OpenCV 学习笔记（0）两幅图像标定配准

参考教程  

依赖opencv扩展库，使用sifi匹配

保存配准信息  

 "./config/calibratedPara.yaml" 

#include <iostream>
#include<opencv2/highgui/highgui.hpp>
#include<opencv2/imgproc/imgproc.hpp>
#include <opencv2/opencv.hpp> 
#include<opencv2/xfeatures2d.hpp>
#include<opencv2/core/core.hpp>


#define PATH_XMAL           "./config/calibratedPara.yaml" 
#define IMG_WIDTH 			2592//2592
#define IMG_HEIGHT  		1944//2048

using namespace cv;
using namespace std;
using namespace cv::xfeatures2d;//只有加上这句命名空间，SiftFeatureDetector and SiftFeatureExtractor才可以使用



								/******************************************************
								*name		:Rect CalcCorners(const Mat& H, const Mat& src)
								*function	:通过H计算图片角点位置，返回左上和宽高
								*time		:2019-4-28
								********************************************************/
Rect CalcCorners(const Mat& H, const Mat& src)
{
	double v1[3];
	Mat _V1 = Mat(3, 1, CV_64FC1, v1);
	//左上角(0,0,1)
	Mat _V2 = (Mat_<double>(3, 1) << 0, 0, 1);
	_V1 = H * _V2;
	Point _left_top;
	_left_top.x = v1[0] / v1[2];
	_left_top.y = v1[1] / v1[2];
	//左下角(0,src.rows,1)
	_V2 = (Mat_<double>(3, 1) << 0, src.rows, 1);
	_V1 = H * _V2;
	Point _left_bottom;
	_left_bottom.x = v1[0] / v1[2];
	_left_bottom.y = v1[1] / v1[2];
	//右上角(src.cols,0,1)
	_V2 = (Mat_<double>(3, 1) << src.cols, 0, 1);
	_V1 = H * _V2;
	Point _right_top;
	_right_top.x = v1[0] / v1[2];
	_right_top.y = v1[1] / v1[2];
	//右下角(src.cols,src.rows,1)
	_V2 = (Mat_<double>(3, 1) << src.cols, src.rows, 1);
	_V1 = H * _V2;
	Point _right_bottom;
	_right_bottom.x = v1[0] / v1[2];
	_right_bottom.y = v1[1] / v1[2];
	int _x1 = (int)max(_left_bottom.x, _left_top.x);
	int _y1 = (int)max(_left_top.y, _right_top.y);
	int _x2 = (int)min(_right_top.x, _right_bottom.x);
	int _y2 = (int)min(_left_bottom.y, _right_bottom.y);

	cout << "point is " << _x1 << " " << _y1 << " " << _x2 << " " << _y2 << endl;
	if (_x2 > IMG_WIDTH) _x2 = IMG_WIDTH - 1;
	if (_y2 > IMG_HEIGHT) _y2 = IMG_HEIGHT - 1;
	if (_x1 < 0) _x1 = 0;
	if (_y1 < 0) _y1 = 0;

	cout << "point is " << _x1 << " " << _y1 << " " << _x2 << " " << _y2 << endl;

	return Rect(Point(_x1, _y1), Point(_x2, _y2));	//表示左上点和右下点
}


Rect inscrRect;
cv::Mat warpedPic;
cv::Mat Homography;
Mat compicCalibrate;

