opencv学习之SURF特征检测提取演示

最新推荐文章于 2023-09-20 20:14:40 发布

原创最新推荐文章于 2023-09-20 20:14:40 发布 · 1.6k 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#opencv 特征检测特征提取特征匹

Opencv_Learning-Diary 专栏收录该内容

44 篇文章

订阅专栏

本文通过具体代码示例，展示了如何使用SURF算法进行图像特征点检测与匹配，并比较了不同匹配器的效果，包括BFMatcher和FLANN。此外，还介绍了如何实时地从摄像头输入中进行特征匹配。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

// opencv2413_test.cpp : 定义控制台应用程序的入口点。
//
#include "stdafx.h"
#include <opencv2\opencv.hpp>
#include <iostream>
#include <string>
#include<opencv2\core\core.hpp>
#include<opencv2\features2d\features2d.hpp>
#include<opencv2\nonfree\nonfree.hpp>

using namespace cv;
using namespace std;

int main()
{
	system("color 2F");
	Mat srcImage1 = imread("1.jpg",-1);
	Mat srcImage2 = imread("2.jpg",-1);

	imshow("src1", srcImage1);
	imshow("src2", srcImage2);
	//定义SURF中的hessian阈值特征点检测算子
	int minHessian = 400;
	//定义一个SurfFeatureDetector特征检测类对象
	SurfFeatureDetector detector(minHessian);
	//定义模板类，vector是可以存放任意类型的动态数组，能够增加和压缩数据
	vector<KeyPoint> keypoints_1, keypoints_2;
	//detect函数检测出surf特征关键点，保存在vector容器中
	detector.detect(srcImage1, keypoints_1);
	detector.detect(srcImage2, keypoints_2);
	//绘制特征关键点
	Mat img_keypoints_1;
	Mat img_keypoints_2;
	drawKeypoints(srcImage1, keypoints_1, img_keypoints_1, 
		Scalar::all(-1), DrawMatchesFlags::DRAW_RICH_KEYPOINTS);
	drawKeypoints(srcImage2, keypoints_2, img_keypoints_2,
		Scalar::all(-1), DrawMatchesFlags::DRAW_RICH_KEYPOINTS);

	imshow("特征点检测图1", img_keypoints_1);
	imshow("特征点检测图2", img_keypoints_2);

	waitKey();
	return 0;
}

特征提取匹配

// opencv2413_test.cpp : 定义控制台应用程序的入口点。
//
#include "stdafx.h"
#include <opencv2\opencv.hpp>
#include <iostream>
#include <string>
#include<opencv2\core\core.hpp>
#include<opencv2\features2d\features2d.hpp>
#include<opencv2\nonfree\nonfree.hpp>
#include<opencv2\legacy\legacy.hpp>

using namespace cv;
using namespace std;

int main()
{
	system("color 2F");
	Mat srcImage1 = imread("1.jpg",-1);
	Mat srcImage2 = imread("2.jpg",-1);

	imshow("src1", srcImage1);
	imshow("src2", srcImage2);
	//定义SURF中的hessian阈值特征点检测算子
	int minHessian = 400;
	//定义一个SurfFeatureDetector特征检测类对象
	SurfFeatureDetector detector(minHessian);
	//定义模板类，vector是可以存放任意类型的动态数组，能够增加和压缩数据
	vector<KeyPoint> keypoints_1, keypoints_2;
	//detect函数检测出surf特征关键点，保存在vector容器中
	detector.detect(srcImage1, keypoints_1);
	detector.detect(srcImage2, keypoints_2);
	//绘制特征关键点
	Mat img_keypoints_1;
	Mat img_keypoints_2;
	drawKeypoints(srcImage1, keypoints_1, img_keypoints_1, 
		Scalar::all(-1), DrawMatchesFlags::DRAW_RICH_KEYPOINTS);
	drawKeypoints(srcImage2, keypoints_2, img_keypoints_2,
		Scalar::all(-1), DrawMatchesFlags::DRAW_RICH_KEYPOINTS);

	imshow("特征点检测图1", img_keypoints_1);
	imshow("特征点检测图2", img_keypoints_2);

