This example illustrates the class otb::MeanDifferenceImageFilter for detecting changes between pairs of images. This filter computes the mean intensity in the neighborhood of each pixel of the pair of images to be compared and uses the difference of means as a change indicator. These correspond to the near infrared band of two Spot acquisitions before and during a flood.




Spot images for change detection. Left: Before the flood. Middle: during the flood. Right: Result of the mean difference change detector.

Example usage:

./DiffChDet Input/SpotBefore.png Input/SpotAfter.png Output/DiffChDet.tif 3

Example source code (DiffChDet.cxx):

#include "otbMeanDifferenceImageFilter.h"
#include "otbImageFileReader.h"
#include "otbImageFileWriter.h"
#include "otbImage.h"
#include "itkUnaryFunctorImageFilter.h"
#include "itkAbsImageFilter.h"
#include "itkRescaleIntensityImageFilter.h"
#include "otbCommandProgressUpdate.h"

int main(int argc, char* argv[])

  if (argc < 5)
    std::cerr << "Usage: " << std::endl;
    std::cerr << argv[0] << " inputImageFile1 inputImageFile2  outputImageFile radius" << std::endl;
    return -1;

  // Define the dimension of the images
  const unsigned int Dimension = 2;

  // We start by declaring the types for the two input images, the
  // change image and the image to be stored in a file for visualization.
  using InternalPixelType = float;
  using OutputPixelType   = unsigned char;
  using InputImageType1   = otb::Image<InternalPixelType, Dimension>;
  using InputImageType2   = otb::Image<InternalPixelType, Dimension>;
  using ChangeImageType   = otb::Image<InternalPixelType, Dimension>;
  using OutputImageType   = otb::Image<OutputPixelType, Dimension>;

  // We can now declare the types for the readers and the writer.
  using ReaderType1 = otb::ImageFileReader<InputImageType1>;
  using ReaderType2 = otb::ImageFileReader<InputImageType2>;
  using WriterType  = otb::ImageFileWriter<OutputImageType>;

  // The change detector will give positive and negative values
  // depending on the sign of the difference. We are usually
  // interested only in the absolute value of the difference. For
  // this purpose, we will use the \doxygen{itk}{AbsImageFilter}. Also, before
  // saving the image to a file in, for instance, PNG format, we will
  // rescale the results of the change detection in order to use the full range
  // of values of the output pixel type.
  using AbsType      = itk::AbsImageFilter<ChangeImageType, ChangeImageType>;
  using RescalerType = itk::RescaleIntensityImageFilter<ChangeImageType, OutputImageType>;

  // The MeanDifferenceImageFilter is templated over
  // the types of the two input images and the type of the generated change
  // image.
  using FilterType = otb::MeanDifferenceImageFilter<InputImageType1, InputImageType2, ChangeImageType>;

  // The different elements of the pipeline can now be instantiated.
  ReaderType1::Pointer  reader1   = ReaderType1::New();
  ReaderType2::Pointer  reader2   = ReaderType2::New();
  WriterType::Pointer   writer    = WriterType::New();
  FilterType::Pointer   filter    = FilterType::New();
  AbsType::Pointer      absFilter = AbsType::New();
  RescalerType::Pointer rescaler  = RescalerType::New();

  const char* inputFilename1 = argv[1];
  const char* inputFilename2 = argv[2];
  const char* outputFilename = argv[3];

  // We set the parameters of the different elements of the pipeline.

  // The only parameter for this change detector is the radius of
  // the window used for computing the mean of the intensities.


  // We build the pipeline by plugging all the elements together.

  // Since the processing time of large images can be long, it is
  // interesting to monitor the evolution of the computation. In
  // order to do so, the change detectors can use the
  // command/observer design pattern. This is easily done by
  // attaching an observer to the filter.
  using CommandType = otb::CommandProgressUpdate<FilterType>;

  CommandType::Pointer observer = CommandType::New();
  filter->AddObserver(itk::ProgressEvent(), observer);