/// <summary>
/// Perform detection on the input image and return the results
/// </summary>
/// <param name="m">The input image</param>
/// <param name="matchScoreThreshold">A threshold used to filter boxes by score.</param>
/// <param name="nmsThreshold">A threshold used in non maximum suppression.</param>
/// <returns>The detected objects</returns>
public MaskedObject[] Detect(IInputArray m, float matchScoreThreshold = 0.5f, float nmsThreshold = 0.4f)
{
using (InputArray iaM = m.GetInputArray())
using (Mat blob = DnnInvoke.BlobFromImage(m))
using (VectorOfMat tensors = new VectorOfMat())
//using(VectorOfMat outputTensors = new VectorOfMat())
{
_maskRcnnDetector.SetInput(blob, "image_tensor");
_maskRcnnDetector.Forward(tensors, new string[] { "detection_out_final", "detection_masks" });
//_maskRcnnModel.Predict(m, outputTensors);
using (Mat boxes = tensors[0])
using (Mat masks = tensors[1])
{
System.Drawing.Size imgSize = iaM.GetSize();
float[,,,] boxesData = boxes.GetData(true) as float[, , , ];
int numDetections = boxesData.GetLength(2);
List <int> classIds = new List <int>();
List <Rectangle> regions = new List <Rectangle>();
List <float> scores = new List <float>();
for (int i = 0; i < numDetections; i++)
{
int classId = (int)boxesData[0, 0, i, 1];
if (_objectsOfInterest == null || _objectsOfInterest.Contains(_labels[classId]))
{
float score = boxesData[0, 0, i, 2];
Rectangle rect = DetectedObject.GetRectangle(
boxesData[0, 0, i, 3],
boxesData[0, 0, i, 4],
boxesData[0, 0, i, 5],
boxesData[0, 0, i, 6],
imgSize.Width,
imgSize.Height);
rect.Intersect(new Rectangle(Point.Empty, imgSize));
regions.Add(rect);
scores.Add(score);
classIds.Add(classId);
}
}
int[] validIdx = DnnInvoke.NMSBoxes(regions.ToArray(), scores.ToArray(), matchScoreThreshold, nmsThreshold);
List <MaskedObject> maskedObjects = new List <MaskedObject>();
for (int i = 0; i < validIdx.Length; i++)
{
int idx = validIdx[i];
int classId = classIds[idx];
Rectangle rect = regions[idx];
float score = scores[idx];
int[] masksDim = masks.SizeOfDimension;
using (Mat mask = new Mat(
masksDim[2],
masksDim[3],
DepthType.Cv32F,
1,
masks.GetDataPointer(i, classId),
masksDim[3] * masks.ElementSize))
{
MaskedObject mo = new MaskedObject(classId, _labels[classId], score, rect, mask);
maskedObjects.Add(mo);
}
}
return(maskedObjects.ToArray());
}
}
}
public DetectedObject[] Detect(Mat image, double confThreshold = 0.5)
{
MCvScalar meanVal = new MCvScalar();
Size imageSize = image.Size;
DnnInvoke.BlobFromImage(
image,
_inputBlob,
1.0,
new Size(416, 416),
meanVal,
true,
false,
DepthType.Cv8U);
_yoloDetector.SetInput(_inputBlob, "", 0.00392);
int[] outLayers = _yoloDetector.UnconnectedOutLayers;
String outLayerType = _yoloDetector.GetLayer(outLayers[0]).Type;
String[] outLayerNames = _yoloDetector.UnconnectedOutLayersNames;
using (VectorOfMat outs = new VectorOfMat())
{
List <DetectedObject> detectedObjects = new List <DetectedObject>();
_yoloDetector.Forward(outs, outLayerNames);
if (outLayerType.Equals("Region"))
{
int size = outs.Size;
for (int i = 0; i < size; i++)
{
// Network produces output blob with a shape NxC where N is a number of
// detected objects and C is a number of classes + 4 where the first 4
// numbers are [center_x, center_y, width, height]
using (Mat m = outs[i])
{
int rows = m.Rows;
int cols = m.Cols;
float[,] data = m.GetData(true) as float[, ];
for (int j = 0; j < rows; j++)
{
using (Mat subM = new Mat(m, new Emgu.CV.Structure.Range(j, j + 1), new Emgu.CV.Structure.Range(5, cols)))
{
double minVal = 0, maxVal = 0;
Point minLoc = new Point();
Point maxLoc = new Point();
CvInvoke.MinMaxLoc(subM, ref minVal, ref maxVal, ref minLoc, ref maxLoc);
if (maxVal > confThreshold)
{
int centerX = (int)(data[j, 0] * imageSize.Width);
int centerY = (int)(data[j, 1] * imageSize.Height);
int width = (int)(data[j, 2] * imageSize.Width);
int height = (int)(data[j, 3] * imageSize.Height);
int left = centerX - width / 2;
int top = centerY - height / 2;
Rectangle rect = new Rectangle(left, top, width, height);
DetectedObject obj = new DetectedObject();
obj.ClassId = maxLoc.X;
obj.Confident = maxVal;
obj.Region = rect;
obj.Label = _labels[obj.ClassId];
detectedObjects.Add(obj);
}
}
}
}
}
return(detectedObjects.ToArray());
}
else
{
throw new Exception(String.Format("Unknown output layer type: {0}", outLayerType));
}
}
}