a raw sound chunk of data and segment into discrete groups.
void	newRawData(PamDataUnit unit, double[] rawDataChunk, int iChan, int rawSampleSize, int rawSampleHop, boolean forcesave)	Take a raw sound chunk of data and segment into discrete groups.
void	newRawDataUnit(PamDataUnit pamRawData)	A new raw data unit.
void	pamStart()	Called for each process to tell it to start (may not be necessary for processes which are listening for data anyway).
void	pamStop()	Stops the process.
void	prepareProcess()	Called for each process before any of them receive the PamStart command
void	setFirstClockUpdate(long startTime)	Set the first clock update which helps the segmenter work out where to start segmenting from.
void	setupProcess()	called for every process once the system model has been created.
void	setupSegmenter()	Set up the DL process.

Methods inherited from class PamguardMVC.PamProcess

absMillisecondsToSamples, absSamplesToMilliseconds, addData, addMultiPlexDataBlock, addOutputDataBlock, changedThreading, clearOldData, createAnnotations, destroyProcess, dumpBufferStatus, flushDataBlockBuffers, getAncestorDataBlock, getAnnotation, getChainPosition, getCpuPercent, getFrequencyRange, getLastSourceNotificationObject, getLastSourceNotificationType, getMuiltiplexDataBlock, getNumAnnotations, getNumMuiltiplexDataBlocks, getNumOutputDataBlocks, getObserverName, getObserverObject, getOfflineData, getOfflineData, getOutputDataBlock, getOutputDataBlocks, getPamControlledUnit, getParentDataBlock, getParentDataBlocks, getParentProcess, getProcessCheck, getProcessName, getRawSourceDataBlock, getRawSourceDataBlock, getRequiredDataHistory, getSampleRate, getSourceDataBlock, getSourceProcess, hasOutputDatablock, isCanMultiThread, isExternalProcess, isMultiplex, makePamProcess, noteNewSettings, notifyModelChanged, prepareProcessOK, processNewBuoyData, receiveSourceNotification, relMillisecondsToSamples, relSamplesToMilliseconds, removeAllDataBlocks, removeAllMultiPlexDataBlocks, removeMultiPlexDataBlock, removeObservable, removeOutputDatablock, resetDataBlocks, saveViewerData, setCanMultiThread, setExternalProcess, setMultiplex, setParentDataBlock, setParentDataBlock, setProcessCheck, setProcessName, setSampleRate, toString, updateData

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Details

SegmenterProcess

public SegmenterProcess(DLControl pamControlledUnit,
 PamDataBlock parentDataBlock)

Method Details

prepareProcess

public void prepareProcess()

Description copied from class: PamProcess

Called for each process before any of them receive the PamStart command

Overrides:

prepareProcess in class PamProcess

getCompatibleDataUnits

public ArrayList getCompatibleDataUnits()

A list of data block class types which are compatible as parent data blocks for the PamProcess. This can return null, e.g. in the case of Acquisition process.

Overrides:

getCompatibleDataUnits in class PamProcess

Returns:

a list of PamDataBlock sub class types which can be used as parent data blocks for the process.

setupProcess

public void setupProcess()

called for every process once the system model has been created. this is a good time to check out and find input data blocks and similar tasks.

Overrides:

setupProcess in class PamProcess

setupSegmenter

public void setupSegmenter()

Set up the DL process.

newData

public void newData(PamObservable obs,
 PamDataUnit pamRawData)

Overrides:

newData in class PamProcess

newData

public void newData(PamDataUnit pamRawData)

newGroupData

public boolean newGroupData(PamDataUnit detection)

A new detection data unit i.e. this is only if we have detection data which is being grouped into segments.

Parameters:

detection - - the whistle data unit.

masterClockUpdate

public void masterClockUpdate(long milliSeconds,
 long sampleNumber)

Specified by:

masterClockUpdate in interface PamObserver

Overrides:

masterClockUpdate in class PamProcess

newRawDataUnit

public void newRawDataUnit(PamDataUnit pamRawData)

A new raw data unit.

Parameters:

pamRawData - - PAM raw data.

obs - - the PAM observable

newClipData

public void newClipData(PamDataUnit pamRawData)

Process new clip data.

Parameters:

pamRawData - - the new raw data unit

obs - - the PAM observable

newClickData

public void newClickData(PamDataUnit pamRawData)

Process new click data.

Parameters:

pamRawData -

obs - - the PAM observable

newRawData

public void newRawData(PamDataUnit unit,
 double[] rawDataChunk,
 int iChan)

Take a raw sound chunk of data and segment into discrete groups. This handles many situations e.g. where the segment is much larger than the raw data or where the segment is much small than each rawDataChunk returning multiple segments.

Parameters:

unit - - the data unit which contains relevant metadata on time etc.

rawDataChunk - - the sound chunk to segment extracted form the data unit.

iChan - - the channel that is being segmented

newRawData

public void newRawData(PamDataUnit unit,
 double[] rawDataChunk,
 int iChan,
 int rawSampleSize,
 int rawSampleHop,
 boolean forcesave)

Take a raw sound chunk of data and segment into discrete groups. This handles many situations e.g. where the segment is much larger than the raw data or where the segment is much small than each rawDataChunk returning multiple segments.

Parameters:

unit - - the data unit which contains relevant metadata on time etc.

rawDataChunk - - the sound chunk extracted from the data unit.

iChan - - the channel that is being segmented

rawSampleSize - - the segment size in samples i.e. the size of the segmenting window.

rawSampleHop - - the segment hop in samples i.e. how far the window jumps for each segment.

forceSave - - make sure that all data is passed into the buffers and do not wait for the next data unit. This is used to make sure that discrete chunks have their full number of segments saved.

pamStart

public void pamStart()

Description copied from class: PamProcess

Called for each process to tell it to start (may not be necessary for processes which are listening for data anyway).

Specified by:

pamStart in class PamProcess

pamStop

public void pamStop()

Description copied from class: PamProcess

Stops the process.

Specified by:

pamStop in class PamProcess

getSegmenterDataBlock

public SegmenterDataBlock getSegmenterDataBlock()

Get the segmenter data block. This holds raw chunks of data to be sent to the deep learning classifier.

Returns:

the segmenter data block.

getSegmenteGroupDataBlock

public SegmenterGroupDataBlock getSegmenteGroupDataBlock()

setFirstClockUpdate

public void setFirstClockUpdate(long startTime)

Set the first clock update which helps the segmenter work out where to start segmenting from.

Parameters:

startTime - - the start time in millis.