SIFT图像拼接，把双目相机拍摄的图像从左图变成右图

ImageMosaic.h

#ifndef IMAGE_MOSAIC_H
#define IMAGE_MOSAIC_H

#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>


using namespace cv;  //包含cv命名空间
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

typedef struct
{
	Point2f left_top;
	Point2f left_bottom;
	Point2f right_top;
	Point2f right_bottom;
}four_corners_t;
four_corners_t corners;

Mat ImageMosaic(Mat img_1, Mat img_2)
{
	//创建SIFT 类指针
	Ptr<Feature2D> f2d = xfeatures2d::SIFT::create();
	//imshow("img_1", img_1);
	//检测关键点
	double t0 = getTickCount();
	vector<KeyPoint> keypoints_1(0), keypoints_2(0);
	f2d->detect(img_1, keypoints_1);
	f2d->detect(img_2, keypoints_2);

	//计算描述符 (特征向量)
	Mat descriptors_1, descriptors_2;
	f2d->compute(img_1, keypoints_1, descriptors_1);
	f2d->compute(img_2, keypoints_2, descriptors_2);

	//使用BF匹配器匹配描述符向量
	BFMatcher matcher;
	vector<DMatch> matches;
	matcher.match(descriptors_1, descriptors_2, matches);

	//绘制匹配出的关键点
	Mat img_matches;
	drawMatches(img_1, keypoints_1, img_2, keypoints_2, matches, 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;
		}
	}

	//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]);
		}
	}

	//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);
	}

	//求转换矩阵
	Mat H;
	vector<uchar> m;
	H = findHomography(p01, p02, RANSAC);//寻找匹配图像
	cout << "H矩阵" << H << endl;

	//H矩阵变换后的图像  
	Mat image1;
	warpPerspective(img_1, image1, H, Size(MAX(corners.right_top.x, corners.right_bottom.x), img_2.rows));
	
	return image1;

}
#endif

main程序

#include "ImageMosaic.h"
int main(int argc, char*argv[])
{
	Mat img_1 = imread("1.jpg");
	Mat img_2 = imread("2.jpg");

	Mat image1 = ImageMosaic(img_1, img_2);
	
	imshow("img_2", img_2);
	imshow("image1", image1);
	
	waitKey(0);
}