C# OpenCvSharp DNN FreeYOLO 密集行人检测

目录

效果

模型信息

项目

代码

下载

C# OpenCvSharp DNN FreeYOLO 密集行人检测

效果

模型信息

Inputs
-------------------------
name：input
tensor：Float[1, 3, 192, 320]
---------------------------------------------------------------

Outputs
-------------------------
name：output
tensor：Float[1, 1260, 6]
---------------------------------------------------------------

项目

代码

using OpenCvSharp;
using OpenCvSharp.Dnn;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Linq;
using System.Windows.Forms;

namespace OpenCvSharp_DNN_Demo
{
    public partial class frmMain : Form
    {
        public frmMain()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";

        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;

        float confThreshold;
        float nmsThreshold;

        int num_stride = 3;
        float[] strides = new float[3] { 8.0f, 16.0f, 32.0f };

        string modelpath;

        int inpHeight;
        int inpWidth;

        List class_names;
        int num_class;

        Net opencv_net;
        Mat BN_image;

        Mat image;
        Mat result_image;

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;

            pictureBox1.Image = null;
            pictureBox2.Image = null;
            textBox1.Text = "";

            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            image = new Mat(image_path);
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            confThreshold = 0.6f;
            nmsThreshold = 0.5f;

            modelpath = "model/yolo_free_huge_crowdhuman_192x320.onnx";

            inpHeight = 192;
            inpWidth = 320;

            opencv_net = CvDnn.ReadNetFromOnnx(modelpath);

            class_names = new List();
            class_names.Add("person");
            num_class = 1;

            image_path = "test_img/1.jpg";
            pictureBox1.Image = new Bitmap(image_path);

        }

        private unsafe void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }
            textBox1.Text = "检测中，请稍等……";
            pictureBox2.Image = null;
            Application.DoEvents();

            image = new Mat(image_path);

            float ratio = Math.Min(1.0f * inpHeight / image.Rows, 1.0f * inpWidth / image.Cols);
            int neww = (int)(image.Cols * ratio);
            int newh = (int)(image.Rows * ratio);

            Mat dstimg = new Mat();
            Cv2.Resize(image, dstimg, new OpenCvSharp.Size(neww, newh));

            Cv2.CopyMakeBorder(dstimg, dstimg, 0, inpHeight - newh, 0, inpWidth - neww, BorderTypes.Constant);

            BN_image = CvDnn.BlobFromImage(dstimg);

            //配置图片输入数据
            opencv_net.SetInput(BN_image);

            //模型推理，读取推理结果
            Mat[] outs = new Mat[1] { new Mat() };
            string[] outBlobNames = opencv_net.GetUnconnectedOutLayersNames().ToArray();

            dt1 = DateTime.Now;

            opencv_net.Forward(outs, outBlobNames);

            dt2 = DateTime.Now;

            int num_proposal = outs[0].Size(1);
            int nout = outs[0].Size(2);

            float* pdata = (float*)outs[0].Data;

            List confidences = new List();
            List boxes = new List();
            List classIds = new List();

            for (int n = 0; n < num_stride; n++)
            {
                int num_grid_x = (int)Math.Ceiling(inpWidth / strides[n]);
                int num_grid_y = (int)Math.Ceiling(inpHeight / strides[n]);

                for (int i = 0; i < num_grid_y; i++)
                {
                    for (int j = 0; j < num_grid_x; j++)
                    {
                        float box_score = pdata[4];
                        int max_ind = 0;
                        float max_class_socre = 0;
                        for (int k = 0; k < num_class; k++)
                        {
                            if (pdata[k + 5] > max_class_socre)
                            {
                                max_class_socre = pdata[k + 5];
                                max_ind = k;
                            }
                        }
                        max_class_socre = max_class_socre* box_score;
                        max_class_socre = (float)Math.Sqrt(max_class_socre);

                        if (max_class_socre > confThreshold)
                        {
                            float cx = (0.5f + j + pdata[0]) * strides[n];  //cx
                            float cy = (0.5f + i + pdata[1]) * strides[n];   //cy
                            float w = (float)(Math.Exp(pdata[2]) * strides[n]);   //w
                            float h = (float)(Math.Exp(pdata[3]) * strides[n]);  //h

                            float xmin = (float)((cx - 0.5 * w) / ratio);
                            float ymin = (float)((cy - 0.5 * h) / ratio);
                            float xmax = (float)((cx + 0.5 * w) / ratio);
                            float ymax = (float)((cy + 0.5 * h) / ratio);

                            int left = (int)((cx - 0.5 * w) / ratio);
                            int top = (int)((cy - 0.5 * h) / ratio);
                            int width = (int)(w / ratio);
                            int height = (int)(h / ratio);

