public DnnDetectedObject[] ClassifyObjects(Mat image, Rect boxToAnalyze)
{
if (image == null)
{
throw new ArgumentNullException(nameof(image));
}
var blob = CvDnn.BlobFromImage(image, 1.0 / 255, new Size(320, 320), new Scalar(), crop: false);
nnet.SetInput(blob);
//create mats for output layer
Mat[] outs = Enumerable.Repeat(false, _outNames.Length).Select(_ => new Mat()).ToArray();
//forward model
nnet.Forward(outs, _outNames);
const float threshold = 0.5f; //for confidence
const float nmsThreshold = 0.3f; //threshold for nms
var detections = ExtractYolo2Results(outs, image, threshold, nmsThreshold);
blob.Dispose();
foreach (var output in outs)
{
output.Dispose();
}
return(detections);
}
public DnnDetectedObject[][] ClassifyObjects(IEnumerable <Mat> images)
{
if (images is null)
{
throw new ArgumentNullException(nameof(images));
}
var imageList = new List <Mat>(images);
foreach (var image in imageList)
{
if (image?.Empty() == true)
{
throw new ArgumentNullException(nameof(images), "One of the images is not initialized");
}
}
using var blob = CvDnn.BlobFromImages(imageList, 1.0 / 255, new Size(320, 320), crop: false);
nnet.SetInput(blob);
//forward model
nnet.Forward(outs, _outNames);
if (imageList.Count == 1)
{
return(ExtractYolo3SingleResults(outs, imageList[0], threshold, nmsThreshold));
}
else
{
return(ExtractYolo3BatchedResults(outs, images, threshold, nmsThreshold));
}
}
private IList <DnnDetectedObject[]> InternalClassifyObjects(IList <Mat> images, float detectionThreshold)
{
using var blob = CvDnn.BlobFromImages(images, scaleFactor, scaleSize, crop: false);
nnet.SetInput(blob);
//forward model
nnet.Forward(outs, _outNames);
if (images.Count == 1)
{
return(ExtractYoloSingleResults(outs, images[0], detectionThreshold, nmsThreshold));
}
else
{
return(ExtractYoloBatchedResults(outs, images, detectionThreshold, nmsThreshold));
}
}