Search in sources :

Example 1 with Homography2D_F32

use of georegression.struct.homography.Homography2D_F32 in project BoofCV by lessthanoptimal.

the class ExampleBackgroundRemovalMoving method main.

public static void main(String[] args) {
    // Example with a moving camera.  Highlights why motion estimation is sometimes required
    String fileName = UtilIO.pathExample("tracking/chipmunk.mjpeg");
    // Camera has a bit of jitter in it.  Static kinda works but motion reduces false positives
    // String fileName = UtilIO.pathExample("background/horse_jitter.mp4");
    // Comment/Uncomment to switch input image type
    ImageType imageType = ImageType.single(GrayF32.class);
    // ImageType imageType = ImageType.il(3, InterleavedF32.class);
    // ImageType imageType = ImageType.il(3, InterleavedU8.class);
    // Configure the feature detector
    ConfigGeneralDetector confDetector = new ConfigGeneralDetector();
    confDetector.threshold = 10;
    confDetector.maxFeatures = 300;
    confDetector.radius = 6;
    // Use a KLT tracker
    PointTracker tracker = FactoryPointTracker.klt(new int[] { 1, 2, 4, 8 }, confDetector, 3, GrayF32.class, null);
    // This estimates the 2D image motion
    ImageMotion2D<GrayF32, Homography2D_F64> motion2D = FactoryMotion2D.createMotion2D(500, 0.5, 3, 100, 0.6, 0.5, false, tracker, new Homography2D_F64());
    ConfigBackgroundBasic configBasic = new ConfigBackgroundBasic(30, 0.005f);
    // Configuration for Gaussian model.  Note that the threshold changes depending on the number of image bands
    // 12 = gray scale and 40 = color
    ConfigBackgroundGaussian configGaussian = new ConfigBackgroundGaussian(12, 0.001f);
    configGaussian.initialVariance = 64;
    configGaussian.minimumDifference = 5;
    // Note that GMM doesn't interpolate the input image. Making it harder to model object edges.
    // However it runs faster because of this.
    ConfigBackgroundGmm configGmm = new ConfigBackgroundGmm();
    configGmm.initialVariance = 1600;
    configGmm.significantWeight = 1e-1f;
    // Comment/Uncomment to switch background mode
    BackgroundModelMoving background = FactoryBackgroundModel.movingBasic(configBasic, new PointTransformHomography_F32(), imageType);
    // FactoryBackgroundModel.movingGaussian(configGaussian, new PointTransformHomography_F32(), imageType);
    // FactoryBackgroundModel.movingGmm(configGmm,new PointTransformHomography_F32(), imageType);
    background.setUnknownValue(1);
    MediaManager media = DefaultMediaManager.INSTANCE;
    SimpleImageSequence video = media.openVideo(fileName, background.getImageType());
    // media.openCamera(null,640,480,background.getImageType());
    // ====== Initialize Images
    // storage for segmented image.  Background = 0, Foreground = 1
    GrayU8 segmented = new GrayU8(video.getNextWidth(), video.getNextHeight());
    // Grey scale image that's the input for motion estimation
    GrayF32 grey = new GrayF32(segmented.width, segmented.height);
    // coordinate frames
    Homography2D_F32 firstToCurrent32 = new Homography2D_F32();
    Homography2D_F32 homeToWorld = new Homography2D_F32();
    homeToWorld.a13 = grey.width / 2;
    homeToWorld.a23 = grey.height / 2;
    // Create a background image twice the size of the input image.  Tell it that the home is in the center
    background.initialize(grey.width * 2, grey.height * 2, homeToWorld);
    BufferedImage visualized = new BufferedImage(segmented.width, segmented.height, BufferedImage.TYPE_INT_RGB);
    ImageGridPanel gui = new ImageGridPanel(1, 2);
    gui.setImages(visualized, visualized);
    ShowImages.showWindow(gui, "Detections", true);
    double fps = 0;
    // smoothing factor for FPS
    double alpha = 0.01;
    while (video.hasNext()) {
        ImageBase input = video.next();
        long before = System.nanoTime();
        GConvertImage.convert(input, grey);
        if (!motion2D.process(grey)) {
            throw new RuntimeException("Should handle this scenario");
        }
        Homography2D_F64 firstToCurrent64 = motion2D.getFirstToCurrent();
        ConvertMatrixData.convert(firstToCurrent64, firstToCurrent32);
        background.segment(firstToCurrent32, input, segmented);
        background.updateBackground(firstToCurrent32, input);
        long after = System.nanoTime();
        fps = (1.0 - alpha) * fps + alpha * (1.0 / ((after - before) / 1e9));
        VisualizeBinaryData.renderBinary(segmented, false, visualized);
        gui.setImage(0, 0, (BufferedImage) video.getGuiImage());
        gui.setImage(0, 1, visualized);
        gui.repaint();
        System.out.println("FPS = " + fps);
        try {
            Thread.sleep(5);
        } catch (InterruptedException e) {
        }
    }
}
Also used : ConfigBackgroundBasic(boofcv.factory.background.ConfigBackgroundBasic) BackgroundModelMoving(boofcv.alg.background.BackgroundModelMoving) SimpleImageSequence(boofcv.io.image.SimpleImageSequence) PointTransformHomography_F32(boofcv.alg.distort.PointTransformHomography_F32) ConfigGeneralDetector(boofcv.abst.feature.detect.interest.ConfigGeneralDetector) Homography2D_F32(georegression.struct.homography.Homography2D_F32) Homography2D_F64(georegression.struct.homography.Homography2D_F64) BufferedImage(java.awt.image.BufferedImage) ImageType(boofcv.struct.image.ImageType) ConfigBackgroundGaussian(boofcv.factory.background.ConfigBackgroundGaussian) GrayF32(boofcv.struct.image.GrayF32) MediaManager(boofcv.io.MediaManager) DefaultMediaManager(boofcv.io.wrapper.DefaultMediaManager) ConfigBackgroundGmm(boofcv.factory.background.ConfigBackgroundGmm) GrayU8(boofcv.struct.image.GrayU8) ImageGridPanel(boofcv.gui.image.ImageGridPanel) PointTracker(boofcv.abst.feature.tracker.PointTracker) FactoryPointTracker(boofcv.factory.feature.tracker.FactoryPointTracker) ImageBase(boofcv.struct.image.ImageBase)

