Class DenseFlowPyramidBase<T extends ImageGray<T>>

java.lang.Object
boofcv.alg.flow.DenseFlowPyramidBase<T>
Direct Known Subclasses:
BroxWarpingSpacial, HornSchunckPyramid

public abstract class DenseFlowPyramidBase<T extends ImageGray<T>> extends Object
Base class for pyramidal dense flow algorithms based on IPOL papers.
  • Field Details

  • Constructor Details

    • DenseFlowPyramidBase

      protected DenseFlowPyramidBase(double scale, double sigma, int maxLayers, InterpolatePixelS<GrayF32> interp)
  • Method Details

    • process

      public void process(T image1, T image2)
      Processes the raw input images. Normalizes them and creates image pyramids from them.
    • interpolateFlowScale

      protected void interpolateFlowScale(GrayF32 prev, GrayF32 curr)
      Takes the flow from the previous lower resolution layer and uses it to initialize the flow in the current layer. Adjusts for change in image scale.
    • warpImageTaylor

      protected void warpImageTaylor(GrayF32 before, GrayF32 flowX, GrayF32 flowY, GrayF32 after)
      Takes the flow from the previous lower resolution layer and uses it to initialize the flow in the current layer. Adjusts for change in image scale.
    • process

      public abstract void process(ImagePyramid<GrayF32> image1, ImagePyramid<GrayF32> image2)
      Computes dense optical flow from the provided image pyramid. Image gradient for each layer should be computed directly from the layer images.
      Parameters:
      image1 - Pyramid of first image
      image2 - Pyramid of second image
    • imageNormalization

      protected static <T extends ImageGray<T>> void imageNormalization(T image1, T image2, GrayF32 normalized1, GrayF32 normalized2)
      Function to normalize the images between 0 and 255.