C++调用Yolov3模型实现目标检测

C++调用Yolov3模型实现目标检测

使用开源权重文件，此训练模型包含80种物体

文件下载地址：

预训练权重文件：
https://pjreddie.com/media/files/yolov3.weights

网络配置文件：
https://github.com/pjreddie/darknet/blob/master/cfg/yolov3.cfg

coco.names：
https://github.com/pjreddie/darknet/blob/master/data/coco.names

计算机环境：Visual Studio配置opencv

下面展示 代码。

#include <fstream>
#include <sstream>
#include <iostream>

#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>

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

string pro_dir = "E:/process/VSproject/"; //项目根目录

float confThreshold = 0.5; // Confidence threshold
float nmsThreshold = 0.4;  // Non-maximum suppression threshold
int inpWidth = 416;  // Width of network's input image
int inpHeight = 416; // Height of network's input image
vector<string> classes;

// Remove the bounding boxes with low confidence using non-maxima suppression
void postprocess(Mat& frame, const vector<Mat>& out);
// Draw the predicted bounding box
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
// Get the names of the output layers
vector<String> getOutputsNames(const Net& net);
void detect_image(string image_path, string modelWeights, string modelConfiguration, string classesFile);
void detect_video(string video_path, string modelWeights, string modelConfiguration, string classesFile);

int main(int argc, char** argv)
{
 	// Give the configuration and weight files for the model
 	String modelConfiguration = pro_dir + "yolov3/yolov3.cfg";
 	String modelWeights = pro_dir + "yolov3/yolov3.weights";
 	string image_path = pro_dir + "yolov3/dog.jpg";
 	string classesFile = pro_dir + "yolov3/coco.names";// "coco.names";

 	//detect_image(image_path, modelWeights, modelConfiguration, classesFile);
 	string video_path = pro_dir + "yolov3/movie.avi";
 	detect_video(video_path, modelWeights, modelConfiguration, classesFile);
 	cv::waitKey(0);

 	return 0;
}

void detect_image(string image_path, string modelWeights, string modelConfiguration, string classesFile) {
 	// Load names of classes
 	ifstream ifs(classesFile.c_str());
 	string line;
 	while (getline(ifs, line)) classes.push_back(line);
 
 	// Load the network
 	Net net = readNetFromDarknet(modelConfiguration, modelWeights);
 	net.setPreferableBackend(DNN_BACKEND_OPENCV);
 	net.setPreferableTarget(DNN_TARGET_OPENCL);
 
 	// Open a video file or an image file or a camera stream.
 	string str, outputFile;
 	cv::Mat frame = cv::imread(image_path);
 
 	// Create a window
 	static const string kWinName = "Deep learning object detection in OpenCV";
 	namedWindow(kWinName, WINDOW_NORMAL);
 
 	// Stop the program if reached end of video
 	// Create a 4D blob from a frame.
 	Mat blob;
 	blobFromImage(frame, blob, 1 / 255.0, cvSize(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, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 255));
 
 	// Write the frame with the detection boxes
 	imshow(kWinName, frame);
 	cv::waitKey(30);
}

void detect_video(string video_path, string modelWeights, string modelConfiguration, string classesFile) {
	string outputFile = "./yolo_out_cpp.avi";;
	
	// Load names of classes
	ifstream ifs(classesFile.c_str());
	string line;
	while (getline(ifs, line)) classes.push_back(line);
	
	// Load the network
	Net net = readNetFromDarknet(modelConfiguration, modelWeights);
	net.setPreferableBackend(DNN_BACKEND_OPENCV);
	net.setPreferableTarget(DNN_TARGET_CPU);
	
	// Open a video file or an image file or a camera stream.
	VideoCapture cap;
	
	//VideoWriter video;
	Mat frame, blob;
	try {
	
		// Open the video file
		ifstream ifile(video_path);
		if (!ifile) throw("error");
		cap.open(video_path);
	}
	catch (...) {
		cout << "Could not open the input image/video stream" << endl;
		return;
	}
	
	// Create a window
	static const string kWinName = "Deep learning object detection in OpenCV";
	namedWindow(kWinName, WINDOW_NORMAL);
	
	// Process frames.
	while (waitKey(1) < 0)
	{
	
		// get frame from the video
		cap >> frame;
		
		// Stop the program if reached end of video
		if (frame.empty()) {
			cout << "Done processing !!!" << endl;
			cout << "Output file is stored as " << outputFile << endl;
			waitKey(3000);
			break;
		}
		
		// Create a 4D blob from a frame.
		blobFromImage(frame, blob, 1 / 255.0, cvSize(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, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 255));
		
		// Write the frame with the detection boxes
		Mat detectedFrame;
		frame.convertTo(detectedFrame, CV_8U);
		
		//video.write(detectedFrame);
		imshow(kWinName, frame);
	}
	cap.release();
	
	//video.release();
}
// 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);
	}
}

// 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(255, 178, 50), 3);
	//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, 0.5, 1, &baseLine);
	top = max(top, labelSize.height);
	rectangle(frame, Point(left, top - round(1.5*labelSize.height)), Point(left + round(1.5*labelSize.width), top + baseLine), Scalar(255, 255, 255), FILLED);
	putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0, 0, 0), 1);
}
// Get the names of the output layers
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;
}
 

效果展示

后续将介绍如何使用openvino工具加速模型的推理速度