C# Onnx Yolov8-OBB 旋转目标检测行驶证副页条码+编号检测，后续裁剪出图片并摆正显示

效果

模型信息

Model Properties
-------------------------
date：2024-06-25T10:59:15.206586
description：Ultralytics YOLOv8n-obb model trained on C:\Work\yolov8\config\dl-obb.yaml
author：Ultralytics
version：8.1.29
task：obb
license：AGPL-3.0 License (https://ultralytics.com/license)
docs：https://docs.ultralytics.com
stride：32
batch：1
imgsz：[1024, 1024]
names：{0: 'code'}
---------------------------------------------------------------

Inputs
-------------------------
name：images
tensor：Float[1, 3, 1024, 1024]
---------------------------------------------------------------

Outputs
-------------------------
name：output0
tensor：Float[1, 6, 21504]
---------------------------------------------------------------

项目

代码

using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using OpenCvSharp;
using OpenCvSharp.Dnn;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Drawing.Imaging;
using System.IO;
using System.Linq;
using System.Windows.Forms;

namespace Onnx_Yolov8_Demo
{
public partial class Form1 : Form
{
public Form1()
{
InitializeComponent();
}

string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
string image_path = "";
string classer_path;
DateTime dt1 = DateTime.Now;
DateTime dt2 = DateTime.Now;
string model_path;
Mat image;
Mat result_image;
public string[] class_lables;
SessionOptions options;
InferenceSession onnx_session;
Tensor<float> input_tensor;
List<NamedOnnxValue> input_container;
IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
DisposableNamedOnnxValue[] results_onnxvalue;

Tensor<float> result_tensors;

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;
}

button2.Enabled = false;

pictureBox2.Image = null;
pictureBox3.Image = null;
textBox1.Text = "";
Application.DoEvents();

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

float[] result_array;
float factor = (float)(max_image_length / 1024.0);

// 将图片转为RGB通道
Mat image_rgb = new Mat();
Cv2.CvtColor(max_image, image_rgb, ColorConversionCodes.BGR2RGB);
Mat resize_image = new Mat();
Cv2.Resize(image_rgb, resize_image, new OpenCvSharp.Size(1024, 1024));

// Cv2.ImShow("resize_image",resize_image);

// 输入Tensor
for (int y = 0; y < resize_image.Height; y++)
{
for (int x = 0; x < resize_image.Width; x++)
{
input_tensor[0, 0, y, x] = resize_image.At<Vec3b>(y, x)[0] / 255f;
input_tensor[0, 1, y, x] = resize_image.At<Vec3b>(y, x)[1] / 255f;
input_tensor[0, 2, y, x] = resize_image.At<Vec3b>(y, x)[2] / 255f;
}
}

//将 input_tensor 放入一个输入参数的容器，并指定名称
input_container.Add(NamedOnnxValue.CreateFromTensor("images", input_tensor));

dt1 = DateTime.Now;
//运行 Inference 并获取结果
result_infer = onnx_session.Run(input_container);
dt2 = DateTime.Now;

// 将输出结果转为DisposableNamedOnnxValue数组
results_onnxvalue = result_infer.ToArray();

// 读取第一个节点输出并转为Tensor数据
result_tensors = results_onnxvalue[0].AsTensor<float>();

result_array = result_tensors.ToArray();

Mat result_data = new Mat(6, 21504, MatType.CV_32F, result_array);
result_data = result_data.T();
string s = result_data.Dump();
List<Rect2d> position_boxes = new List<Rect2d>();
List<int> class_ids = new List<int>();
List<float> confidences = new List<float>();
List<float> rotations = new List<float>();
// Preprocessing output results
for (int i = 0; i < result_data.Rows; i++)
{
Mat classes_scores = new Mat(result_data, new Rect(4, i, 1, 1));
string s2 = classes_scores.Dump();
OpenCvSharp.Point max_classId_point, min_classId_point;
double max_score, min_score;
// Obtain the maximum value and its position in a set of data
Cv2.MinMaxLoc(classes_scores, out min_score, out max_score,
out min_classId_point, out max_classId_point);
// Confidence level between 0 ~ 1
// Obtain identification box information
if (max_score > 0.5)
{
float cx = result_data.At<float>(i, 0);
float cy = result_data.At<float>(i, 1);
float ow = result_data.At<float>(i, 2);
float oh = result_data.At<float>(i, 3);
double x = (cx - 0.5 * ow) * factor;
double y = (cy - 0.5 * oh) * factor;
double width = ow * factor;
double height = oh * factor;
Rect2d box = new Rect2d();
box.X = x;
box.Y = y;
box.Width = width;
box.Height = height;
position_boxes.Add(box);
class_ids.Add(max_classId_point.X);
confidences.Add((float)max_score);
rotations.Add(result_data.At<float>(i, 5));
}
}