int main()
{
	//Create SIFT class pointer
	Ptr<Feature2D> f2d = xfeatures2d::SIFT::create();
	//SiftFeatureDetector siftDetector;
	//Loading images
	Mat img_1 = imread("1.bmp");
	Mat img_2 = imread("2.bmp");
	if (!img_1.data || !img_2.data)
	{
		cout << "Reading picture error！" << endl;
		return false;
	}
	//Detect the keypoints
	double t0 = getTickCount();//当前
	vector<KeyPoint> keypoints_1, keypoints_2;
	f2d->detect(img_1, keypoints_1);
	f2d->detect(img_2, keypoints_2);
	cout << "The keypoints number of img1 is:" << keypoints_1.size() << endl;
	cout << "The keypoints number of img2 is:" << keypoints_2.size() << endl;
	//Calculate descriptors (feature vectors)
	Mat descriptors_1, descriptors_2;
	f2d->compute(img_1, keypoints_1, descriptors_1);
	f2d->compute(img_2, keypoints_2, descriptors_2);
	double freq = getTickFrequency();
	double tt = ((double)getTickCount() - t0) / freq;
	cout << "Extract SIFT Time:" << tt << "ms" << endl;
	//画关键点
	Mat img_keypoints_1, img_keypoints_2;
	drawKeypoints(img_1, keypoints_1, img_keypoints_1, Scalar::all(-1), 0);
	drawKeypoints(img_2, keypoints_2, img_keypoints_2, Scalar::all(-1), 0);
	//imshow("img_keypoints_1",img_keypoints_1);
	//imshow("img_keypoints_2",img_keypoints_2);

	//Matching descriptor vector using BFMatcher
	BFMatcher matcher;
	vector<DMatch> matches;
	matcher.match(descriptors_1, descriptors_2, matches);
	cout << "The number of match:" << matches.size() << endl;
	//绘制匹配出的关键点
	Mat img_matches;
	drawMatches(img_1, keypoints_1, img_2, keypoints_2, matches, img_matches);
	//imshow("Match image",img_matches);
	//计算匹配结果中距离最大和距离最小值
	double min_dist = matches[0].distance, max_dist = matches[0].distance;
	for (int m = 0; m < matches.size(); m++)
	{
		if (matches[m].distance<min_dist)
		{
			min_dist = matches[m].distance;
		}
		if (matches[m].distance>max_dist)
		{
			max_dist = matches[m].distance;
		}
	}
	cout << "min dist=" << min_dist << endl;
	cout << "max dist=" << max_dist << endl;
	//筛选出较好的匹配点
	vector<DMatch> goodMatches;
	for (int m = 0; m < matches.size(); m++)
	{
		if (matches[m].distance < 0.6*max_dist)
		{
			goodMatches.push_back(matches[m]);
		}
	}
	cout << "The number of good matches:" << goodMatches.size() << endl;
	//画出匹配结果
	Mat img_out;
	//红色连接的是匹配的特征点数，绿色连接的是未匹配的特征点数
	//matchColor – Color of matches (lines and connected keypoints). If matchColor==Scalar::all(-1) , the color is generated randomly.
	//singlePointColor – Color of single keypoints(circles), which means that keypoints do not have the matches.If singlePointColor == Scalar::all(-1), the color is generated randomly.
	//CV_RGB(0, 255, 0)存储顺序为R-G-B,表示绿色
	drawMatches(img_1, keypoints_1, img_2, keypoints_2, goodMatches, img_out, Scalar::all(-1), CV_RGB(0, 0, 255), Mat(), 2);
	namedWindow("good Matches", 0);
	imshow("good Matches", img_out);
	//RANSAC匹配过程
	vector<DMatch> m_Matches;
	m_Matches = goodMatches;
	int ptCount = goodMatches.size();
	if (ptCount < 100)
	{
		cout << "Don't find enough match points" << endl;
		return 0;
	}

