OpenCV DNN模块官方教程(二)YoloV4目标检测实例

String config = "./model/yolov4.cfg";
String weights = "./model/yolov4.weights";
string classesFile = "./model/coco.names";

// 加载darknet网络
Net net = readNetFromDarknet(config, weights);

// DNN_YOLO_V4.cpp : 此文件包含 "main" 函数。程序执行将在此处开始并结束。
#include "pch.h"

#include<opencv2/opencv.hpp>
#include<opencv2/dnn.hpp>
#include <iostream>
#include <fstream>
#include<istream>
#include<string>

using namespace std;
using namespace cv;
using namespace dnn;

// 初始化参数
float confThreshold = 0.5; // 置信度阈值
float nmsThreshold = 0.4;  // 非极大值抑制(NMS)阈值
int inpWidth = 416;        // 网络输入图像宽度
int inpHeight = 416;       // 网络输入图像高度


// 加载类别名称文件
vector<string>classes;
// Load names of classes
string classesFile = "./model/coco.names";
ifstream ifs(classesFile.c_str());


// 设置模型配置文件和权重
String config = "./model/yolov4.cfg";
String weights = "./model/yolov4.weights";

// 加载网络
Net net = readNetFromDarknet(config, weights);


// 获取输出层名称
vector<String> getOutputsNames(const Net& net)
{
  static vector<String> names;
  if (names.empty())
  {
    //Get the indices of the output layers, i.e. the layers with unconnected outputs
    vector<int> outLayers = net.getUnconnectedOutLayers();

    //get the names of all the layers in the network
    vector<String> layersNames = net.getLayerNames();

    // Get the names of the output layers in names
    names.resize(outLayers.size());
    for (size_t i = 0; i < outLayers.size(); ++i)
      names[i] = layersNames[outLayers[i] - 1];
  }
  return names;
}

// Draw the predicted bounding box
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
{
  //Draw a rectangle displaying the bounding box
  rectangle(frame, Point(left, top), Point(right, bottom), Scalar(0, 0, 255), 2);

  //Get the label for the class name and its confidence
  string label = format("%.2f", conf);
  if (!classes.empty())
  {
    CV_Assert(classId < (int)classes.size());
    label = classes[classId] + ":" + label;
  }

  //Display the label at the top of the bounding box
  int baseLine;
  Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.8, 1, &baseLine);
  top = max(top, labelSize.height);
  putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.8, Scalar(0, 255, 0), 2);
}

// Remove the bounding boxes with low confidence using non-maxima suppression
void postprocess(Mat& frame, const vector<Mat>& outs)
{
  vector<int> classIds;
  vector<float> confidences;
  vector<Rect> boxes;

  for (size_t i = 0; i < outs.size(); ++i)
  {
    // Scan through all the bounding boxes output from the network and keep only the
    // ones with high confidence scores. Assign the box's class label as the class
    // with the highest score for the box.
    float* data = (float*)outs[i].data;
    for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols)
    {
      Mat scores = outs[i].row(j).colRange(5, outs[i].cols);
      Point classIdPoint;
      double confidence;
      // Get the value and location of the maximum score
      minMaxLoc(scores, 0, &confidence, 0, &classIdPoint);
      if (confidence > confThreshold)
      {
        int centerX = (int)(data[0] * frame.cols);
        int centerY = (int)(data[1] * frame.rows);
        int width = (int)(data[2] * frame.cols);
        int height = (int)(data[3] * frame.rows);
        int left = centerX - width / 2;
        int top = centerY - height / 2;

        classIds.push_back(classIdPoint.x);
        confidences.push_back((float)confidence);
        boxes.push_back(Rect(left, top, width, height));
      }
    }
  }

  // Perform non maximum suppression to eliminate redundant overlapping boxes with
  // lower confidences
  vector<int> indices;
  NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
  for (size_t i = 0; i < indices.size(); ++i)
  {
    int idx = indices[i];
    Rect box = boxes[idx];
    drawPred(classIds[idx], confidences[idx], box.x, box.y,
      box.x + box.width, box.y + box.height, frame);
  }
}

int main()
{
  Mat img = imread("./1.jpg");
  if (img.empty())
  {
    cout << "Image read error, please check again!" << endl;
  }
  string line;
  while (getline(ifs, line))
  {
    classes.push_back(line);
  }
  net.setPreferableBackend(DNN_BACKEND_OPENCV);
  net.setPreferableTarget(DNN_TARGET_CPU);
  // Create a 4D blob from a frame.
  Mat blob;
  blobFromImage(img, blob, 1 / 255.0, Size(inpWidth, inpHeight), Scalar(0, 0, 0), true, false);

  //Sets the input to the network
  net.setInput(blob);

  // Runs the forward pass to get output of the output layers
  vector<Mat> outs;
  net.forward(outs, getOutputsNames(net));

  // Remove the bounding boxes with low confidence
  postprocess(img, outs);

  // Put efficiency information. The function getPerfProfile returns the
  // overall time for inference(t) and the timings for each of the layers(in layersTimes)
  vector<double> layersTimes;
  double freq = getTickFrequency() / 1000;
  double t = net.getPerfProfile(layersTimes) / freq;
  string label = format("Inference time for a frame : %.2f ms", t);
  putText(img, label, Point(0, 20), FONT_HERSHEY_SIMPLEX, 0.8, Scalar(255, 255, 0), 2);
  namedWindow("OpenCV_YoloV4_Demo", WINDOW_NORMAL);
  imshow("OpenCV_YoloV4_Demo", img);
  waitKey(0);

  return 0;
}

int main()
{
  string line;
  while (getline(ifs, line))
  {
    classes.push_back(line);
  }
  VideoCapture cap("./cars.mp4");
  Mat frame;
  while (1)
  {
    if (!cap.isOpened())
    {
      cout << "Video open failed, please check!" << endl;
      break;
    }
    cap.read(frame);
    if (frame.empty())
    {
      cout << "frame is empty, please check!" << endl;
      break;
    }
    
    net.setPreferableBackend(DNN_BACKEND_OPENCV);
    net.setPreferableTarget(DNN_TARGET_CPU);
    // Create a 4D blob from a frame.
    Mat blob;
    blobFromImage(frame, blob, 1 / 255.0, Size(inpWidth, inpHeight), Scalar(0, 0, 0), true, false);

    //Sets the input to the network
    net.setInput(blob);

    // Runs the forward pass to get output of the output layers
    vector<Mat> outs;
    net.forward(outs, getOutputsNames(net));

    // Remove the bounding boxes with low confidence
    postprocess(frame, outs);

    // Put efficiency information. The function getPerfProfile returns the
    // overall time for inference(t) and the timings for each of the layers(in layersTimes)
    vector<double> layersTimes;
    double freq = getTickFrequency() / 1000;
    double t = net.getPerfProfile(layersTimes) / freq;
    string label = format("Inference time for a frame : %.2f ms", t);
    putText(frame, label, Point(0, 20), FONT_HERSHEY_SIMPLEX, 0.8, Scalar(255, 255, 0), 2);
    namedWindow("OpenCV_YoloV4_Demo", WINDOW_NORMAL);
    imshow("OpenCV_YoloV4_Demo", frame);
    int c = waitKey(1);
    if (c == 27)
      break;
  }
  return 0;
}