Package boofcv.factory.feature.detect.intensity

Class FactoryIntensityPoint

java.lang.Object
boofcv.factory.feature.detect.intensity.FactoryIntensityPoint
public class FactoryIntensityPoint extends Object
Provides intensity feature intensity algorithms which conform to the GeneralFeatureIntensity interface.
See Also:

  • Constructor Details

    • FactoryIntensityPoint

      public FactoryIntensityPoint()

  • Method Details

    • fast

      public static <I extends ImageGray<I>, D extends ImageGray<D>> GeneralFeatureIntensity<I,D> fast(int pixelTol, int minCont, Class<I> imageType)
      Feature intensity for Fast corner detector. See FastCornerDetector for more details.
      Type Parameters:
      I - Input image type.
      D - Derivative type.
      Parameters:
      pixelTol - How different pixels need to be to be considered part of a corner. Image dependent. Try 20 to start.
      minCont - Minimum number of continue pixels in a circle for it ot be a corner. Can be 9,10,11 or 12.
      imageType - Type of input image it is computed form.
      Returns:
      Fast feature intensity

    • harris

      public static <I extends ImageGray<I>, D extends ImageGray<D>> GeneralFeatureIntensity<I,D> harris(int windowRadius, float kappa, boolean weighted, Class<D> derivType)
      Feature intensity for Harris corner detector. See HarrisCornerIntensity for more details.
      Type Parameters:
      I - Input image type.
      D - Derivative type.
      Parameters:
      windowRadius - Size of the feature it is detects, Try 2.
      kappa - Tuning parameter, typically a small number around 0.04
      weighted - Is the gradient weighted using a Gaussian distribution? Weighted is much slower than unweighted.
      derivType - Image derivative type it is computed from. @return Harris corner
      Returns:
      Harris feature intensity

    • shiTomasi

      public static <I extends ImageGray<I>, D extends ImageGray<D>> GeneralFeatureIntensity<I,D> shiTomasi(int windowRadius, boolean weighted, Class<D> derivType)
      Feature intensity for KLT corner detector. See ShiTomasiCornerIntensity for more details.
      Type Parameters:
      I - Input image type.
      D - Derivative type.
      Parameters:
      windowRadius - Size of the feature it detects, Try 2.
      weighted - Should the it be weighted by a Gaussian kernel? Unweighted is much faster.
      derivType - Image derivative type it is computed from.
      Returns:
      KLT feature intensity

    • kitros

      public static <I extends ImageGray<I>, D extends ImageGray<D>> GeneralFeatureIntensity<I,D> kitros(Class<D> derivType)
      Feature intensity for Kitchen and Rosenfeld corner detector. See KitRosCornerIntensity for more details.
      Type Parameters:
      I - Input image type.
      D - Derivative type.
      Parameters:
      derivType - Image derivative type it is computed from.
      Returns:
      Kitchen and Rosenfeld feature intensity

    • median

      public static <I extends ImageGray<I>, D extends ImageGray<D>> GeneralFeatureIntensity<I,D> median(int radius, Class<I> imageType)
      Feature intensity for median corner detector.
      Type Parameters:
      I - Input image type.
      Parameters:
      radius - Size of the feature it detects,
      Returns:
      Median feature intensity

    • hessian

      public static <I extends ImageGray<I>, D extends ImageGray<D>> GeneralFeatureIntensity<I,D> hessian(HessianBlobIntensity.Type type, Class<D> derivType)
      Blob detector which uses the image's second order derivatives directly.
      Type Parameters:
      I - Input image type.
      D - Derivative type.
      Parameters:
      type - Type of Hessian
      Returns:
      Hessian based blob intensity
      See Also:

    • hessianDet

      public static <I extends ImageGray<I>, D extends ImageGray<D>> GeneralFeatureIntensity<I,D> hessianDet(Class<I> imageType)
      Computes the Hessian determinant directly from the input image pixels. Does not use passed in derivatives
      Type Parameters:
      I - Input image type.
      D - Derivative type.
      Returns:
      Hessian based blob intensity
      See Also:

    • laplacian

      public static <I extends ImageGray<I>> GeneralFeatureIntensity<I,?> laplacian(Class<I> imageType)
      Blob detector which uses a 3x3 kernel to approximate the second order derivatives and compute a Laplacian blob.