w2qcref::CombineSmartMean Class Reference

Inheritance diagram for w2qcref::CombineSmartMean:

w2qcref::Postprocessor List of all members.

Detailed Description

postprocesses the precip confidence field by computing a local mean, but taking into account the distribution of high confidences in either direction.

Author:
Lakshman
Version:
Id
w2img_Postprocessor.h,v 1.9 2009/06/02 20:18:01 lakshman Exp


Public Member Functions

 CombineSmartMean (float not_precip=0.25, float def_precip=0.75)
 Pass in thresholds for when we should consider the probabilites "definite".
virtual ~CombineSmartMean ()
virtual void doPostprocess (const code::Image< float > &expanded_input, code::PolarGrid &output, const code::Image< float > &expanded_refmax, int half_size, int full_size, float edge_threshold)
 sub-classes over-ride this method.
void postprocess (code::PolarGrid &grid, code::Image< float > &refmax)
 postprocesses the input field, replacing its data values.
void setHalfSize (int hsize)
 change default from 2
void setEdgeThreshold (float edge)
 change default threshold for precip from 0.
void useBlobInformation (const code::Image< float > &refmax, code::PolarGrid &grid, const code::Image< int > &labels)
 Use the label information about regions.
virtual void clear ()

Static Public Member Functions

static void setBoostingDirectory (const std::string &dir)
 During NN training, polar grids with boosting information will be written out to this directory.

Protected Member Functions

void writeBoostingProduct (const code::PolarGrid &example, const code::Image< int > &labels, const std::vector< bool > &marginal)


Constructor & Destructor Documentation

w2qcref::CombineSmartMean::CombineSmartMean ( float  not_precip = 0.25,
float  def_precip = 0.75 
) [inline]

Pass in thresholds for when we should consider the probabilites "definite".

virtual w2qcref::CombineSmartMean::~CombineSmartMean (  )  [inline, virtual]


Member Function Documentation

virtual void w2qcref::Postprocessor::clear (  )  [virtual, inherited]

virtual void w2qcref::CombineSmartMean::doPostprocess ( const code::Image< float > &  expanded_input,
code::PolarGrid &  output,
const code::Image< float > &  expanded_refmax,
int  half_size,
int  full_size,
float  edge_threshold 
) [virtual]

sub-classes over-ride this method.

The expanded_input has wrapped radials.

Implements w2qcref::Postprocessor.

void w2qcref::Postprocessor::postprocess ( code::PolarGrid &  grid,
code::Image< float > &  refmax 
) [inherited]

postprocesses the input field, replacing its data values.

Can also correct the refmax for atroicious values that should not be added back by connectivity-based tests.

static void w2qcref::Postprocessor::setBoostingDirectory ( const std::string &  dir  )  [inline, static, inherited]

During NN training, polar grids with boosting information will be written out to this directory.

If this method is not called, no boosted products will be written out (assumed to be in runtime mode).

void w2qcref::Postprocessor::setEdgeThreshold ( float  edge  )  [inline, inherited]

change default threshold for precip from 0.

This value is used to decide edges etc.

void w2qcref::Postprocessor::setHalfSize ( int  hsize  )  [inline, inherited]

change default from 2

void w2qcref::Postprocessor::useBlobInformation ( const code::Image< float > &  refmax,
code::PolarGrid &  grid,
const code::Image< int > &  labels 
) [inherited]

Use the label information about regions.

void w2qcref::Postprocessor::writeBoostingProduct ( const code::PolarGrid &  example,
const code::Image< int > &  labels,
const std::vector< bool > &  marginal 
) [protected, inherited]


Generated on Fri May 4 13:40:25 2012 for WDSS-IIw2algs by  doxygen 1.4.7