HornSchunckPyramid (feature 0.23 API)

java.lang.Object
- boofcv.alg.flow.DenseFlowPyramidBase<T>
- - boofcv.alg.flow.HornSchunckPyramid<T>

```
public class HornSchunckPyramid<T extends boofcv.struct.image.ImageGray>
extends DenseFlowPyramidBase<T>
```
Pyramidal implementation of Horn-Schunck [2] based on the discussion in [1]. The problem formulation has been modified from the original found in [2] to account for larger displacements. The Euler-Lagrange equations are solved using Successive Over-Relaxation (SOR).
1. Meinhardt-Llopis, Enric and Sánchez Pérez, Javier and Kondermann, Daniel, "Horn-Schunck Optical Flow with a Multi-Scale Strategy" vol 3, 2013, Image Processing On Line
2. Horn, Berthold K., and Brian G. Schunck. "Determining optical flow." 1981 Technical Symposium East. International Society for Optics and Photonics, 1981.

Field Summary

Fields
Modifier and Type	Field and Description
`protected boofcv.struct.image.GrayF32`	`flowX`
`protected boofcv.struct.image.GrayF32`	`flowY`
`protected boofcv.struct.image.GrayF32`	`initFlowX`
`protected boofcv.struct.image.GrayF32`	`initFlowY`
`protected boofcv.struct.image.GrayF32`	`warpDeriv2X`
`protected boofcv.struct.image.GrayF32`	`warpDeriv2Y`
`protected boofcv.struct.image.GrayF32`	`warpImage2`

Fields inherited from class boofcv.alg.flow.DenseFlowPyramidBase
interp, pyr1, pyr2

Constructor Summary

Constructors
Constructor and Description
`HornSchunckPyramid(ConfigHornSchunckPyramid config, boofcv.alg.interpolate.InterpolatePixelS<boofcv.struct.image.GrayF32> interp)` Configures flow estimation

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`protected static float`	`A_safe(int x, int y, boofcv.struct.image.GrayF32 flow)` See equation 25.
`protected static float`	`A(int x, int y, boofcv.struct.image.GrayF32 flow)` See equation 25.
`boofcv.struct.image.GrayF32`	`getFlowX()`
`boofcv.struct.image.GrayF32`	`getFlowY()`
`protected void`	`interpolateFlowScale(boofcv.struct.image.GrayF32 prev, boofcv.struct.image.GrayF32 curr)` Takes the flow from the previous lower resolution layer and uses it to initialize the flow in the current layer.
`protected void`	`interpolateFlowScale(int widthNew, int heightNew)` Provides an initial estimate for the flow by interpolating values from the previous layer.
`void`	`process(boofcv.struct.pyramid.ImagePyramid<boofcv.struct.image.GrayF32> image1, boofcv.struct.pyramid.ImagePyramid<boofcv.struct.image.GrayF32> image2)` Computes dense optical flow from the provided image pyramid.
`protected void`	`processLayer(boofcv.struct.image.GrayF32 image1, boofcv.struct.image.GrayF32 image2, boofcv.struct.image.GrayF32 derivX2, boofcv.struct.image.GrayF32 derivY2)` Computes the flow for a layer using Taylor series expansion and Successive Over-Relaxation linear solver.
`protected static float`	`safe(int x, int y, boofcv.struct.image.GrayF32 image)` Ensures pixel values are inside the image.
`protected void`	`warpImageTaylor(boofcv.struct.image.GrayF32 before, boofcv.struct.image.GrayF32 flowX, boofcv.struct.image.GrayF32 flowY, boofcv.struct.image.GrayF32 after)` Takes the flow from the previous lower resolution layer and uses it to initialize the flow in the current layer.

Methods inherited from class boofcv.alg.flow.DenseFlowPyramidBase
imageNormalization, process

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

flowX

protected boofcv.struct.image.GrayF32 flowX

flowY

protected boofcv.struct.image.GrayF32 flowY

initFlowX

protected boofcv.struct.image.GrayF32 initFlowX

initFlowY

protected boofcv.struct.image.GrayF32 initFlowY

warpImage2

protected boofcv.struct.image.GrayF32 warpImage2

warpDeriv2X

protected boofcv.struct.image.GrayF32 warpDeriv2X

warpDeriv2Y

protected boofcv.struct.image.GrayF32 warpDeriv2Y

Constructor Detail
- HornSchunckPyramid
```
public HornSchunckPyramid(ConfigHornSchunckPyramid config,
                          boofcv.alg.interpolate.InterpolatePixelS<boofcv.struct.image.GrayF32> interp)
```
  Configures flow estimation
  
  Parameters:
  
  config - Configuration parameters
  
  interp - Interpolation for image flow between image layers and warping. Overrides selection in config.

Method Detail

process
```
public void process(boofcv.struct.pyramid.ImagePyramid<boofcv.struct.image.GrayF32> image1,
                    boofcv.struct.pyramid.ImagePyramid<boofcv.struct.image.GrayF32> image2)
```
Computes dense optical flow from the provided image pyramid. Image gradient for each layer should be computed directly from the layer images.

Specified by:

process in class DenseFlowPyramidBase<T extends boofcv.struct.image.ImageGray>

Parameters:

image1 - Pyramid of first image

image2 - Pyramid of second image

interpolateFlowScale
```
protected void interpolateFlowScale(int widthNew,
                                    int heightNew)
```
Provides an initial estimate for the flow by interpolating values from the previous layer.

interpolateFlowScale
```
protected void interpolateFlowScale(boofcv.struct.image.GrayF32 prev,
                                    boofcv.struct.image.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.

Overrides:

interpolateFlowScale in class DenseFlowPyramidBase<T extends boofcv.struct.image.ImageGray>

warpImageTaylor

protected void warpImageTaylor(boofcv.struct.image.GrayF32 before,
                               boofcv.struct.image.GrayF32 flowX,
                               boofcv.struct.image.GrayF32 flowY,
                               boofcv.struct.image.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.

Overrides:: warpImageTaylor in class DenseFlowPyramidBase<T extends boofcv.struct.image.ImageGray>

processLayer

protected void processLayer(boofcv.struct.image.GrayF32 image1,
                            boofcv.struct.image.GrayF32 image2,
                            boofcv.struct.image.GrayF32 derivX2,
                            boofcv.struct.image.GrayF32 derivY2)

Computes the flow for a layer using Taylor series expansion and Successive Over-Relaxation linear solver. Flow estimates from previous layers are feed into this by setting initFlow and flow to their values.

A_safe

protected static float A_safe(int x,
                              int y,
                              boofcv.struct.image.GrayF32 flow)

See equation 25. Safe version

A

protected static float A(int x,
                         int y,
                         boofcv.struct.image.GrayF32 flow)

See equation 25. Fast unsafe version

safe

protected static float safe(int x,
                            int y,
                            boofcv.struct.image.GrayF32 image)

Ensures pixel values are inside the image. If output it is assigned to the nearest pixel inside the image

getFlowX

public boofcv.struct.image.GrayF32 getFlowX()

getFlowY

public boofcv.struct.image.GrayF32 getFlowY()

Class HornSchunckPyramid<T extends boofcv.struct.image.ImageGray>