                            confidences.Add(max_class_socre);
                            boxes.Add(new Rect(left, top, width, height));
                            classIds.Add(max_ind);
                        }
                        pdata += nout;
                    }
                }

            }

            int[] indices;
            CvDnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, out indices);

            result_image = image.Clone();

            for (int ii = 0; ii < indices.Length; ++ii)
            {
                int idx = indices[ii];
                Rect box = boxes[idx];
                Cv2.Rectangle(result_image, new OpenCvSharp.Point(box.X, box.Y), new OpenCvSharp.Point(box.X + box.Width, box.Y + box.Height), new Scalar(0, 0, 255), 2);
                string label = class_names[classIds[idx]] + ":" + confidences[idx].ToString("0.00");
                Cv2.PutText(result_image, label, new OpenCvSharp.Point(box.X, box.Y - 5), HersheyFonts.HersheySimplex, 1, new Scalar(0, 0, 255), 2);
            }

            pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

        }

        private void pictureBox2_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox2.Image);
        }

        private void pictureBox1_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox1.Image);
        }
    }
}

  1. using OpenCvSharp;
  2. using OpenCvSharp.Dnn;
  3. using System;
  4. using System.Collections.Generic;
  5. using System.Drawing;
  6. using System.Linq;
  7. using System.Windows.Forms;
  8.  
  9. namespace OpenCvSharp_DNN_Demo
  10. {
  11.     public partial class frmMain : Form
  12.     {
  13.         public frmMain()
  14.         {
  15.             InitializeComponent();
  16.         }
  17.  
  18.         string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
  19.         string image_path = "";
  20.  
  21.         DateTime dt1 = DateTime.Now;
  22.         DateTime dt2 = DateTime.Now;
  23.  
  24.         float confThreshold;
  25.         float nmsThreshold;
  26.  
  27.         int num_stride = 3;
  28.         float[] strides = new float[3] { 8.0f, 16.0f, 32.0f };
  29.  
  30.         string modelpath;
  31.  
  32.         int inpHeight;
  33.         int inpWidth;
  34.  
  35.         List<string> class_names;
  36.         int num_class;
  37.  
  38.         Net opencv_net;
  39.         Mat BN_image;
  40.  
  41.         Mat image;
  42.         Mat result_image;
  43.  
  44.         private void button1_Click(object sender, EventArgs e)
  45.         {
  46.             OpenFileDialog ofd = new OpenFileDialog();
  47.             ofd.Filter = fileFilter;
  48.             if (ofd.ShowDialog() != DialogResult.OK) return;
  49.  
  50.             pictureBox1.Image = null;
  51.             pictureBox2.Image = null;
  52.             textBox1.Text = "";
  53.  
  54.             image_path = ofd.FileName;
  55.             pictureBox1.Image = new Bitmap(image_path);
  56.             image = new Mat(image_path);
  57.         }
  58.  
  59.         private void Form1_Load(object sender, EventArgs e)
  60.         {
  61.             confThreshold = 0.6f;
  62.             nmsThreshold = 0.5f;
  63.  
  64.             modelpath = "model/yolo_free_huge_crowdhuman_192x320.onnx";
  65.  
  66.             inpHeight = 192;
  67.             inpWidth = 320;
  68.  
  69.             opencv_net = CvDnn.ReadNetFromOnnx(modelpath);
  70.  
  71.             class_names = new List<string>();
  72.             class_names.Add("person");
  73.             num_class = 1;
  74.  
  75.             image_path = "test_img/1.jpg";
  76.             pictureBox1.Image = new Bitmap(image_path);
  77.  
  78.         }
  79.  
  80.         private unsafe void button2_Click(object sender, EventArgs e)
  81.         {
  82.             if (image_path == "")
  83.             {
  84.                 return;
  85.             }
  86.             textBox1.Text = "检测中，请稍等……";
  87.             pictureBox2.Image = null;
  88.             Application.DoEvents();
  89.  
  90.             image = new Mat(image_path);
  91.  
  92.             float ratio = Math.Min(1.0f * inpHeight / image.Rows, 1.0f * inpWidth / image.Cols);
  93.             int neww = (int)(image.Cols * ratio);
  94.             int newh = (int)(image.Rows * ratio);
  95.  
  96.             Mat dstimg = new Mat();
  97.             Cv2.Resize(image, dstimg, new OpenCvSharp.Size(neww, newh));
  98.  
  99.             Cv2.CopyMakeBorder(dstimg, dstimg, 0, inpHeight - newh, 0, inpWidth - neww, BorderTypes.Constant);
  100.  
  101.             BN_image = CvDnn.BlobFromImage(dstimg);
  102.  
  103.             //配置图片输入数据
  104.             opencv_net.SetInput(BN_image);
  105.  
  106.             //模型推理，读取推理结果
  107.             Mat[] outs = new Mat[1] { new Mat() };