	/*
		进行SURF的特征提取
	*/
	//计算描述符（特征向量）
	SurfDescriptorExtractor extractor;
	Mat descriptors1, descriptors2;
	extractor.compute(srcImage1, keypoints_1, descriptors1);
	extractor.compute(srcImage2, keypoints_2, descriptors2);
	//实例化一个匹配器
	BruteForceMatcher<L2<float>> matcher;
	vector<DMatch> matches;
	matcher.match(descriptors1, descriptors2, matches);
	//绘制从两个图像中匹配出的关键点
	Mat imgMatches;
	drawMatches(srcImage1, keypoints_1, srcImage2, keypoints_2, matches, imgMatches);
	imshow("匹配图", imgMatches);


	waitKey();
	return 0;
}

使用Flann进行关键点的描述和匹配

// opencv2413_test.cpp : 定义控制台应用程序的入口点。
//
#include "stdafx.h"
#include <opencv2\opencv.hpp>
#include <iostream>
#include <string>
#include<opencv2\core\core.hpp>
#include<opencv2\features2d\features2d.hpp>
#include<opencv2\nonfree\nonfree.hpp>
#include<opencv2\legacy\legacy.hpp>

using namespace cv;
using namespace std;

int main()
{
	system("color 2F");
	Mat srcImage1 = imread("1.jpg",-1);
	Mat srcImage2 = imread("2.jpg",-1);

	imshow("src1", srcImage1);
	imshow("src2", srcImage2);
	//定义SURF中的hessian阈值特征点检测算子
	int minHessian = 400;
	//定义一个SurfFeatureDetector特征检测类对象
	SurfFeatureDetector detector(minHessian);
	//定义模板类，vector是可以存放任意类型的动态数组，能够增加和压缩数据
	vector<KeyPoint> keypoints_1, keypoints_2;
	//detect函数检测出surf特征关键点，保存在vector容器中
	detector.detect(srcImage1, keypoints_1);
	detector.detect(srcImage2, keypoints_2);
	//绘制特征关键点
	Mat img_keypoints_1;
	Mat img_keypoints_2;
	drawKeypoints(srcImage1, keypoints_1, img_keypoints_1, 
		Scalar::all(-1), DrawMatchesFlags::DRAW_RICH_KEYPOINTS);
	drawKeypoints(srcImage2, keypoints_2, img_keypoints_2,
		Scalar::all(-1), DrawMatchesFlags::DRAW_RICH_KEYPOINTS);

	imshow("特征点检测图1", img_keypoints_1);
	imshow("特征点检测图2", img_keypoints_2);

	/*
		进行SURF的特征提取
	*/
	//计算描述符（特征向量）
	SurfDescriptorExtractor extractor;
	Mat descriptors1, descriptors2;
	extractor.compute(srcImage1, keypoints_1, descriptors1);
	extractor.compute(srcImage2, keypoints_2, descriptors2);
	/*
	//实例化一个匹配器
	BruteForceMatcher<L2<float>> matcher;
	vector<DMatch> matches;
	matcher.match(descriptors1, descriptors2, matches);
	//绘制从两个图像中匹配出的关键点
	Mat imgMatches;
	drawMatches(srcImage1, keypoints_1, srcImage2, keypoints_2, matches, imgMatches);
	imshow("SURF--匹配图", imgMatches);
	*/
	/*
	使用Flann进行特征点匹配
	*/
	FlannBasedMatcher matcher;
	vector<DMatch> matches2;
	matcher.match(descriptors1, descriptors2, matches2);
	double max_dist = 0;
	double min_dist = 100;
	//快速计算关键点之间的最大和最小距离
	for (int i = 0; i < descriptors1.rows; i++) {
		double dist = matches2[i].distance;
		if (dist < min_dist)min_dist = dist;
		if (dist > max_dist)max_dist = dist;
	}
	//输出距离信息
	cout << "最大距离(Max Dist):" << "\n" << max_dist;
	cout << "最小距离(Min Dist):" << "\n" << min_dist;

