boofcv.alg.tracker.klt

Class KltTracker<InputImage extends ImageGray,DerivativeImage extends ImageGray>

java.lang.Object

boofcv.alg.tracker.klt.KltTracker<InputImage,DerivativeImage>

public class KltTracker<InputImage extends ImageGray,DerivativeImage extends ImageGray>
extends java.lang.Object

A Kanade-Lucas-Tomasi (KLT) [1,2,3,4] point feature tracker for a single layer gray scale image. It tracks point features across a sequence of images by having each feature individually follow the image's gradient. Feature locations are estimated to within sub-pixel accuracy.

For this particular implementation of KLT, image derivatives is only needed when setDescription() is called. Tracker quality will degrade if features change orientation, but this technique is significantly faster.

Citations:

[1] Bruce D. Lucas and Takeo Kanade. An Iterative Image Registration Technique with an Application to Stereo Vision. International Joint Conference on Artificial Intelligence, pages 674-679, 1981.
[2] Carlo Tomasi and Takeo Kanade. Detection and Tracking of Point Features. Carnegie Mellon University Technical Report CMU-CS-91-132, April 1991.
[3] Jianbo Shi and Carlo Tomasi. Good Features to Track. IEEE Conference on Computer Vision and Pattern Recognition, pages 593-600, 1994.
[4] Stan Birchfield, http://www.ces.clemson.edu/~stb/klt/

Constructor Summary

Constructors

Constructor and Description
KltTracker(InterpolateRectangle<InputImage> interpInput, InterpolateRectangle<DerivativeImage> interpDeriv, KltConfig config)

Method Summary

Modifier and Type	Method and Description
KltConfig	getConfig()
float	getError() Average absolute value of the difference between each pixel in the image and the template
boolean	isDescriptionComplete(KltFeature feature) Checks to see if the feature description is complete or if it was created by a feature partially outside the image
boolean	isFullyInside(float x, float y) Returns true if the features is entirely enclosed inside of the image.
boolean	isFullyOutside(float x, float y) Returns true if the features is entirely outside of the image.
boolean	setDescription(KltFeature feature) Sets the features description using the current image and the location of the feature stored in the feature.
void	setImage(InputImage image, DerivativeImage derivX, DerivativeImage derivY) Sets the current image it should be tracking with.
KltTrackFault	track(KltFeature feature) Updates the feature's location inside the image.
void	unsafe_setImage(InputImage image, DerivativeImage derivX, DerivativeImage derivY) Same as setImage(InputImage, DerivativeImage, DerivativeImage), but it doesn't check to see if the images are the same size each time

Methods inherited from class java.lang.Object

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

Constructor Detail

KltTracker

public KltTracker(InterpolateRectangle<InputImage> interpInput,
                  InterpolateRectangle<DerivativeImage> interpDeriv,
                  KltConfig config)

Method Detail

setImage

public void setImage(InputImage image,
                     DerivativeImage derivX,
                     DerivativeImage derivY)

Sets the current image it should be tracking with.

Parameters:

image - Original input image.

derivX - Image derivative along the x-axis

derivY - Image derivative along the y-axis

unsafe_setImage

public void unsafe_setImage(InputImage image,
                            DerivativeImage derivX,
                            DerivativeImage derivY)

Same as setImage(InputImage, DerivativeImage, DerivativeImage), but it doesn't check to see if the images are the same size each time

setDescription

public boolean setDescription(KltFeature feature)

Sets the features description using the current image and the location of the feature stored in the feature. If the feature is an illegal location and cannot be set then false is returned.

Parameters:

feature - Feature description which is to be set. Location must be specified.

Returns:

true if the feature's description was modified.

track

public KltTrackFault track(KltFeature feature)

Updates the feature's location inside the image. The feature's position can be modified even if tracking fails.

Parameters:

feature - Feature being tracked.

Returns:

If the tracking was successful or not.

isDescriptionComplete

public boolean isDescriptionComplete(KltFeature feature)

Checks to see if the feature description is complete or if it was created by a feature partially outside the image

isFullyInside

public boolean isFullyInside(float x,
                             float y)

Returns true if the features is entirely enclosed inside of the image.

isFullyOutside

public boolean isFullyOutside(float x,
                              float y)

Returns true if the features is entirely outside of the image. A region is entirely outside if not an entire pixel is contained inside the image. So if only 0.999 of a pixel is inside then the whole region is considered to be outside. Can't interpolate nothing...

getError

public float getError()

Average absolute value of the difference between each pixel in the image and the template

Returns:

Average error

getConfig

public KltConfig getConfig()