  108.             string[] outBlobNames = opencv_net.GetUnconnectedOutLayersNames().ToArray();
  109.  
  110.             dt1 = DateTime.Now;
  111.  
  112.             opencv_net.Forward(outs, outBlobNames);
  113.  
  114.             dt2 = DateTime.Now;
  115.  
  116.             int num_proposal = outs[0].Size(1);
  117.             int nout = outs[0].Size(2);
  118.  
  119.             float* pdata = (float*)outs[0].Data;
  120.  
  121.             List<float> confidences = new List<float>();
  122.             List<Rect> boxes = new List<Rect>();
  123.             List<int> classIds = new List<int>();
  124.  
  125.             for (int n = 0; n < num_stride; n++)
  126.             {
  127.                 int num_grid_x = (int)Math.Ceiling(inpWidth / strides[n]);
  128.                 int num_grid_y = (int)Math.Ceiling(inpHeight / strides[n]);
  129.  
  130.                 for (int i = 0; i < num_grid_y; i++)
  131.                 {
  132.                     for (int j = 0; j < num_grid_x; j++)
  133.                     {
  134.                         float box_score = pdata[4];
  135.                         int max_ind = 0;
  136.                         float max_class_socre = 0;
  137.                         for (int k = 0; k < num_class; k++)
  138.                         {
  139.                             if (pdata[k + 5] > max_class_socre)
  140.                             {
  141.                                 max_class_socre = pdata[k + 5];
  142.                                 max_ind = k;
  143.                             }
  144.                         }
  145.                         max_class_socre = max_class_socre* box_score;
  146.                         max_class_socre = (float)Math.Sqrt(max_class_socre);
  147.  
  148.                         if (max_class_socre > confThreshold)
  149.                         {
  150.                             float cx = (0.5f + j + pdata[0]) * strides[n];  //cx
  151.                             float cy = (0.5f + i + pdata[1]) * strides[n];   //cy
  152.                             float w = (float)(Math.Exp(pdata[2]) * strides[n]);   //w
  153.                             float h = (float)(Math.Exp(pdata[3]) * strides[n]);  //h
  154.  
  155.                             float xmin = (float)((cx - 0.5 * w) / ratio);
  156.                             float ymin = (float)((cy - 0.5 * h) / ratio);
  157.                             float xmax = (float)((cx + 0.5 * w) / ratio);
  158.                             float ymax = (float)((cy + 0.5 * h) / ratio);
  159.  
  160.                             int left = (int)((cx - 0.5 * w) / ratio);
  161.                             int top = (int)((cy - 0.5 * h) / ratio);
  162.                             int width = (int)(w / ratio);
  163.                             int height = (int)(h / ratio);
  164.  
  165.                             confidences.Add(max_class_socre);
  166.                             boxes.Add(new Rect(left, top, width, height));
  167.                             classIds.Add(max_ind);
  168.                         }
  169.                         pdata += nout;
  170.                     }
  171.                 }
  172.  
  173.             }
  174.  
  175.             int[] indices;
  176.             CvDnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, out indices);
  177.  
  178.             result_image = image.Clone();
  179.  
  180.             for (int ii = 0; ii < indices.Length; ++ii)
  181.             {
  182.                 int idx = indices[ii];
  183.                 Rect box = boxes[idx];
  184.                 Cv2.Rectangle(result_image, new OpenCvSharp.Point(box.X, box.Y), new OpenCvSharp.Point(box.X + box.Width, box.Y + box.Height), new Scalar(0, 0, 255), 2);
  185.                 string label = class_names[classIds[idx]] + ":" + confidences[idx].ToString("0.00");
  186.                 Cv2.PutText(result_image, label, new OpenCvSharp.Point(box.X, box.Y - 5), HersheyFonts.HersheySimplex, 1, new Scalar(0, 0, 255), 2);
  187.             }
  188.  
  189.             pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
  190.             textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
  191.  
  192.         }
  193.  
  194.         private void pictureBox2_DoubleClick(object sender, EventArgs e)
  195.         {
  196.             Common.ShowNormalImg(pictureBox2.Image);
  197.         }
  198.  
  199.         private void pictureBox1_DoubleClick(object sender, EventArgs e)
  200.         {
  201.             Common.ShowNormalImg(pictureBox1.Image);
  202.         }
  203.     }
  204. }

下载

可执行程序exe下载

源码下载

天天代码码天天
微信公众号
.NET 人工智能实践
注：本文转载自blog.csdn.net的天天代码码天天的文章"https://lw112190.blog.csdn.net/article/details/135400353"。版权归原作者所有，此博客不拥有其著作权，亦不承担相应法律责任。如有侵权，请联系我们删除。
复制链接
相关推荐
发表评论

评论记录：

未查询到任何数据！