private void TrackFeatures(Image <Gray, byte> grayImage)
{
if (framesProcessed == 1)
{
keyPoints = featureDetector.Detect(grayImage);
kpVector = new VectorOfPointF((keyPoints.Select(p => p.Point).ToArray()));
nextVector = new VectorOfPointF(kpVector.Size);
statusArray = new VectorOfByte(kpVector.Size);
errArray = new VectorOfFloat(kpVector.Size);
}
else if (framesProcessed > 2)
{
kpVector = nextVector;
}
if (framesProcessed % 50 == 0)
{
kpVector = CreateGrid(currentImage);
}
if (framesProcessed >= 2)
{
CvInvoke.CalcOpticalFlowPyrLK(lastGray, grayImage, kpVector, nextVector, statusArray, errArray, new Size(trackBar1.Value * 2 + 2, trackBar1.Value * 2 + 2), trackBar4.Value, new MCvTermCriteria(trackBar2.Value, trackBar3.Value / 100.0));
DrawPoints(nextVector, Color.Blue);
}
}
public IEnumerable <Mat> DescribeMany(IEnumerable <Mat> images, out KeyPoint[][] keypoints)
{
List <Mat> descriptors = new List <Mat>();
KeyPoint[][] keypoints2 = _featureDetector.Detect(images);
_featureDetector.Compute(images, ref keypoints2, descriptors);
keypoints = keypoints2;
return(descriptors);
}
static object[] DetectAndCompute2(UMat img, Feature2D detector, Feature2D computer) // находит и обрабатывает дескрипторы изображения
{
object[] outp = new object[0];
UMat descriptors = new UMat();
var mkp = new MKeyPoint[0];
VectorOfKeyPoint keypoints;
try
{
mkp = detector.Detect(img);
keypoints = new VectorOfKeyPoint(mkp);
computer.Compute(img, keypoints, descriptors);
outp = new object[] { keypoints, descriptors };
}
finally
{
}
return(outp);
}
private static void BowTest()
{
DescriptorMatcher matcher = new BFMatcher();
Feature2D extractor = AKAZE.Create();
Feature2D detector = AKAZE.Create();
TermCriteria criteria = new TermCriteria(CriteriaType.Count | CriteriaType.Eps, 10, 0.001);
BOWKMeansTrainer bowTrainer = new BOWKMeansTrainer(200, criteria, 1);
BOWImgDescriptorExtractor bowDescriptorExtractor = new BOWImgDescriptorExtractor(extractor, matcher);
Mat img = null;
KeyPoint[] keypoint = detector.Detect(img);
Mat features = new Mat();
extractor.Compute(img, ref keypoint, features);
bowTrainer.Add(features);
throw new NotImplementedException();
}
public static double hessianThresh = 300; // настройка SURF
public static void DetectAndCompute(Mat img, out VectorOfKeyPoint keypoints, out Mat descriptors, Feature2D detector, Feature2D computer) // находит и обрабатывает дескрипторы изображения
{
keypoints = null;
descriptors = new Mat();
try
{
var mkp = detector.Detect(img, null);
keypoints = new VectorOfKeyPoint(mkp);
}
catch (Exception e)
{
throw e;
}
try
{
computer.Compute(img, keypoints, descriptors);
}
catch (Exception e)
{
throw e;
}
}
private void CaptureOnImageGrabbed(object sender, EventArgs eventArgs)
{
var capture = (Capture)sender;
var frame = new Mat();
capture.Retrieve(frame);
// 1. get key points
var keyPoints = new VectorOfKeyPoint(_detector.Detect(frame));
_tempCloudPoints.SetKeyFeatures(_selectedFrameIndex, keyPoints);
// 2. get descripters
var descripters = new Mat();
_descripter.Compute(frame, keyPoints, descripters);
// draw keypoints
var imageFrame = new Mat();
Features2DToolbox.DrawKeypoints(frame, keyPoints, imageFrame, new Bgr(Color.DarkBlue),
Features2DToolbox.KeypointDrawType.NotDrawSinglePoints);
if (_selectedFrameIndex != 0)
{
var previousKeyPoints = _tempCloudPoints.GetKeyFeatures(_selectedFrameIndex - 1);
var previousKeyDescripters = _previousDescripters;
const int k = 2;
const double uniquenessThreshold = 0.8;
// 3. compute all matches with previous frame
var matches = new VectorOfVectorOfDMatch();
var matcher = GetNativeMatcher(SelectedMatcher);
matcher.Add(previousKeyDescripters);
matcher.KnnMatch(descripters, matches, k, null);
var mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
Features2DToolbox.VoteForSizeAndOrientation(previousKeyPoints, keyPoints,
matches, mask, 1.5, 20);
Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(previousKeyPoints,
keyPoints, matches, mask, 2);
var managedMask = mask.GetData();
// 4. separate good matches
var currentKeys = keyPoints;
for (int i = 0; i < matches.Size; i++)
{
var match = matches[i][0];
// filter wrong matches
if (managedMask[i] == 1)
{
var previousIndex = match.TrainIdx;
var currentIndex = match.QueryIdx;
var previousPoint = previousKeyPoints[previousIndex].Point;
var currentPoint = currentKeys[currentIndex].Point;
_tempCloudPoints.Unite(_selectedFrameIndex - 1, previousIndex,
_selectedFrameIndex, currentIndex);
CvInvoke.Line(imageFrame,
Point.Round(previousPoint),
Point.Round(currentPoint),
new Bgr(Color.Red).MCvScalar,
2);
}
}
}
_previousDescripters = descripters;
PreviewImageSource = imageFrame;
_selectedFrameIndex++;
RaisePropertyChanged("Progress");
RaisePropertyChanged("ProgressText");
if (_selectedFrameIndex == _framesCount)
{
GeneratingStates = FeatureGeneratingStates.Finished;
}
}