C# OpenCvSharp Yolov11 Pose 手部关键点检测

目录

效果

模型信息

项目

代码

下载

参考

效果

模型信息

Model Properties
-------------------------
date：2024-12-04T17:34:08.564548
description：Ultralytics YOLO11n-pose model trained on data.yaml
author：Ultralytics
version：8.3.5
kpt_shape：[21, 3]
task：pose
license：AGPL-3.0 License (https://ultralytics.com/license)
docs：https://docs.ultralytics.com
stride：32
batch：1
imgsz：[640, 640]
names：{0: 'hand'}
---------------------------------------------------------------

Inputs
-------------------------
name：images
tensor：Float[1, 3, 640, 640]
---------------------------------------------------------------

Outputs
-------------------------
name：output0
tensor：Float[1, 68, 8400]
---------------------------------------------------------------

项目

代码

using OpenCvSharp;
using OpenCvSharp.Dnn;
using System;
using System.Drawing;
using System.Text;
using System.Windows.Forms;

namespace OpenCvSharp_Yolov8_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

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

        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;

        PoseResult result_pro;
        Mat result_mat;
        Mat result_image;
        Mat result_mat_to_float;

        Net opencv_net;
        Mat BN_image;

        float[] result_array;
        float[] factors;

        int max_image_length;
        Mat max_image;
        Rect roi;

        Result result;
        StringBuilder sb = new StringBuilder();

        private void Form1_Load(object sender, EventArgs e)
        {
            startupPath = System.Windows.Forms.Application.StartupPath;
            model_path = startupPath + "\\best.onnx";
            classer_path = startupPath + "\\lable.txt";

            //初始化网络类，读取本地模型
            opencv_net = CvDnn.ReadNetFromOnnx(model_path);

            result_array = new float[8400 * 68];
            factors = new float[2];

            result_pro = new PoseResult(factors);

            //test.jpg
            image_path = "test.jpg";
            pictureBox1.Image = new Bitmap(image_path);
            textBox1.Text = "";
            image = new Mat(image_path);
            pictureBox2.Image = null;
        }

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;
            pictureBox1.Image = null;
            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            textBox1.Text = "";
            image = new Mat(image_path);
            pictureBox2.Image = null;
        }

        private void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }

            //缩放图片
            max_image_length = image.Cols > image.Rows ? image.Cols : image.Rows;
            max_image = Mat.Zeros(new OpenCvSharp.Size(max_image_length, max_image_length), MatType.CV_8UC3);
            roi = new Rect(0, 0, image.Cols, image.Rows);
            image.CopyTo(new Mat(max_image, roi));

            factors[0] = factors[1] = (float)(max_image_length / 640.0);

            //数据归一化处理
            BN_image = CvDnn.BlobFromImage(max_image, 1 / 255.0, new OpenCvSharp.Size(640, 640), new Scalar(0, 0, 0), true, false);

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

            dt1 = DateTime.Now;
            //模型推理，读取推理结果
            result_mat = opencv_net.Forward();
            dt2 = DateTime.Now;

            //将推理结果转为float数据类型
            result_mat_to_float = new Mat(8400, 68, MatType.CV_32F, result_mat.Data);

            //将数据读取到数组中
            result_mat_to_float.GetArray<float>(out result_array);

            result = result_pro.process_result(result_array);

            result_image = result_pro.draw_result(result, image.Clone());

            if (!result_image.Empty())
            {
                pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
                sb.Clear();
                sb.AppendLine("推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms");
                sb.AppendLine("------------------------------");
                textBox1.Text = sb.ToString();
            }
            else
            {
                textBox1.Text = "无信息";
            }

        }
    }
}
 

using OpenCvSharp;
using OpenCvSharp.Dnn;
using System;
using System.Drawing;
using System.Text;
using System.Windows.Forms;

namespace OpenCvSharp_Yolov8_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

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

        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;

        PoseResult result_pro;
        Mat result_mat;
        Mat result_image;
        Mat result_mat_to_float;

        Net opencv_net;
        Mat BN_image;

        float[] result_array;
        float[] factors;

        int max_image_length;
        Mat max_image;
        Rect roi;

        Result result;
        StringBuilder sb = new StringBuilder();

        private void Form1_Load(object sender, EventArgs e)
        {
            startupPath = System.Windows.Forms.Application.StartupPath;
            model_path = startupPath + "\\best.onnx";
            classer_path = startupPath + "\\lable.txt";

            //初始化网络类，读取本地模型
            opencv_net = CvDnn.ReadNetFromOnnx(model_path);

            result_array = new float[8400 * 68];
            factors = new float[2];

            result_pro = new PoseResult(factors);

            //test.jpg
            image_path = "test.jpg";
            pictureBox1.Image = new Bitmap(image_path);
            textBox1.Text = "";
            image = new Mat(image_path);
            pictureBox2.Image = null;
        }

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;
            pictureBox1.Image = null;
            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            textBox1.Text = "";
            image = new Mat(image_path);
            pictureBox2.Image = null;
        }

        private void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }

            //缩放图片
            max_image_length = image.Cols > image.Rows ? image.Cols : image.Rows;
            max_image = Mat.Zeros(new OpenCvSharp.Size(max_image_length, max_image_length), MatType.CV_8UC3);
            roi = new Rect(0, 0, image.Cols, image.Rows);
            image.CopyTo(new Mat(max_image, roi));

            factors[0] = factors[1] = (float)(max_image_length / 640.0);

            //数据归一化处理
            BN_image = CvDnn.BlobFromImage(max_image, 1 / 255.0, new OpenCvSharp.Size(640, 640), new Scalar(0, 0, 0), true, false);

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

            dt1 = DateTime.Now;
            //模型推理，读取推理结果
            result_mat = opencv_net.Forward();
            dt2 = DateTime.Now;

            //将推理结果转为float数据类型
            result_mat_to_float = new Mat(8400, 68, MatType.CV_32F, result_mat.Data);

            //将数据读取到数组中
            result_mat_to_float.GetArray<float>(out result_array);

            result = result_pro.process_result(result_array);

            result_image = result_pro.draw_result(result, image.Clone());

            if (!result_image.Empty())
            {
                pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
                sb.Clear();
                sb.AppendLine("推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms");
                sb.AppendLine("------------------------------");
                textBox1.Text = sb.ToString();
            }
            else
            {
                textBox1.Text = "无信息";
            }

        }
    }
}

下载

源码下载

参考

GitHub - chrismuntean/YOLO11n-pose-hands: Trained YOLO11n-pose model on hand keypoints