Example 2 with Homography2D_F32

use of georegression.struct.homography.Homography2D_F32 in project BoofCV by lessthanoptimal.

the class BenchmarkImageDistort method benchmark.

private void benchmark() {
    Random rand = new Random(234);
    Homography2D_F32 affine = new Homography2D_F32((float) rand.nextGaussian(), (float) rand.nextGaussian(), (float) rand.nextGaussian(), (float) rand.nextGaussian(), (float) rand.nextGaussian(), (float) rand.nextGaussian(), (float) rand.nextGaussian(), (float) rand.nextGaussian(), (float) rand.nextGaussian());
    System.out.println("=========  Profile Image Size " + imgWidth + " x " + imgHeight + " ==========");
    System.out.println();
    ProfileOperation.printOpsPerSec(new MapBilinear_F32(affine), TEST_TIME);
    ProfileOperation.printOpsPerSec(new HomographyBilinear_F32(affine), TEST_TIME);
    ProfileOperation.printOpsPerSec(new HomographyBilinearCrop_F32(affine), TEST_TIME);
}
Also used : Random(java.util.Random) Homography2D_F32(georegression.struct.homography.Homography2D_F32)

Example 3 with Homography2D_F32

use of georegression.struct.homography.Homography2D_F32 in project BoofCV by lessthanoptimal.

the class GenericBackgroundModelMovingChecks method checkTransform.

private <T extends ImageBase<T>> void checkTransform(T frame, GrayU8 segmented, BackgroundModelMoving<T, Homography2D_F32> alg, Homography2D_F32 homeToCurrent, double tol) {
    Homography2D_F32 currentToHome = homeToCurrent.invert(null);
    alg.reset();
    alg.updateBackground(homeToCurrent, frame);
    alg.segment(homeToCurrent, frame, segmented);
    checkSegmented(currentToHome, segmented, tol);
    alg.segment(new Homography2D_F32(), frame, segmented);
    checkSegmented(homeToCurrent, segmented, tol);
}
Also used : Homography2D_F32(georegression.struct.homography.Homography2D_F32)

Example 4 with Homography2D_F32

use of georegression.struct.homography.Homography2D_F32 in project BoofCV by lessthanoptimal.

the class GenericBackgroundModelMovingChecks method currentOutsideBackground.

