public static void Detect(Mat image, List <Rectangle> faces)
{
Net net = DnnInvoke.ReadNetFromTensorflow(@"C:\models\opencv_face_detector_uint8.pb", @"C:\models\opencv_face_detector.pbtxt");
Mat inputBlob = DnnInvoke.BlobFromImage(image, 1.0, new Size(300, 300), new MCvScalar(104.0, 117.0, 123.0), true, false);
net.SetInput(inputBlob, "data");
Mat detection = net.Forward("detection_out");
int resultRows = detection.SizeOfDimension[2];
int resultCols = detection.SizeOfDimension[3];
float[] temp = new float[resultRows * resultCols];
Marshal.Copy(detection.DataPointer, temp, 0, temp.Length);
for (int i = 0; i < resultRows; i++)
{
float confidence = temp[i * resultCols + 2];
if (confidence > 0.7)
{
int x1 = (int)(temp[i * resultCols + 3] * image.Width);
int y1 = (int)(temp[i * resultCols + 4] * image.Height);
int x2 = (int)(temp[i * resultCols + 5] * image.Width);
int y2 = (int)(temp[i * resultCols + 6] * image.Height);
Rectangle rectangle = new Rectangle(x1, y1, x2 - x1, y2 - y1);
faces.Add(rectangle);
}
}
}
////////////////
/// 窗口操作 ///
////////////////
public Form1()
{
InitializeComponent();
net = DnnInvoke.ReadNetFromTensorflow(@"Properties\frozen_inference_graph.pb", @"Properties\graph.pbtxt"); //载入神经网络
if (net == null) //如果载入失败
{
throw new Exception("Error"); //报错
}
Application.Idle += new EventHandler(delegate //于空闲状态时执行以下代码
{
if (img != null) //如果摄像头有传入图像
{ //则依次经过以下图像处理方法
img = ProcessImageUseDnn(img); // 1.DNN网络手部检测方法
if (showPoints)
{
img = DrawPoints(img); // 2.检测点绘制方法
}
if (showKeyPoint)
{
img = DrawKeyPoint(img); // 3.关键点绘制方法
}
imageBox1.Image = img; //最后输出图像到 imageBox1
}
});
}
public DnnFaceDetector(IConfiguration configuration)
{
int.TryParse(configuration["Algos:Dnn:Height"], out _height);
int.TryParse(configuration["Algos:Dnn:Width"], out _width);
double.TryParse(configuration["Algos:Dnn:Probability"], out _probability);
_net = DnnInvoke.ReadNetFromTensorflow(configuration["Algos:Dnn:BinFilePath"], configuration["Algos:Dnn:ParamFilePath"]);
}
public CameraObjectDetectionWindow()
{
InitializeComponent();
frame = new Image <Bgr, byte>(resolutionX, resolutionY);
net = DnnInvoke.ReadNetFromTensorflow(graphPath, configPath);
labels = File.ReadAllLines(labelPath);
}
/// <summary>
/// 初始化臉部偵測物件
/// </summary>
public FaceDetector()
{
string programPath = AppDomain.CurrentDomain.BaseDirectory;
string modelsPath = Path.Combine(programPath, "models");
string detectionPbPath = Path.Combine(modelsPath, "opencv_face_detector_uint8.pb");
string detectionPbtxtPath = Path.Combine(modelsPath, "opencv_face_detector.pbtxt");
detectorModel = DnnInvoke.ReadNetFromTensorflow(detectionPbPath, detectionPbtxtPath);
}
public DnnInfo(string modeFileName)
{
try
{
m_dnnModel = DnnInvoke.ReadNetFromTensorflow(modeFileName);
UpdateInfo();
}
catch (Exception ex)
{
m_dnnModel = null;
}
}
// Ищем лица по списку изображений (SSD)
public List <int[][]> DetectFacesSDD(List <string> imagePaths)
{
List <int[][]> allFaces = new List <int[][]>()
{
};
int count = 0;
// Ищем лица для каждого изображения
foreach (var file in imagePaths)
{
List <int[]> faces = new List <int[]>();
int i = 0;
using (Image <Bgr, byte> image = new Image <Bgr, byte>(file))
{
int cols = image.Width;
int rows = image.Height;
Net net = DnnInvoke.ReadNetFromTensorflow(_modelFile, _configFile);
net.SetInput(DnnInvoke.BlobFromImage(image.Mat, 1, new System.Drawing.Size(300, 300), default(MCvScalar), false, false));
Mat mat = net.Forward();
float[,,,] flt = (float[, , , ])mat.GetData();
for (int x = 0; x < flt.GetLength(2); x++)
{
if (flt[0, 0, x, 2] > 0.2)
{
int left = Convert.ToInt32(flt[0, 0, x, 3] * cols);
int top = Convert.ToInt32(flt[0, 0, x, 4] * rows);
int right = Convert.ToInt32(flt[0, 0, x, 5] * cols) - left;
int bottom = Convert.ToInt32(flt[0, 0, x, 6] * rows) - top;
int[] face = new[] { left, top, right, bottom };
faces.Add(face);
i++;
}
}
}
allFaces.Add(faces.ToArray());
Console.WriteLine(count);
count++;
}
return(allFaces);
}
