vs2015+opencv346+yolov3 目标检测学习

文件下载：

https://pjreddie.com/media/files/yolov3.weights

https://github.com/pjreddie/darknet/blob/master/cfg/yolov3.cfg

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

下载yolov3.weights文件（包含预先训练的网络权重），yolov3.cfg文件（包含网络配置）和coco.names文件，其中包含COCO数据集中使用的80个不同的类名。

#include "stdafx.h"
#include <opencv2/opencv.hpp>
#include <opencv2/dnn.hpp>
#include <fstream>

using namespace std;
using namespace cv;

//initialize the parameters
float confThreshold = 0.6;
float nmsThreshold = 0.4;
int inpWidth = 416;
int inpHeight = 416;
vector<std::string> classes;

// Get the names of the output layers
vector<String> getOutputsNames(const cv::dnn::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));

	//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);
	putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(255, 0, 0));
}

// 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;
	cv::dnn::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()
{
	// Load names of classes
	string classesFile = "..\\..\\yolov3\\coco.names";
	ifstream ifs(classesFile.c_str());
	string line;
    classes.clear();
	while (getline(ifs, line))
	{
		classes.push_back(line);
	}

	// Give the configuration and weight files for the model
	String modelConfiguration = "..\\..\\yolov3\\yolov3.cfg";
	String modelWeights = "..\\..\\yolov3\\yolov3.weights";

	// Load the network
	cv::dnn::Net net = cv::dnn::readNetFromDarknet(modelConfiguration, modelWeights);
	net.setPreferableBackend(cv::dnn::DNN_BACKEND_OPENCV);
	net.setPreferableTarget(cv::dnn::DNN_TARGET_CPU);
	
	cv::Mat testImage = imread("..\\..\\yolov3\\dog.jpg", 1);

	// Create a 4D blob from a frame.
	cv::Mat blob;
	cv::dnn::blobFromImage(testImage, 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(testImage, outs);

	return 0;
}