// NMS
int[] indexes = new int[position_boxes.Count];
CvDnn.NMSBoxes(position_boxes, confidences, 0.5f, 0.5f, out indexes);
List<RotatedRect> rotated_rects = new List<RotatedRect>();
for (int i = 0; i < indexes.Length; i++)
{
int index = indexes[i];
float w = (float)position_boxes[index].Width;
float h = (float)position_boxes[index].Height;
float x = (float)position_boxes[index].X + w / 2;
float y = (float)position_boxes[index].Y + h / 2;
float r = rotations[index];
float w_ = w > h ? w : h;
float h_ = w > h ? h : w;
r = (float)((w > h ? r : (float)(r + Math.PI / 2)) % Math.PI);
RotatedRect rotate = new RotatedRect(new Point2f(x, y), new Size2f(w_, h_), (float)(r * 180.0 / Math.PI));

if (rotate.Angle>90)
{
rotate.Angle = rotate.Angle-180;
}
rotated_rects.Add(rotate);
}

result_image = image.Clone();

for (int i = 0; i < indexes.Length; i++)
{
int index = indexes[i];

if (confidences[index]<0.7)
{
continue;
}

Point2f[] points = rotated_rects[i].Points();

//裁剪出需要的图片
Mat codeMat = GetRotateCropImage(image, rotated_rects[i]);
pictureBox3.Image = new Bitmap(codeMat.ToMemoryStream());

for (int j = 0; j < 4; j++)
{
Cv2.Line(result_image, (OpenCvSharp.Point)points[j], (OpenCvSharp.Point)points[(j + 1) % 4], new Scalar(0, 255, 0), 2, LineTypes.Link8);
}

Cv2.PutText(result_image, class_lables[class_ids[index]] + "-" + confidences[index].ToString("0.00"),
(OpenCvSharp.Point)points[0], HersheyFonts.HersheySimplex, 0.8, new Scalar(0, 0, 255), 2);

pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());

}

textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

button2.Enabled = true;
}

private Mat GetRotateCropImage(Mat src, RotatedRect rect)
{
bool wider = rect.Size.Width > rect.Size.Height;
float angle = rect.Angle;
OpenCvSharp.Size srcSize = src.Size();
Rect boundingRect = rect.BoundingRect();

int expTop = Math.Max(0, 0 - boundingRect.Top);
int expBottom = Math.Max(0, boundingRect.Bottom - srcSize.Height);
int expLeft = Math.Max(0, 0 - boundingRect.Left);
int expRight = Math.Max(0, boundingRect.Right - srcSize.Width);

Rect rectToExp = boundingRect + new OpenCvSharp.Point(expTop, expLeft);
Rect roiRect = Rect.FromLTRB(
boundingRect.Left + expLeft,
boundingRect.Top + expTop,
boundingRect.Right - expRight,
boundingRect.Bottom - expBottom);
Mat boundingMat = src[roiRect];

Mat expanded = boundingMat.CopyMakeBorder(expTop, expBottom, expLeft, expRight, BorderTypes.Replicate);
Point2f[] rp = rect.Points()
.Select(v => new Point2f(v.X - rectToExp.X, v.Y - rectToExp.Y))
.ToArray();

Point2f[] srcPoints = new[] { rp[0], rp[3], rp[2], rp[1] };

if (wider == true && angle >= 0 && angle < 45)
{
srcPoints = new[] { rp[1], rp[2], rp[3], rp[0] };
}

var ptsDst0 = new Point2f(0, 0);
var ptsDst1 = new Point2f(rect.Size.Width, 0);
var ptsDst2 = new Point2f(rect.Size.Width, rect.Size.Height);
var ptsDst3 = new Point2f(0, rect.Size.Height);