	//存下所有符合条件的匹配结果，距离小于2*min_dist
	vector<DMatch> good_matches;
	for (int i = 0; i < descriptors1.rows; i++) {
		if (matches2[i].distance < 2 * min_dist) {
			good_matches.push_back(matches2[i]);
		}
	}
	//绘制符合条件的匹配点
	Mat img_matches;
	drawMatches(srcImage1, keypoints_1, srcImage2, keypoints_2, good_matches, 
		img_matches, Scalar::all(-1), Scalar::all(-1), vector<char>(), DrawMatchesFlags::
		NOT_DRAW_SINGLE_POINTS);

	//输出相关匹配点信息
	for (int i = 0; i < good_matches.size(); i++) {
		printf(">符合条件的匹配点[%d] 特征点1：%d -- 特征点2：%d\n", i, 
			good_matches[i].queryIdx, good_matches[i].trainIdx);
	}
	imshow("Flann--匹配效果图", img_matches);

	waitKey();
	return 0;
}

基于摄像头捕获图片进行特征匹配

// opencv2413_test.cpp : 定义控制台应用程序的入口点。
//
#include "stdafx.h"
#include <opencv2\opencv.hpp>
#include <iostream>
#include <string>
#include<opencv2\core\core.hpp>
#include<opencv2\features2d\features2d.hpp>
#include<opencv2\nonfree\nonfree.hpp>
#include<opencv2\legacy\legacy.hpp>

using namespace cv;
using namespace std;

int main()
{
	system("color 2F");
	//【0】改变console字体颜色

	//【1】载入图像、显示并转化为灰度图
	Mat trainImage = imread("3.jpg"), trainImage_gray;
	imshow("原始图", trainImage);
	cvtColor(trainImage, trainImage_gray, CV_BGR2GRAY);

	//【2】检测Surf关键点、提取训练图像描述符
	vector<KeyPoint> train_keyPoint;
	Mat trainDescriptor;
	SurfFeatureDetector featureDetector(80);
	featureDetector.detect(trainImage_gray, train_keyPoint);
	SurfDescriptorExtractor featureExtractor;
	featureExtractor.compute(trainImage_gray, train_keyPoint, trainDescriptor);

	//【3】创建基于FLANN的描述符匹配对象
	FlannBasedMatcher matcher;
	vector<Mat> train_desc_collection(1, trainDescriptor);
	matcher.add(train_desc_collection);
	matcher.train();

	//【4】创建视频对象、定义帧率
	VideoCapture cap(0);
	unsigned int frameCount = 0;//帧数

								//【5】不断循环，直到q键被按下
	while (char(waitKey(1)) != 'q')
	{
		//<1>参数设置
		int64 time0 = getTickCount();
		Mat testImage, testImage_gray;
		cap >> testImage;//采集视频到testImage中
		if (testImage.empty())
			continue;

		//<2>转化图像到灰度
		cvtColor(testImage, testImage_gray, CV_BGR2GRAY);

		//<3>检测S关键点、提取测试图像描述符
		vector<KeyPoint> test_keyPoint;
		Mat testDescriptor;
		featureDetector.detect(testImage_gray, test_keyPoint);
		featureExtractor.compute(testImage_gray, test_keyPoint, testDescriptor);

		//<4>匹配训练和测试描述符
		vector<vector<DMatch> > matches;
		matcher.knnMatch(testDescriptor, matches, 2);

		// <5>根据劳氏算法（Lowe's algorithm），得到优秀的匹配点
		vector<DMatch> goodMatches;
		for (unsigned int i = 0; i < matches.size(); i++)
		{
			if (matches[i][0].distance < 0.6 * matches[i][1].distance)
				goodMatches.push_back(matches[i][0]);
		}

		//<6>绘制匹配点并显示窗口
		Mat dstImage;
		drawMatches(testImage, test_keyPoint, trainImage, train_keyPoint, goodMatches, dstImage);
		imshow("匹配窗口", dstImage);

		//<7>输出帧率信息
		cout << "当前帧率为：" << getTickFrequency() / (getTickCount() - time0) << endl;
	}

	waitKey();
	return 0;
}