NICE_SemSeg/semseg/SemanticSegmentation.h

/**
* @file SemanticSegmentation.h
* @brief abstract interface for semantic segmentation algorithms
* @author Erik Rodner
* @date 03/19/2009

*/
#ifndef SEMANTICSEGMENTATIONINCLUDE
#define SEMANTICSEGMENTATIONINCLUDE

#include <vector>
#include "core/image/MultiChannelImage3DT.h"
#include "vislearning/cbaselib/MultiDataset.h"
#include "vislearning/cbaselib/LocalizationResult.h"
#include "vislearning/cbaselib/CachedExample.h"
#include "vislearning/cbaselib/Example.h"


namespace OBJREC
{

/** abstract interface for semantic segmentation algorithms */
class SemanticSegmentation
{

protected:
  /** accessible class names and information about
      number of classes etc. */
  const ClassNames *classNames;

  /** enum type for imagetype */
  enum
  {
    IMAGETYPE_RGB = 0,
    IMAGETYPE_GRAY
  };

  /** whether to load images with color information */
  int imagetype;

public:

  /** simple constructor */
  SemanticSegmentation ();

  /** constructor
      @param conf global settings
      @param classNames this ClassNames object while be stored as a attribute
  */
  SemanticSegmentation ( const NICE::Config *conf,
                         const ClassNames *classNames );

  /** simple destructor */
  virtual ~SemanticSegmentation();

  /** classification function (has to be overloaded by all subclasses)
   * @param imgData image data
   * @param segresult result of the semantic segmentation with a label for each pixel
   * @param probabilities multi-channel image with one channel for each class and
   *        corresponding probabilities for each pixel
   * @param filelist filename list of images that represent slices of a stack
   */
  virtual void classify ( NICE::MultiChannelImage3DT<double> & imgData,
                          NICE::MultiChannelImageT<double> & segresult,
                          NICE::MultiChannelImage3DT<double> & probabilities,
                          const std::vector<std::string> & filelist ) = 0;

  /** training function (has to be overloaded by all subclasses)
   * @param md the data set
   */
  virtual void train ( const MultiDataset * md ) = 0;

  /**
   * collect information about the depth of 3d images
   * @param *Files a labeled set of data
   * @param depthVec output of depth values
   * @param run3dseg whether slice counting is necessary or not
   */
  void getDepthVector ( const LabeledSet *Files, std::vector<int> & depthVec, const bool run3dseg );

  /**
   * convert different datatypes
   */
  void convertVVectorToExamples ( NICE::VVector &feats,OBJREC::Examples &examples, std::vector<int> &label );
  void convertExamplesToVVector ( NICE::VVector &feats,OBJREC::Examples &examples, std::vector<int> &label );
  void convertExamplesToLSet ( OBJREC::Examples &examples, OBJREC::LabeledSetVector &lvec );
  void convertLSetToExamples ( OBJREC::Examples &examples, OBJREC::LabeledSetVector &lvec );
  void convertLSetToSparseExamples ( OBJREC::Examples &examples, OBJREC::LabeledSetVector &lvec );

  /**
   *load image slices into a single MCI3DT
   */
  void make3DImage ( const std::vector<std::string> & filelist,
                     NICE::MultiChannelImage3DT<double> & imgData );

  /**
   * @brief show a probability map for a given class
   * @param prob  class probabilites for each pixel
   * @param cl    class number
   */
  void getProbabilityMap( const NICE::MultiChannelImage3DT<double> & prob );

};


} // namespace

#endif