	//坐标转换为float类型
	vector <KeyPoint> RAN_KP1, RAN_KP2;
	//size_t是标准C库中定义的，应为unsigned int，在64位系统中为long unsigned int,在C++中为了适应不同的平台，增加可移植性。
	for (size_t i = 0; i < m_Matches.size(); i++)
	{
		RAN_KP1.push_back(keypoints_1[goodMatches[i].queryIdx]);
		RAN_KP2.push_back(keypoints_2[goodMatches[i].trainIdx]);
		//RAN_KP1是要存储img01中能与img02匹配的点
		//goodMatches存储了这些匹配点对的img01和img02的索引值
	}
	//坐标变换
	vector <Point2f> p01, p02;
	for (size_t i = 0; i < m_Matches.size(); i++)
	{
		p01.push_back(RAN_KP1[i].pt);
		p02.push_back(RAN_KP2[i].pt);
	}
	/*vector <Point2f> img1_corners(4);
	img1_corners[0] = Point(0,0);
	img1_corners[1] = Point(img_1.cols,0);
	img1_corners[2] = Point(img_1.cols, img_1.rows);
	img1_corners[3] = Point(0, img_1.rows);
	vector <Point2f> img2_corners(4);*/
	////求转换矩阵
	//Mat m_homography;
	//vector<uchar> m;
	//m_homography = findHomography(p01, p02, RANSAC);//寻找匹配图像
	//求基础矩阵 Fundamental,3*3的基础矩阵
	vector<uchar> RansacStatus;
	Mat Fundamental = findFundamentalMat(p01, p02, RansacStatus, FM_RANSAC);
	//重新定义关键点RR_KP和RR_matches来存储新的关键点和基础矩阵，通过RansacStatus来删除误匹配点
	vector <KeyPoint> RR_KP1, RR_KP2;
	vector <DMatch> RR_matches;
	int index = 0;
	for (size_t i = 0; i < m_Matches.size(); i++)
	{
		if (RansacStatus[i] != 0)
		{
			RR_KP1.push_back(RAN_KP1[i]);
			RR_KP2.push_back(RAN_KP2[i]);
			m_Matches[i].queryIdx = index;
			m_Matches[i].trainIdx = index;
			RR_matches.push_back(m_Matches[i]);
			index++;
		}
	}
	cout << "RANSAC后匹配点数" << RR_matches.size() << endl;
	Mat img_RR_matches;
	drawMatches(img_1, RR_KP1, img_2, RR_KP2, RR_matches, img_RR_matches);
	namedWindow("After RANSAC", 0);
	imshow("After RANSAC", img_RR_matches);
	//等待任意按键按下
	waitKey(1);




	vector<cv::Point2f> Pic1Point, Pic2Point;
	for (int i = 0; i < RR_matches.size(); i++)
	{
		Pic1Point.push_back(RR_KP1[RR_matches[i].queryIdx].pt);
		Pic2Point.push_back(RR_KP2[RR_matches[i].trainIdx].pt);
	}

	Homography = cv::findHomography(Pic1Point, Pic2Point, CV_RANSAC); //计算将p2投影到p1上的单映性矩阵

	FileStorage fs(PATH_XMAL, FileStorage::WRITE); //单应矩阵保存
	fs << "Homography" << Homography;

	warpPerspective(img_1, warpedPic, Homography, cv::Size(img_2.cols, img_2.rows));//第一路图像根据参数Homography变换映射到warpedPic图
	inscrRect = CalcCorners(Homography, img_1);// 第一路图像根据参数Homography计算本土映射区域的起始点和宽高
	fs << "inscrRect" << inscrRect;//保存在xml
	fs.release();

	Rect cutRoi(inscrRect.x, inscrRect.y, inscrRect.width, inscrRect.height);// 定义一个抠图区域
	Mat Pic1Roi = warpedPic(cutRoi).clone();//第一张变换图扣出对应区域 

	compicCalibrate.create(inscrRect.height, inscrRect.width * 2, CV_8UC3);

//	Mat Pic1Roi = warpedPic(inscrRect);
	Mat Pic2Roi = img_2(inscrRect);
	Pic1Roi.copyTo(compicCalibrate(Rect(0, 0, Pic1Roi.cols, Pic1Roi.rows)));
	Pic2Roi.copyTo(compicCalibrate(Rect(Pic1Roi.cols, 0, Pic2Roi.cols, Pic2Roi.rows)));
	namedWindow("martch", 0);
	imshow("martch", compicCalibrate);
	waitKey(0);
}