Difference between revisions of "Example Associate Interest Points"

From BoofCV
Jump to navigationJump to search
m
m
Line 10: Line 10:


Example Code:
Example Code:
* [https://github.com/lessthanoptimal/BoofCV/blob/v0.27/examples/src/boofcv/examples/features/ExampleAssociatePoints.java ExampleAssociatePoints.java]
* [https://github.com/lessthanoptimal/BoofCV/blob/v0.36/examples/src/boofcv/examples/features/ExampleAssociatePoints.java ExampleAssociatePoints.java]


Concepts:
Concepts:
Line 106: Line 106:


ScoreAssociation scorer = FactoryAssociation.defaultScore(detDesc.getDescriptionType());
ScoreAssociation scorer = FactoryAssociation.defaultScore(detDesc.getDescriptionType());
AssociateDescription associate = FactoryAssociation.greedy(scorer, Double.MAX_VALUE, true);
AssociateDescription associate = FactoryAssociation.greedy(new ConfigAssociateGreedy(true),scorer);


// load and match images
// load and match images

Revision as of 22:01, 17 May 2020

Associated feature between images using example code.
Associated feature between images using example code.

A common problem for many computer vision applications is matching features observed in two or more images. Below is an example of how this can be accomplished using interest point and their descriptions. When run, you can click on the image to select individual points or drag a region to select several.

Example Code:

Concepts:

  • Describe point features
  • Associate descriptions

Example Code

/**
 * After interest points have been detected in two images the next step is to associate the two
 * sets of images so that the relationship can be found.  This is done by computing descriptors for
 * each detected feature and associating them together.  In the code below abstracted interfaces are
 * used to allow different algorithms to be easily used.  The cost of this abstraction is that detector/descriptor
 * specific information is thrown away, potentially slowing down or degrading performance.
 *
 * @author Peter Abeles
 */
public class ExampleAssociatePoints<T extends ImageGray<T>, TD extends TupleDesc> {

	// algorithm used to detect and describe interest points
	DetectDescribePoint<T, TD> detDesc;
	// Associated descriptions together by minimizing an error metric
	AssociateDescription<TD> associate;

	// location of interest points
	public List<Point2D_F64> pointsA;
	public List<Point2D_F64> pointsB;

	Class<T> imageType;

	public ExampleAssociatePoints(DetectDescribePoint<T, TD> detDesc,
								  AssociateDescription<TD> associate,
								  Class<T> imageType) {
		this.detDesc = detDesc;
		this.associate = associate;
		this.imageType = imageType;
	}

	/**
	 * Detect and associate point features in the two images.  Display the results.
	 */
	public void associate( BufferedImage imageA , BufferedImage imageB )
	{
		T inputA = ConvertBufferedImage.convertFromSingle(imageA, null, imageType);
		T inputB = ConvertBufferedImage.convertFromSingle(imageB, null, imageType);

		// stores the location of detected interest points
		pointsA = new ArrayList<>();
		pointsB = new ArrayList<>();

		// stores the description of detected interest points
		FastQueue<TD> descA = UtilFeature.createQueue(detDesc,100);
		FastQueue<TD> descB = UtilFeature.createQueue(detDesc,100);

		// describe each image using interest points
		describeImage(inputA,pointsA,descA);
		describeImage(inputB,pointsB,descB);

		// Associate features between the two images
		associate.setSource(descA);
		associate.setDestination(descB);
		associate.associate();

		// display the results
		AssociationPanel panel = new AssociationPanel(20);
		panel.setAssociation(pointsA,pointsB,associate.getMatches());
		panel.setImages(imageA,imageB);

		ShowImages.showWindow(panel,"Associated Features",true);
	}

	/**
	 * Detects features inside the two images and computes descriptions at those points.
	 */
	private void describeImage(T input, List<Point2D_F64> points, FastQueue<TD> descs )
	{
		detDesc.detect(input);

		for( int i = 0; i < detDesc.getNumberOfFeatures(); i++ ) {
			points.add( detDesc.getLocation(i).copy() );
			descs.grow().setTo(detDesc.getDescription(i));
		}
	}

	public static void main( String args[] ) {

		Class imageType = GrayF32.class;
//		Class imageType = GrayU8.class;

		// select which algorithms to use
		DetectDescribePoint detDesc = FactoryDetectDescribe.
				surfStable(new ConfigFastHessian(1, 2, 300, 1, 9, 4, 4), null,null, imageType);
//				sift(new ConfigCompleteSift(0,5,600));

		ScoreAssociation scorer = FactoryAssociation.defaultScore(detDesc.getDescriptionType());
		AssociateDescription associate = FactoryAssociation.greedy(new ConfigAssociateGreedy(true),scorer);

		// load and match images
		ExampleAssociatePoints app = new ExampleAssociatePoints(detDesc,associate,imageType);

		BufferedImage imageA = UtilImageIO.loadImage(UtilIO.pathExample("stitch/kayak_01.jpg"));
		BufferedImage imageB = UtilImageIO.loadImage(UtilIO.pathExample("stitch/kayak_03.jpg"));

		app.associate(imageA,imageB);
	}
}