/// <summary>
/// Postprocess the specified frame, outs and net.
/// </summary>
/// <param name="frame">Frame.</param>
/// <param name="outs">Outs.</param>
/// <param name="net">Net.</param>
private void postprocess(Mat frame, List <Mat> outs, Net net)
{
string outLayerType = outBlobTypes[0];
List <int> classIdsList = new List <int>();
List <float> confidencesList = new List <float>();
List <OpenCVForUnity.CoreModule.Rect> boxesList = new List <OpenCVForUnity.CoreModule.Rect>();
if (net.getLayer(new DictValue(0)).outputNameToIndex("im_info") != -1)
{
// Faster-RCNN or R-FCN
// Network produces output blob with a shape 1x1xNx7 where N is a number of
// detections and an every detection is a vector of values
// [batchId, classId, confidence, left, top, right, bottom]
if (outs.Count == 1)
{
outs[0] = outs[0].reshape(1, (int)outs[0].total() / 7);
//Debug.Log ("outs[i].ToString() " + outs [0].ToString ());
float[] data = new float[7];
for (int i = 0; i < outs[0].rows(); i++)
{
outs[0].get(i, 0, data);
float confidence = data[2];
if (confidence > confThreshold)
{
int class_id = (int)(data[1]);
int left = (int)(data[3] * frame.cols());
int top = (int)(data[4] * frame.rows());
int right = (int)(data[5] * frame.cols());
int bottom = (int)(data[6] * frame.rows());
int width = right - left + 1;
int height = bottom - top + 1;
classIdsList.Add((int)(class_id) - 0);
confidencesList.Add((float)confidence);
boxesList.Add(new OpenCVForUnity.CoreModule.Rect(left, top, width, height));
}
}
}
}
else if (outLayerType == "DetectionOutput")
{
// Network produces output blob with a shape 1x1xNx7 where N is a number of
// detections and an every detection is a vector of values
// [batchId, classId, confidence, left, top, right, bottom]
if (outs.Count == 1)
{
outs[0] = outs[0].reshape(1, (int)outs[0].total() / 7);
//Debug.Log ("outs[i].ToString() " + outs [0].ToString ());
float[] data = new float[7];
for (int i = 0; i < outs[0].rows(); i++)
{
outs[0].get(i, 0, data);
float confidence = data[2];
if (confidence > confThreshold)
{
int class_id = (int)(data[1]);
int left = (int)(data[3] * frame.cols());
int top = (int)(data[4] * frame.rows());
int right = (int)(data[5] * frame.cols());
int bottom = (int)(data[6] * frame.rows());
int width = right - left + 1;
int height = bottom - top + 1;
classIdsList.Add((int)(class_id) - 0);
confidencesList.Add((float)confidence);
boxesList.Add(new OpenCVForUnity.CoreModule.Rect(left, top, width, height));
}
}
}
}
else if (outLayerType == "Region")
{
for (int i = 0; i < outs.Count; ++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]
//Debug.Log ("outs[i].ToString() "+outs[i].ToString());
float[] positionData = new float[5];
float[] confidenceData = new float[outs[i].cols() - 5];
for (int p = 0; p < outs[i].rows(); p++)
{
outs[i].get(p, 0, positionData);
outs[i].get(p, 5, confidenceData);
int maxIdx = confidenceData.Select((val, idx) => new { V = val, I = idx }).Aggregate((max, working) => (max.V > working.V) ? max : working).I;
float confidence = confidenceData[maxIdx];
if (confidence > confThreshold)
{
int centerX = (int)(positionData[0] * frame.cols());
int centerY = (int)(positionData[1] * frame.rows());
int width = (int)(positionData[2] * frame.cols());
int height = (int)(positionData[3] * frame.rows());
int left = centerX - width / 2;
int top = centerY - height / 2;
classIdsList.Add(maxIdx);
confidencesList.Add((float)confidence);
boxesList.Add(new OpenCVForUnity.CoreModule.Rect(left, top, width, height));
}
}
}
}
else
{
Debug.Log("Unknown output layer type: " + outLayerType);
}
MatOfRect boxes = new MatOfRect();
boxes.fromList(boxesList);
MatOfFloat confidences = new MatOfFloat();
confidences.fromList(confidencesList);
MatOfInt indices = new MatOfInt();
Dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
//Debug.Log ("indices.dump () "+indices.dump ());
//Debug.Log ("indices.ToString () "+indices.ToString());
for (int i = 0; i < indices.total(); ++i)
{
int idx = (int)indices.get(i, 0)[0];
OpenCVForUnity.CoreModule.Rect box = boxesList[idx];
drawPred(classIdsList[idx], confidencesList[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame);
}
indices.Dispose();
boxes.Dispose();
confidences.Dispose();
}
/// <summary>
/// Process
/// </summary>
/// <returns></returns>
private async void Process()
{
float DOWNSCALE_RATIO = 1.0f;
while (true)
{
// Check TaskCancel
if (tokenSource.Token.IsCancellationRequested)
{
break;
}
rgbaMat = webCamTextureToMatHelper.GetMat();
// Debug.Log ("rgbaMat.ToString() " + rgbaMat.ToString ());
Mat downScaleRgbaMat = null;
DOWNSCALE_RATIO = 1.0f;
if (enableDownScale)
{
downScaleRgbaMat = imageOptimizationHelper.GetDownScaleMat(rgbaMat);
DOWNSCALE_RATIO = imageOptimizationHelper.downscaleRatio;
}
else
{
downScaleRgbaMat = rgbaMat;
DOWNSCALE_RATIO = 1.0f;
}
Imgproc.cvtColor(downScaleRgbaMat, bgrMat, Imgproc.COLOR_RGBA2BGR);
await Task.Run(() =>
{
// detect faces on the downscale image
if (!enableSkipFrame || !imageOptimizationHelper.IsCurrentFrameSkipped())
{
if (net == null)
{
Imgproc.putText(rgbaMat, "model file is not loaded.", new Point(5, rgbaMat.rows() - 30), Imgproc.FONT_HERSHEY_SIMPLEX, 0.7, new Scalar(255, 255, 255, 255), 2, Imgproc.LINE_AA, false);
Imgproc.putText(rgbaMat, "Please read console message.", new Point(5, rgbaMat.rows() - 10), Imgproc.FONT_HERSHEY_SIMPLEX, 0.7, new Scalar(255, 255, 255, 255), 2, Imgproc.LINE_AA, false);
}
else
{
// Create a 4D blob from a frame.
