boofcv.alg.flow

Class DenseOpticalFlowBlockPyramid<T extends boofcv.struct.image.ImageSingleBand>

java.lang.Object

boofcv.alg.flow.DenseOpticalFlowBlockPyramid<T>

Direct Known Subclasses:

DenseOpticalFlowBlockPyramid.F32, DenseOpticalFlowBlockPyramid.U8

public abstract class DenseOpticalFlowBlockPyramid<T extends boofcv.struct.image.ImageSingleBand>
extends java.lang.Object

Computes dense optical flow optical using pyramidal approach with square regions and a locally exhaustive search. Flow estimates from higher layers in the pyramid are used to provide an initial estimate flow lower layers. For each pixel in the 'prev' image, a square region centered around it is compared against all other regions within the specified search radius of it in image 'curr'. For each candidate flow the error is computed. After the best score has been found each local pixel which contributed to that square region is checked. When a pixel is checked its current score compared to see if it's better than the score it was previously assigned (if any) then its flow and score will be set to the current. This improves the handled along object edges. If only the flow is considered when a pixel is the center then it almost always fails at edges.

When scoring hypotheses for optical flow and there is a tie, select the hypothesis with the least amount of motion. This only really comes into play when there is absolutely no texture in real-world data.

By checking all pixels associated with the score and not just the center one to see if it has a better score the edges of objects is handled better.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	DenseOpticalFlowBlockPyramid.F32 Implementation for ImageFloat32
static class	DenseOpticalFlowBlockPyramid.U8 Implementation for ImageUInt8

Field Summary

Fields

Modifier and Type	Field and Description
protected ImageFlow	flowCurrLayer
protected ImageFlow	flowPrevLayer
protected int	maxError
protected int	regionRadius
protected float[]	scores
protected int	searchRadius
protected T	template
protected ImageFlow.D	tmp

Constructor Summary

Constructors

Constructor and Description
DenseOpticalFlowBlockPyramid(int searchRadius, int regionRadius, int maxPerPixelError, java.lang.Class<T> imageType) Configures the search.

Method Summary

Methods

Modifier and Type	Method and Description
protected void	checkNeighbors(int cx, int cy, ImageFlow.D flow, ImageFlow image, float score) Examines every pixel inside the region centered at (cx,cy) to see if their optical flow has a worse score the one specified in 'flow'
protected abstract float	computeError(int cx, int cy, T curr) Computes the error between the template and a region in 'curr' centered at cx,cy
protected abstract void	extractTemplate(int cx, int cy, T prev) Extracts a square template from the image 'prev' center at cx and cy
protected float	findFlow(int cx, int cy, T curr, ImageFlow.D flow) Performs an exhaustive search centered around (cx,cy) for the region in 'curr' which is the best match for the template.
ImageFlow	getOpticalFlow() Returns the found optical flow
int	getRegionRadius()
int	getSearchRadius()
void	process(boofcv.struct.pyramid.ImagePyramid<T> pyramidPrev, boofcv.struct.pyramid.ImagePyramid<T> pyramidCurr) Computes the optical flow form 'prev' to 'curr' and stores the output into output

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

searchRadius

protected int searchRadius

regionRadius

protected int regionRadius

template

protected T extends boofcv.struct.image.ImageSingleBand template

maxError

protected int maxError

flowPrevLayer

protected ImageFlow flowPrevLayer

flowCurrLayer

protected ImageFlow flowCurrLayer

tmp

protected ImageFlow.D tmp

scores

protected float[] scores

Constructor Detail

DenseOpticalFlowBlockPyramid

public DenseOpticalFlowBlockPyramid(int searchRadius,
                            int regionRadius,
                            int maxPerPixelError,
                            java.lang.Class<T> imageType)

Configures the search.

Parameters:

searchRadius - Determines the size of the area search for matches. area = (2*r + 1)^2

regionRadius - Radius of the square region

maxPerPixelError - Maximum error allowed per pixel.

imageType - Type of image which is being processed.

Method Detail

process

public void process(boofcv.struct.pyramid.ImagePyramid<T> pyramidPrev,
           boofcv.struct.pyramid.ImagePyramid<T> pyramidCurr)

Computes the optical flow form 'prev' to 'curr' and stores the output into output

Parameters:

pyramidPrev - Previous image

pyramidCurr - Current image

findFlow

protected float findFlow(int cx,
             int cy,
             T curr,
             ImageFlow.D flow)

Performs an exhaustive search centered around (cx,cy) for the region in 'curr' which is the best match for the template. Results are written into 'flow'

checkNeighbors

protected void checkNeighbors(int cx,
                  int cy,
                  ImageFlow.D flow,
                  ImageFlow image,
                  float score)

Examines every pixel inside the region centered at (cx,cy) to see if their optical flow has a worse score the one specified in 'flow'

extractTemplate

protected abstract void extractTemplate(int cx,
                   int cy,
                   T prev)

Extracts a square template from the image 'prev' center at cx and cy

computeError

protected abstract float computeError(int cx,
                 int cy,
                 T curr)

Computes the error between the template and a region in 'curr' centered at cx,cy

getOpticalFlow

public ImageFlow getOpticalFlow()

Returns the found optical flow

getSearchRadius

public int getSearchRadius()

getRegionRadius

public int getRegionRadius()