Mat matrix = Cv2.GetPerspectiveTransform(srcPoints, new[] { ptsDst0, ptsDst1, ptsDst2, ptsDst3 });

Mat dest = expanded.WarpPerspective(matrix, new OpenCvSharp.Size(rect.Size.Width, rect.Size.Height), InterpolationFlags.Nearest, BorderTypes.Replicate);

if (rect.Angle<0)
{
Cv2.Flip(dest, dest, FlipMode.X);
}

boundingMat.Dispose();
expanded.Dispose();
matrix.Dispose();

return dest;
}

private void Form1_Load(object sender, EventArgs e)
{
model_path = "model/best.onnx";
classer_path = "model/lable.txt";

// 创建输出会话，用于输出模型读取信息
options = new SessionOptions();
options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行

// 创建推理模型类，读取本地模型文件
onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径

// 输入Tensor
input_tensor = new DenseTensor<float>(new[] { 1, 3, 1024, 1024 });
// 创建输入容器
input_container = new List<NamedOnnxValue>();

List<string> str = new List<string>();
StreamReader sr = new StreamReader(classer_path);
string line;
while ((line = sr.ReadLine()) != null)
{
str.Add(line);
}
class_lables = str.ToArray();

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

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

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

SaveFileDialog sdf = new SaveFileDialog();
private void button3_Click(object sender, EventArgs e)
{
if (pictureBox3.Image == null)
{
return;
}
Bitmap output = new Bitmap(pictureBox3.Image);
sdf.Title = "保存";
sdf.Filter = "Images (*.jpg)|*.jpg|Images (*.png)|*.png|Images (*.bmp)|*.bmp";
if (sdf.ShowDialog() == DialogResult.OK)
{
switch (sdf.FilterIndex)
{
case 1:
{
output.Save(sdf.FileName, ImageFormat.Jpeg);
break;
}
case 2:
{
output.Save(sdf.FileName, ImageFormat.Png);
break;
}
case 3:
{
output.Save(sdf.FileName, ImageFormat.Bmp);
break;
}
}
MessageBox.Show("保存成功，位置：" + sdf.FileName);
}
}
}
}

using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using OpenCvSharp;
using OpenCvSharp.Dnn;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Drawing.Imaging;
using System.IO;
using System.Linq;
using System.Windows.Forms;

namespace Onnx_Yolov8_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";
        string classer_path;
        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;
        Mat result_image;
        public string[] class_lables;
        SessionOptions options;
        InferenceSession onnx_session;
        Tensor<float> input_tensor;
        List<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;

        Tensor<float> result_tensors;

        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;
            }

            button2.Enabled = false;

            pictureBox2.Image = null;
            pictureBox3.Image = null;
            textBox1.Text = "";
            Application.DoEvents();

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

            float[] result_array;
            float factor = (float)(max_image_length / 1024.0);

            // 将图片转为RGB通道
            Mat image_rgb = new Mat();
            Cv2.CvtColor(max_image, image_rgb, ColorConversionCodes.BGR2RGB);
            Mat resize_image = new Mat();
            Cv2.Resize(image_rgb, resize_image, new OpenCvSharp.Size(1024, 1024));

           // Cv2.ImShow("resize_image",resize_image);

            // 输入Tensor
            for (int y = 0; y < resize_image.Height; y++)
            {
                for (int x = 0; x < resize_image.Width; x++)
                {
                    input_tensor[0, 0, y, x] = resize_image.At<Vec3b>(y, x)[0] / 255f;
                    input_tensor[0, 1, y, x] = resize_image.At<Vec3b>(y, x)[1] / 255f;
                    input_tensor[0, 2, y, x] = resize_image.At<Vec3b>(y, x)[2] / 255f;
                }
            }

            //将 input_tensor 放入一个输入参数的容器，并指定名称
            input_container.Add(NamedOnnxValue.CreateFromTensor("images", input_tensor));

            dt1 = DateTime.Now;
            //运行 Inference 并获取结果
            result_infer = onnx_session.Run(input_container);
            dt2 = DateTime.Now;

