SURF匹配演示源码说明(opencv4.2+opencv_contirb4.20)用法说明

最新推荐文章于 2023-04-14 17:29:25 发布

dcx_dcx

最新推荐文章于 2023-04-14 17:29:25 发布

阅读量1.9k

点赞数 2

文章标签： opencv

本文链接：https://blog.csdn.net/dcx_dcx/article/details/104509934

版权

本源码是根据网络大牛的在opencv2的例子移植过来到opencv4.2上的的，很多语法需要调整。特别是SURF探测器定义：

旧代码为：

SurfFeatureDetector featureDetector(80);
SurfDescriptorExtractor featureExtractor;

新的opencv4.2中为：

Ptr<cv::xfeatures2d::SURF> detector = cv::xfeatures2d::SURF::create(minHessian);
Ptr <cv::xfeatures2d::SURF> extractor = cv::xfeatures2d::SURF::create(minHessian);

要运行本代码，需要下载在opencv4.2+pencv_contirb4.20（64位）平台上运行。可以在以下地址下载已经这个资源

https://download.csdn.net/download/dcx_dcx/12237707

本代码是是用vc2019编译的成64位代码。
演示源码下载地址为： https://download.csdn.net/download/dcx_dcx/12192309
主要代码如下：

void SURFDemo1(void) 
{
	//使用SURF算子检测关键点
	int minHessian = 400;//SURF算法中的hessian阈值

	Ptr<cv::xfeatures2d::SURF> detector = cv::xfeatures2d::SURF::create(minHessian);
	vector<KeyPoint> keypoints_object, keypoints_scene;//vector模板类，存放任意类型的动态数组
	Ptr <cv::xfeatures2d::SURF> extractor = cv::xfeatures2d::SURF::create(minHessian);;
	Mat descriptors_object, descriptors_scene;

	//调用detect函数检测出SURF特征关键点，保存在vector容器中
	detector->detect(srcImage1, keypoints_object);
	detector->detect(srcImage2, keypoints_scene);
	Mat matshow1, matshow2, kp1, kp2;
	//画出SURF关键点
	//drawKeypoints(srcImage1, keypoints_object, kp1, Scalar::all(-1), DrawMatchesFlags::DEFAULT);
	//drawKeypoints(srcImage2, keypoints_scene, kp2, Scalar::all(-1), DrawMatchesFlags::DEFAULT);
	extractor->compute(srcImage1, keypoints_object, descriptors_object);
	extractor->compute(srcImage2, keypoints_scene, descriptors_scene);

	//下面是吧detect和compute用一个函数就完成了
	//detector->detectAndCompute(srcImage1, Mat(), keypoints_object, descriptors_object);
	//detector->detectAndCompute(srcImage2, Mat(),keypoints_scene, descriptors_scene);

	vector< DMatch > matches;

	//使用FLANN匹配算子进行匹配		
	FlannBasedMatcher matcher;// (new flann::LshIndexParams(20, 10, 2));
	//使用暴力匹配匹配算子进行匹配
	BFMatcher matcher1;
	//自选一种匹配
	if (0)
	{
		matcher.match(descriptors_object, descriptors_scene, matches);
	}
	else
	{
		matcher1.match(descriptors_object, descriptors_scene, matches);
	}

	double max_dist = 0; double min_dist = 100;//最小距离和最大距离

	//【6】计算出关键点之间距离的最大值和最小值
	for (int i = 0; i < descriptors_object.rows; i++)
	{
		double dist = matches[i].distance;
		if (dist < min_dist) min_dist = dist;
		if (dist > max_dist) max_dist = dist;
	}

	printf(">Max dist 最大距离 : %f \n", max_dist);
	printf(">Min dist 最小距离 : %f \n", min_dist);

	//【7】存下匹配距离小于3*min_dist的点对
	std::vector< DMatch > good_matches;

	for (int i = 0; i < descriptors_object.rows; i++)
	{
		if (matches[i].distance < 2.5 * min_dist)
		{
			good_matches.push_back(matches[i]);
		}
	}
	//绘制出匹配到的关键点
	Mat img_matches;
	drawMatches(srcImage1, keypoints_object, srcImage2, keypoints_scene,
		good_matches, img_matches, Scalar::all(-1), Scalar::all(-1),
		vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);

	//定义两个局部变量
	vector<Point2f> obj;
	vector<Point2f> scene;

	//从匹配成功的匹配对中获取关键点
	for (unsigned int i = 0; i < good_matches.size(); i++)
		//for (unsigned int i = 0; i < 10; i++)
	{
		obj.push_back(keypoints_object[good_matches[i].queryIdx].pt);
		scene.push_back(keypoints_scene[good_matches[i].trainIdx].pt);
	}

	Mat H = findHomography(obj, scene, RANSAC);//计算透视变换 

	//从待测图片中获取角点
	vector<Point2f> obj_corners(4);
	obj_corners[0] = cv::Point(0, 0);
	obj_corners[1] = Point(srcImage1.cols, 0);
	obj_corners[2] = Point(srcImage1.cols, srcImage1.rows);
	obj_corners[3] = Point(0, srcImage1.rows);
	vector<Point2f> scene_corners(4);

	//进行透视变换
	perspectiveTransform(obj_corners, scene_corners, H);

	//绘制出角点之间的直线
	cv::Point2f p1, p2, p;
	p1 = scene_corners[0] + Point2f(static_cast<float>(srcImage1.cols), 0);
	p2 = scene_corners[1] + Point2f(static_cast<float>(srcImage1.cols), 0),
		p = p1 - p2;
	float fk, ang;
	fk = p.x / p.y;
	ang = atan(fk);
	ang = 180.00001 * ang / 3.1415926;

	//在大图中画出小图的匹配位置
	line(img_matches, scene_corners[0] + Point2f(static_cast<float>(srcImage1.cols), 0), scene_corners[1] + Point2f(static_cast<float>(srcImage1.cols), 0), Scalar(0, 0, 255), 8);
	line(img_matches, scene_corners[1] + Point2f(static_cast<float>(srcImage1.cols), 0), scene_corners[2] + Point2f(static_cast<float>(srcImage1.cols), 0), Scalar(0, 0, 255), 8);
	line(img_matches, scene_corners[2] + Point2f(static_cast<float>(srcImage1.cols), 0), scene_corners[3] + Point2f(static_cast<float>(srcImage1.cols), 0), Scalar(0, 0, 255), 8);
	line(img_matches, scene_corners[3] + Point2f(static_cast<float>(srcImage1.cols), 0), scene_corners[0] + Point2f(static_cast<float>(srcImage1.cols), 0), Scalar(0, 0, 255), 8);

	//显示最终结果
	imshow("效果图", img_matches);

}