Size inpSize = new Size(inpWidth > 0 ? inpWidth : bgrMat.cols(),
inpHeight > 0 ? inpHeight : bgrMat.rows());
Mat blob = Dnn.blobFromImage(bgrMat, scale, inpSize, mean, swapRB, false);
// Run a model.
net.setInput(blob);
if (net.getLayer(new DictValue(0)).outputNameToIndex("im_info") != -1)
{ // Faster-RCNN or R-FCN
Imgproc.resize(bgrMat, bgrMat, inpSize);
Mat imInfo = new Mat(1, 3, CvType.CV_32FC1);
imInfo.put(0, 0, new float[] {
(float)inpSize.height,
(float)inpSize.width,
1.6f
});
net.setInput(imInfo, "im_info");
}
TickMeter tm = new TickMeter();
tm.start();
List <Mat> outs = new List <Mat>();
net.forward(outs, outBlobNames);
tm.stop();
// Debug.Log ("Inference time, ms: " + tm.getTimeMilli ());
postprocess(bgrMat, outs, net);
for (int i = 0; i < outs.Count; i++)
{
outs[i].Dispose();
}
blob.Dispose();
if (enableDownScale)
{
for (int i = 0; i < _boxesList.Count; ++i)
{
var rect = _boxesList[i];
_boxesList[i] = new OpenCVForUnity.CoreModule.Rect(
(int)(rect.x * DOWNSCALE_RATIO),
(int)(rect.y * DOWNSCALE_RATIO),
(int)(rect.width * DOWNSCALE_RATIO),
(int)(rect.height * DOWNSCALE_RATIO));
}
}
}
//Imgproc.rectangle(rgbaMat, new Point(0, 0), new Point(rgbaMat.width(), rgbaMat.height()), new Scalar(0, 0, 0, 0), -1);
MatOfRect boxes = new MatOfRect();
boxes.fromList(_boxesList);
MatOfFloat confidences = new MatOfFloat();
confidences.fromList(_confidencesList);
MatOfInt indices = new MatOfInt();
Dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
// Debug.Log ("indices.dump () "+indices.dump ());
// Debug.Log ("indices.ToString () "+indices.ToString());
for (int i = 0; i < indices.total(); ++i)
{
int idx = (int)indices.get(i, 0)[0];
OpenCVForUnity.CoreModule.Rect box = _boxesList[idx];
drawPred(_classIdsList[idx], _confidencesList[idx], box.x, box.y,
box.x + box.width, box.y + box.height, rgbaMat);
}
indices.Dispose();
boxes.Dispose();
confidences.Dispose();
}
});
Utils.fastMatToTexture2D(rgbaMat, texture);
Thread.Sleep(10);
}
}
/// <summary>
/// Postprocess the specified frame, outs and net.