            // 将输出结果转为DisposableNamedOnnxValue数组
            results_onnxvalue = result_infer.ToArray();

            // 读取第一个节点输出并转为Tensor数据
            result_tensors = results_onnxvalue[0].AsTensor<float>();

            result_array = result_tensors.ToArray();

            Mat result_data = new Mat(6, 21504, MatType.CV_32F, result_array);
            result_data = result_data.T();
            string s = result_data.Dump();
            List<Rect2d> position_boxes = new List<Rect2d>();
            List<int> class_ids = new List<int>();
            List<float> confidences = new List<float>();
            List<float> rotations = new List<float>();
            // Preprocessing output results
            for (int i = 0; i < result_data.Rows; i++)
            {
                Mat classes_scores = new Mat(result_data, new Rect(4, i, 1, 1));
                string s2 = classes_scores.Dump();
                OpenCvSharp.Point max_classId_point, min_classId_point;
                double max_score, min_score;
                // Obtain the maximum value and its position in a set of data
                Cv2.MinMaxLoc(classes_scores, out min_score, out max_score,
                    out min_classId_point, out max_classId_point);
                // Confidence level between 0 ~ 1
                // Obtain identification box information
                if (max_score > 0.5)
                {
                    float cx = result_data.At<float>(i, 0);
                    float cy = result_data.At<float>(i, 1);
                    float ow = result_data.At<float>(i, 2);
                    float oh = result_data.At<float>(i, 3);
                    double x = (cx - 0.5 * ow) * factor;
                    double y = (cy - 0.5 * oh) * factor;
                    double width = ow * factor;
                    double height = oh * factor;
                    Rect2d box = new Rect2d();
                    box.X = x;
                    box.Y = y;
                    box.Width = width;
                    box.Height = height;
                    position_boxes.Add(box);
                    class_ids.Add(max_classId_point.X);
                    confidences.Add((float)max_score);
                    rotations.Add(result_data.At<float>(i, 5));
                }
            }



            // NMS 
            int[] indexes = new int[position_boxes.Count];
            CvDnn.NMSBoxes(position_boxes, confidences, 0.5f, 0.5f, out indexes);
            List<RotatedRect> rotated_rects = new List<RotatedRect>();
            for (int i = 0; i < indexes.Length; i++)
            {
                int index = indexes[i];
                float w = (float)position_boxes[index].Width;
                float h = (float)position_boxes[index].Height;
                float x = (float)position_boxes[index].X + w / 2;
                float y = (float)position_boxes[index].Y + h / 2;
                float r = rotations[index];
                float w_ = w > h ? w : h;
                float h_ = w > h ? h : w;
                r = (float)((w > h ? r : (float)(r + Math.PI / 2)) % Math.PI);
                RotatedRect rotate = new RotatedRect(new Point2f(x, y), new Size2f(w_, h_), (float)(r * 180.0 / Math.PI));

                if (rotate.Angle>90)
                {
                    rotate.Angle =  rotate.Angle-180;
                }
                rotated_rects.Add(rotate);
            }

            result_image = image.Clone();

            for (int i = 0; i < indexes.Length; i++)
            {
                int index = indexes[i];

                if (confidences[index]<0.7)
                {
                    continue;
                }

                Point2f[] points = rotated_rects[i].Points();

                //裁剪出需要的图片
                Mat codeMat = GetRotateCropImage(image, rotated_rects[i]);
                pictureBox3.Image = new Bitmap(codeMat.ToMemoryStream());

                for (int j = 0; j < 4; j++)
                {
                    Cv2.Line(result_image, (OpenCvSharp.Point)points[j], (OpenCvSharp.Point)points[(j + 1) % 4], new Scalar(0, 255, 0), 2, LineTypes.Link8);
                }

                Cv2.PutText(result_image, class_lables[class_ids[index]] + "-" + confidences[index].ToString("0.00"),
                    (OpenCvSharp.Point)points[0], HersheyFonts.HersheySimplex, 0.8, new Scalar(0, 0, 255), 2);

                pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());

