FLANN特征匹配

         FLANN (Fast Approximate Nearest Neighbor Search Library)， 快速最近邻逼近搜索函数库。即实现快速高效匹配。      

         特征匹配记录下目标图像与待匹配图像的特征点（KeyPoint），并根据特征点集合构造特征量（descriptor），对这个特征量进行比较、筛选，最终得到一个匹配点的映射集合。我们也可以根据这个集合的大小来衡量两幅图片的匹配程度。

        特征匹配与模板匹配不同，由于是计算特征点集合的相关度，转置操作对匹配影响不大，但它容易受到失真、缩放的影响。

 

代码示例：

#include <opencv2/opencv.hpp>
#include <opencv2/xfeatures2d.hpp>
#include <iostream>

using namespace cv;
using namespace std;
using namespace cv::xfeatures2d;

int main(int argc, char** argv) 
{
	Mat img1 = imread("D:/cv400/data/box.png", IMREAD_GRAYSCALE);
	Mat img2 = imread("D:/cv400/data/box_in_scene.png", IMREAD_GRAYSCALE);
	if (img1.empty() || img2.empty()) 
	{
		cout << "Load image error..." << endl;
		return -1;
	}
	imshow("object image", img1);
	imshow("object in scene", img2);

	// surf featurs extraction
	double t1 = (double)getTickCount();
	int minHessian = 400;
	Ptr<SURF> detector = SURF::create(minHessian);
	vector<KeyPoint> keypoints_obj;
	vector<KeyPoint> keypoints_scene;
	Mat descriptor_obj, descriptor_scene;
	detector->detectAndCompute(img1, Mat(), keypoints_obj, descriptor_obj);
	detector->detectAndCompute(img2, Mat(), keypoints_scene, descriptor_scene);

	// matching
	FlannBasedMatcher matcher;
	vector<DMatch> matches;
	matcher.match(descriptor_obj, descriptor_scene, matches);
	double t2 = (double)getTickCount();
	double t = (t2 - t1) / getTickFrequency();
	cout << "spend time : " << t << "s" << endl;
	
	//求匹配点最近距离
	double minDist = 1000;
	for (int i = 0; i < descriptor_obj.rows; i++)
	{
		double dist = matches[i].distance;
		if (dist < minDist) 
			minDist = dist;	
	}
	cout<<"min distance : "<< minDist<<endl;

	//距离较近即匹配较好的点
	vector<DMatch> goodMatches;
	for (int i = 0; i < descriptor_obj.rows; i++)
	{
		double dist = matches[i].distance;
		if (dist < max(3 * minDist, 0.02)) 
			goodMatches.push_back(matches[i]);	
	}

	Mat matchesImg;
	drawMatches(img1, keypoints_obj, img2, keypoints_scene, goodMatches, matchesImg, Scalar::all(-1),
		         Scalar::all(-1), vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);
	imshow("Flann Matching Result", matchesImg);

	waitKey(0);
	return 0;
}

运行截图：

耗时 175 ms 

 

接下来，在前面程序的基础上，将场景中的目标图像定位出来（画出来），要用到两个函数：

• 使用函数 findHomography 寻找匹配上的关键点的变换。
• 使用函数 perspectiveTransform 来映射点.

#include <opencv2/opencv.hpp>
#include <opencv2/xfeatures2d.hpp>
#include <opencv2/calib3d/calib3d.hpp>
#include <iostream>

using namespace cv;
using namespace std;
using namespace cv::xfeatures2d;

int main(int argc, char** argv) 
{
	Mat img1 = imread("D:/cv400/data/box.png", IMREAD_GRAYSCALE);
	Mat img2 = imread("D:/cv400/data/box_in_scene.png", IMREAD_GRAYSCALE);
	if (img1.empty() || img2.empty()) 
	{
		cout << "Load image error..." << endl;
		return -1;
	}
	imshow("object image", img1);
	imshow("object in scene", img2);

	// surf featurs extraction
	double t1 = (double)getTickCount();
	int minHessian = 400;
	Ptr<SURF> detector = SURF::create(minHessian);
	vector<KeyPoint> keypoints_obj;
	vector<KeyPoint> keypoints_scene;
	Mat descriptor_obj, descriptor_scene;
	detector->detectAndCompute(img1, Mat(), keypoints_obj, descriptor_obj);
	detector->detectAndCompute(img2, Mat(), keypoints_scene, descriptor_scene);

	// matching
	FlannBasedMatcher matcher;
	vector<DMatch> matches;
	matcher.match(descriptor_obj, descriptor_scene, matches);
	double t2 = (double)getTickCount();
	double t = (t2 - t1) / getTickFrequency();
	cout << "spend time : " << t << "s" << endl;
	
	//求匹配点最近距离
	double minDist = 1000;
	for (int i = 0; i < descriptor_obj.rows; i++)
	{
		double dist = matches[i].distance;
		if (dist < minDist) 
			minDist = dist;	
	}
	cout<<"min distance : "<< minDist<<endl;

	//距离较近即匹配较好的点
	vector<DMatch> goodMatches;
	for (int i = 0; i < descriptor_obj.rows; i++)
	{
		double dist = matches[i].distance;
		if (dist < max(3 * minDist, 0.02)) 
			goodMatches.push_back(matches[i]);	
	}

	
	//寻找匹配上的关键点的变换
	vector<Point2f> obj;  //目标特征点
	vector<Point2f> objInScene;  //场景中目标特征点
	for (size_t t = 0; t < goodMatches.size(); t++) 
	{
		obj.push_back(keypoints_obj[goodMatches[t].queryIdx].pt);
		objInScene.push_back(keypoints_scene[goodMatches[t].trainIdx].pt);
	}
	Mat imgBH = findHomography(obj, objInScene, RANSAC);

	//映射点
	vector<Point2f> obj_corners(4);
	vector<Point2f> scene_corners(4);
	obj_corners[0] = Point(0, 0);
	obj_corners[1] = Point(img1.cols, 0);
	obj_corners[2] = Point(img1.cols, img1.rows);
	obj_corners[3] = Point(0, img1.rows);
	perspectiveTransform(obj_corners, scene_corners, imgBH);

	//四个点之间画线
	Mat dst;
	cvtColor(img2, dst, COLOR_GRAY2BGR);
	line(dst, scene_corners[0], scene_corners[1], Scalar(0, 0, 255), 2, 8, 0);
	line(dst, scene_corners[1], scene_corners[2], Scalar(0, 0, 255), 2, 8, 0);
	line(dst, scene_corners[2], scene_corners[3], Scalar(0, 0, 255), 2, 8, 0);
	line(dst, scene_corners[3], scene_corners[0], Scalar(0, 0, 255), 2, 8, 0);

	imshow("find object in sence", dst);
	waitKey(0);
	return 0;
}

运行截图：