/// </summary>
/// <param name="frame">Frame.</param>
/// <param name="outs">Outs.</param>
/// <param name="net">Net.</param>
private void postprocess(Mat frame, List <Mat> outs, Net net)
{
string outLayerType = outBlobTypes[0];
List <int> classIdsList = new List <int>();
List <float> confidencesList = new List <float>();
List <OpenCVForUnity.CoreModule.Rect> boxesList = new List <OpenCVForUnity.CoreModule.Rect>();
if (outLayerType == "Region")
{
for (int i = 0; i < outs.Count; ++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]
//Debug.Log("outs[i].ToString() " + outs[i].ToString());
float[] positionData = new float[5];
float[] confidenceData = new float[outs[i].cols() - 5];
for (int p = 0; p < outs[i].rows(); p++)
{
outs[i].get(p, 0, positionData);
outs[i].get(p, 5, confidenceData);
int maxIdx = confidenceData.Select((val, idx) => new { V = val, I = idx }).Aggregate((max, working) => (max.V > working.V) ? max : working).I;
float confidence = confidenceData[maxIdx];
if (confidence > confThreshold)
{
int centerX = (int)(positionData[0] * frame.cols());
int centerY = (int)(positionData[1] * frame.rows());
int width = (int)(positionData[2] * frame.cols());
int height = (int)(positionData[3] * frame.rows());
int left = centerX - width / 2;
int top = centerY - height / 2;
classIdsList.Add(maxIdx);
confidencesList.Add((float)confidence);
boxesList.Add(new OpenCVForUnity.CoreModule.Rect(left, top, width, height));
}
}
}
}
else
{
Debug.Log("Unknown output layer type: " + outLayerType);
}
MatOfRect boxes = new MatOfRect();
boxes.fromList(boxesList);
MatOfFloat confidences = new MatOfFloat();
confidences.fromList(confidencesList);
MatOfInt indices = new MatOfInt();
Dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
//Check the Language selected
switch (menuVariables.GetLanguage())
{
case "EN":
vocOffset = 0;
break;
case "ES":
vocOffset = 80;
break;
case "FR":
vocOffset = 160;
break;
case "DE":
vocOffset = 240;
break;
case "IT":
vocOffset = 320;
break;
default:
vocOffset = 0;
break;
}
//Draw the bouding box only if its in the center of the image (On Cursor)
for (int i = 0; i < indices.total(); ++i)
{
int idx = (int)indices.get(i, 0)[0];
OpenCVForUnity.CoreModule.Rect box = boxesList[idx];
if (isOnCursor(box, cursorObject.GetComponent <Cursor>()))
{
drawPred(vocOffset + classIdsList[idx], confidencesList[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame);
wordDisplay.text = classNames[classIdsList[idx]];
//Update the text summarizing the object encountered
if (!vocIDList.Contains(classIdsList[idx]))
{
//Update the vocabulary learned
vocIDList.Add(classIdsList[idx]);
EnglishText.text += "\n" + classNames[classIdsList[idx]] + "\n";
SpanishText.text += "\n" + classNames[80 + classIdsList[idx]] + "\n";
FrenchText.text += "\n" + classNames[160 + classIdsList[idx]] + "\n";
GermanText.text += "\n" + classNames[240 + classIdsList[idx]] + "\n";
ItalianText.text += "\n" + classNames[320 + classIdsList[idx]] + "\n";
}
}
}
indices.Dispose();
boxes.Dispose();
confidences.Dispose();
}
/// <summary>
/// Scanning the specified frame, outs and net.
/// </summary>
/// <param name="frame">Frame.</param>
/// <param name="outs">Outs.</param>
/// <param name="net">Net.</param>
private void postscan(Mat frame, List <Mat> outs, Net net)
{
string outLayerType = outBlobTypes[0];
List <int> classIdsList = new List <int>();
List <float> confidencesList = new List <float>();
List <OpenCVForUnity.CoreModule.Rect> boxesList = new List <OpenCVForUnity.CoreModule.Rect>();
if (outLayerType == "Region")
{
for (int i = 0; i < outs.Count; ++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]
//Debug.Log("outs[i].ToString() " + outs[i].ToString());
float[] positionData = new float[5];
float[] confidenceData = new float[outs[i].cols() - 5];
for (int p = 0; p < outs[i].rows(); p++)
{
outs[i].get(p, 0, positionData);
outs[i].get(p, 5, confidenceData);
int maxIdx = confidenceData.Select((val, idx) => new { V = val, I = idx }).Aggregate((max, working) => (max.V > working.V) ? max : working).I;
float confidence = confidenceData[maxIdx];
if (confidence > confThreshold)
{
int centerX = (int)(positionData[0] * frame.cols());
int centerY = (int)(positionData[1] * frame.rows());
int width = (int)(positionData[2] * frame.cols());
int height = (int)(positionData[3] * frame.rows());
int left = centerX - width / 2;
int top = centerY - height / 2;
classIdsList.Add(maxIdx);
confidencesList.Add((float)confidence);
boxesList.Add(new OpenCVForUnity.CoreModule.Rect(left, top, width, height));
}
}
}
}
else
{
Debug.Log("Unknown output layer type: " + outLayerType);
}
MatOfRect boxes = new MatOfRect();
boxes.fromList(boxesList);
MatOfFloat confidences = new MatOfFloat();
confidences.fromList(confidencesList);
MatOfInt indices = new MatOfInt();
Dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
//for-loop for the mini game - if a new class appears, add it to the
for (int i = 0; i < indices.total(); ++i)
{
int idx = (int)indices.get(i, 0)[0];
if (!minigameList.Contains(classIdsList[idx]))
{
Debug.Log(classNames[classIdsList[idx]]);
minigameList.Add(classIdsList[idx]);
if (minigameList.Count() > 1)
{
wordDisplay.text = minigameList.Count().ToString() + " words";
}
else
{
wordDisplay.text = minigameList.Count().ToString() + " word";
}
}
}
indices.Dispose();
boxes.Dispose();
confidences.Dispose();
}