根据orb特征匹配两幅图片

#include < iostream>
#include <opencv2/core/core.hpp>
#include <opencv2/features2d/features2d.hpp>
#include <opencv2/highgui/highgui.hpp>
#include < chrono>

using namespace std;
using namespace cv;

int main( ) {

//-- 读取图像
Mat img_1 = imread("/home/hotfinda/example_slambook/slambook2-master/ch7/1.png", 1);
Mat img_2 = imread(“2.png”, 1);
assert(img_1.data != nullptr && img_2.data != nullptr);

//-- 初始化
std::vector< KeyPoint> keypoints_1, keypoints_2; //KeyPoin类型存储关键点
Mat descriptors_1, descriptors_2; //Mat类型存储描述子
Ptr< FeatureDetector> detector = ORB::create()；//设定一个ORB检测类型指针，用于ORB关键点
Ptr< DescriptorExtractor> descriptor = ORB::create();//设定一个ORB检测类型指针，用于ORB描述子
Ptr< DescriptorMatcher> matcher = DescriptorMatcher::create(“BruteForce-Hamming”); 设定描述子匹配类型指针

//-- 第一步:检测 Oriented FAST 角点位置
chrono::steady_clock::time_point t1 = chrono::steady_clock::now();
detector->detect(img_1, keypoints_1); detect()函数计算关键点
detector->detect(img_2, keypoints_2);

//-- 第二步:根据角点位置计算 BRIEF 描述子
descriptor->compute(img_1, keypoints_1, descriptors_1); compute函数根据关键点计算描述子，一个描述子就是一个向量
descriptor->compute(img_2, keypoints_2, descriptors_2);
chrono::steady_clock::time_point t2 = chrono::steady_clock::now();
chrono::duration< double> time_used = chrono::duration_cast<chrono::duration< double>>(t2 - t1);
cout << "extract ORB cost = " << time_used.count() << " seconds. " << endl;

Mat outimg1;
drawKeypoints(img_1, keypoints_1, outimg1, Scalar::all(-1), DrawMatchesFlags::DEFAULT);drawKeypoints()函数，将img1的关键点显示，另存为outimg1
imshow(“ORB features”, outimg1);

//-- 第三步:对两幅图像中的BRIEF描述子进行匹配，使用 Hamming 距离，记录描述子差异位数
vector< DMatch> matches; DMatch存储匹配结果
t1 = chrono::steady_clock::now();
matcher->match(descriptors_1, descriptors_2, matches); match()函数根据描述子进行匹配，结果存储在DMatch类型的matches下面，类似于整数数组的距离信息
t2 = chrono::steady_clock::now();
time_used = chrono::duration_cast<chrono::duration>(t2 - t1);
cout << "match ORB cost = " << time_used.count() << " seconds. " << endl;

//-- 第四步:匹配点对筛选
// 计算所有匹配特征点的最小距离和最大距离
auto min_max = minmax_element(matches.begin(), matches.end(),
[] (const DMatch &m1, const DMatch &m2) { return m1.distance < m2.distance; });不懂？？？？？？？？？？？？？？？？？？？？
double min_dist = min_max.first->distance;
double max_dist = min_max.second->distance;

printf("-- Max dist : %f \n", max_dist);
printf("-- Min dist : %f \n", min_dist);

//当描述子之间的距离大于两倍的最小距离时,即认为匹配有误.但有时候最小距离会非常小,设置一个经验值30作为下限.
.distance获取匹配的描述子的距离
std::vector< DMatch> good_matches;
for (int i = 0; i < descriptors_1.rows; i++) {
if (matches[i].distance <= max(2 * min_dist, 30.0)) {
good_matches.push_back(matches[i]);
}
}

//-- 第五步:绘制匹配结果
Mat img_match;
Mat img_goodmatch;
drawMatches(img_1, keypoints_1, img_2, keypoints_2, matches, img_match);将关键点和描述子进行关联，最终图片保存在Img_match下
drawMatches(img_1, keypoints_1, img_2, keypoints_2, good_matches, img_goodmatch);
imshow(“all matches”, img_match);
imshow(“good matches”, img_goodmatch);
waitKey(0);

return 0;
}