private <T extends ImageBase<T>> void currentOutsideBackground(ImageType<T> imageType) {
    T frame = imageType.createImage(width, height);
    GrayU8 segmented = new GrayU8(width, height);
    BackgroundModelMoving<T, Homography2D_F32> alg = create(frame.getImageType());
    Homography2D_F32 homeToWorld = new Homography2D_F32();
    alg.initialize(width, height, homeToWorld);
    alg.setUnknownValue(2);
    double translationTol = backgroundOutsideTol / 2;
    Homography2D_F32 homeToCurrent = new Homography2D_F32();
    homeToCurrent.a13 = 5;
    checkTransform(frame, segmented, alg, homeToCurrent, translationTol);
    homeToCurrent.a13 = -5;
    checkTransform(frame, segmented, alg, homeToCurrent, translationTol);
    homeToCurrent.a13 = 0;
    homeToCurrent.a23 = 5;
    checkTransform(frame, segmented, alg, homeToCurrent, translationTol);
    homeToCurrent.a23 = -5;
    checkTransform(frame, segmented, alg, homeToCurrent, translationTol);
    // make it more interesting
    homeToCurrent.set(1.0f, 0.6f, 20, -0.6f, 0.95f, 20, 0, 0, 1);
    checkTransform(frame, segmented, alg, homeToCurrent, backgroundOutsideTol);
}
Also used : GrayU8(boofcv.struct.image.GrayU8) Homography2D_F32(georegression.struct.homography.Homography2D_F32)

Example 5 with Homography2D_F32

use of georegression.struct.homography.Homography2D_F32 in project BoofCV by lessthanoptimal.

the class GenericBackgroundMovingGmmChecks method performStationaryTests.

@Test
public void performStationaryTests() {
    GenericBackgroundStationaryGmmChecks stationary = new GenericBackgroundStationaryGmmChecks() {

        @Override
        public BackgroundModelStationary create(ImageType imageType) {
            BackgroundModelMoving moving = GenericBackgroundMovingGmmChecks.this.create(imageType);
            return new MovingToStationary((BackgroundMovingGmm) moving, new Homography2D_F32());
        }
    };
    stationary.initialVariance();
    stationary.learnRate();
    stationary.checkBandsUsed();
}
Also used : GenericBackgroundStationaryGmmChecks(boofcv.alg.background.stationary.GenericBackgroundStationaryGmmChecks) BackgroundModelMoving(boofcv.alg.background.BackgroundModelMoving) Homography2D_F32(georegression.struct.homography.Homography2D_F32) ImageType(boofcv.struct.image.ImageType) Test(org.junit.Test)

Aggregations

Homography2D_F32 (georegression.struct.homography.Homography2D_F32)18 GrayU8 (boofcv.struct.image.GrayU8)8 Test (org.junit.Test)7 BackgroundModelMoving (boofcv.alg.background.BackgroundModelMoving)4 ImageType (boofcv.struct.image.ImageType)4 Random (java.util.Random)3 Affine2D_F32 (georegression.struct.affine.Affine2D_F32)2 Homography2D_F64 (georegression.struct.homography.Homography2D_F64)2 Point2D_F32 (georegression.struct.point.Point2D_F32)2 ConfigGeneralDetector (boofcv.abst.feature.detect.interest.ConfigGeneralDetector)1 PointTracker (boofcv.abst.feature.tracker.PointTracker)1 GenericBackgroundStationaryBasicChecks (boofcv.alg.background.stationary.GenericBackgroundStationaryBasicChecks)1 GenericBackgroundStationaryGaussianChecks (boofcv.alg.background.stationary.GenericBackgroundStationaryGaussianChecks)1 GenericBackgroundStationaryGmmChecks (boofcv.alg.background.stationary.GenericBackgroundStationaryGmmChecks)1 PixelTransformAffine_F32 (boofcv.alg.distort.PixelTransformAffine_F32)1 PixelTransformHomography_F32 (boofcv.alg.distort.PixelTransformHomography_F32)1 PointTransformHomography_F32 (boofcv.alg.distort.PointTransformHomography_F32)1 ConfigBackgroundBasic (boofcv.factory.background.ConfigBackgroundBasic)1 ConfigBackgroundGaussian (boofcv.factory.background.ConfigBackgroundGaussian)1 ConfigBackgroundGmm (boofcv.factory.background.ConfigBackgroundGmm)1