boofcv.alg.flow

Class HornSchunck<T extends ImageBase,D extends ImageBase>

java.lang.Object

boofcv.alg.flow.HornSchunck<T,D>

Direct Known Subclasses:

HornSchunck_F32, HornSchunck_U8

public abstract class HornSchunck<T extends ImageBase,D extends ImageBase>
extends java.lang.Object

This is Horn-Schunck's well known work [1] for dense optical flow estimation. It is based off the following equation Ex*u + Ey*v + Et = 0, where (u,v) is the estimated flow for a single pixel, and (Ex,Ey) is the pixel's gradient and Et is the grave in intensity value. It is assumed that each pixel maintains a constant intensity and that changes in flow are smooth. This implementation is faithful to the original work and does not make any effort to improve its performance using more modern techniques.

[1] Horn, Berthold K., and Brian G. Schunck. "Determining optical flow." 1981 Technical Symposium East. International Society for Optics and Photonics, 1981.

Constructor Summary

Constructors

Constructor and Description
HornSchunck(float alpha, int numIterations, ImageType<D> derivType) Constructor

Method Summary

Modifier and Type	Method and Description
void	process(T image1, T image2, ImageFlow output) Computes dense optical flow from the first image's gradient and the difference between the second and the first image.
void	setNumIterations(int numIterations) changes the maximum number of iterations

Methods inherited from class java.lang.Object

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

Constructor Detail

HornSchunck

public HornSchunck(float alpha,
                   int numIterations,
                   ImageType<D> derivType)

Constructor

Parameters:

alpha - Larger values place more importance on flow smoothness consistency over brightness consistency. Try 20

numIterations - Number of iterations. Try 1000

Method Detail

setNumIterations

public void setNumIterations(int numIterations)

changes the maximum number of iterations

Parameters:

numIterations - maximum number of iterations

process

public void process(T image1,
                    T image2,
                    ImageFlow output)

Computes dense optical flow from the first image's gradient and the difference between the second and the first image.

Parameters:

image1 - First image

image2 - Second image

output - Found dense optical flow