            }

          
            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

            button2.Enabled = true;
        }

        private Mat GetRotateCropImage(Mat src, RotatedRect rect)
        {
            bool wider = rect.Size.Width > rect.Size.Height;
            float angle = rect.Angle;
            OpenCvSharp.Size srcSize = src.Size();
            Rect boundingRect = rect.BoundingRect();

            int expTop = Math.Max(0, 0 - boundingRect.Top);
            int expBottom = Math.Max(0, boundingRect.Bottom - srcSize.Height);
            int expLeft = Math.Max(0, 0 - boundingRect.Left);
            int expRight = Math.Max(0, boundingRect.Right - srcSize.Width);

            Rect rectToExp = boundingRect + new OpenCvSharp.Point(expTop, expLeft);
            Rect roiRect = Rect.FromLTRB(
                boundingRect.Left + expLeft,
                boundingRect.Top + expTop,
                boundingRect.Right - expRight,
                boundingRect.Bottom - expBottom);
            Mat boundingMat = src[roiRect];


            Mat expanded = boundingMat.CopyMakeBorder(expTop, expBottom, expLeft, expRight, BorderTypes.Replicate);
            Point2f[] rp = rect.Points()
                .Select(v => new Point2f(v.X - rectToExp.X, v.Y - rectToExp.Y))
                .ToArray();


            Point2f[] srcPoints = new[] { rp[0], rp[3], rp[2], rp[1] };

            if (wider == true && angle >= 0 && angle < 45)
            {
                srcPoints = new[] { rp[1], rp[2], rp[3], rp[0] };
            }

            var ptsDst0 = new Point2f(0, 0);
            var ptsDst1 = new Point2f(rect.Size.Width, 0);
            var ptsDst2 = new Point2f(rect.Size.Width, rect.Size.Height);
            var ptsDst3 = new Point2f(0, rect.Size.Height);

            Mat matrix = Cv2.GetPerspectiveTransform(srcPoints, new[] { ptsDst0, ptsDst1, ptsDst2, ptsDst3 });

            Mat dest = expanded.WarpPerspective(matrix, new OpenCvSharp.Size(rect.Size.Width, rect.Size.Height), InterpolationFlags.Nearest, BorderTypes.Replicate);

            if (rect.Angle<0)
            {
                Cv2.Flip(dest, dest, FlipMode.X);
            }

            boundingMat.Dispose();
            expanded.Dispose();
            matrix.Dispose();

            return dest;
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            model_path = "model/best.onnx";
            classer_path = "model/lable.txt";

            // 创建输出会话，用于输出模型读取信息
            options = new SessionOptions();
            options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
            options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行

            // 创建推理模型类，读取本地模型文件
            onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径

            // 输入Tensor
            input_tensor = new DenseTensor<float>(new[] { 1, 3, 1024, 1024 });
            // 创建输入容器
            input_container = new List<NamedOnnxValue>();

            List<string> str = new List<string>();
            StreamReader sr = new StreamReader(classer_path);
            string line;
            while ((line = sr.ReadLine()) != null)
            {
                str.Add(line);
            }
            class_lables = str.ToArray();

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

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

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

        SaveFileDialog sdf = new SaveFileDialog();
        private void button3_Click(object sender, EventArgs e)
        {
            if (pictureBox3.Image == null)
            {
                return;
            }
            Bitmap output = new Bitmap(pictureBox3.Image);
            sdf.Title = "保存";
            sdf.Filter = "Images (*.jpg)|*.jpg|Images (*.png)|*.png|Images (*.bmp)|*.bmp";
            if (sdf.ShowDialog() == DialogResult.OK)
            {
                switch (sdf.FilterIndex)
                {
                    case 1:
                        {
                            output.Save(sdf.FileName, ImageFormat.Jpeg);
                            break;
                        }
                    case 2:
                        {
                            output.Save(sdf.FileName, ImageFormat.Png);
                            break;
                        }
                    case 3:
                        {
                            output.Save(sdf.FileName, ImageFormat.Bmp);
                            break;
                        }
                }
                MessageBox.Show("保存成功，位置：" + sdf.FileName);
            }
        }
    }
}