一,角点检测与特征点匹配
1.角点
在特征中最重要的是角点
灰度剃度的最大值对应的像素
两条线的角点
极值点(一阶导数最大值,但二阶导数为0)
2. Harris角点
哈里斯角点检测
Harris点
① 光滑地区,无论向哪里移动,衡量系数不变;
②边缘地址,垂直边缘移动时,衡量系统变换剧烈;
③在交点处,往哪个方向移动,衡量系统都变化剧烈;
cornerHarris(img,dst,blockSize,ksize,k)
blockSize:检测窗口大小
ksize:Sobel的卷积核
k:权重系数,经验值,一般取0.02~0.04之间。
#include "opencv2/opencv.hpp"
using namespace cv;
int main()
{
Mat srcImage = imread("1.jpg", IMREAD_GRAYSCALE);
if (srcImage.empty())
{
std::cout << "Could not open or find the image!" << std::endl;
return -1;
}
Mat cornerResponse;
cornerHarris(srcImage, cornerResponse, 2, 3, 0.04);
Mat cornerMap = Mat::zeros(cornerResponse.size(), CV_8UC1);
double maxResponse;
minMaxLoc(cornerResponse, 0, &maxResponse);
for (int i = 0; i < cornerResponse.rows; i++)
{
for (int j = 0; j < cornerResponse.cols; j++)
{
if (cornerResponse.at<float>(i, j) > 0.01 * maxResponse)
{
circle(cornerMap, Point(j, i), 5, Scalar(255), 2);
}
}
}
imshow("Corner Map", cornerMap);
waitKey(0);
return 0;
}
二,SIFT特征点提取
using namespace cv;
using namespace std;
using namespace cv::xfeatures2d;
Mat src;
int main(int argc, char** argv)
{
src = imread("./data2/101.png", IMREAD_GRAYSCALE);
//src = imread("./data2/101.png"); //加载图像
if (!src.data)
{
cout << "图片加载失败" << endl;
return -1;
}
//namedWindow("加载的灰度图像", CV_WINDOW_NORMAL); //可任意改变窗口大小
imshow("加载的灰度图像", src);
int numfeature = 400; //特征点数目
Ptr<SIFT>detector = SIFT::create(numfeature);
//auto detector = SIFT::create(); //自动生成特征点的个数
vector<KeyPoint>keypoints;
detector->detect(src, keypoints, Mat());
printf("所有的特征点个数:%d", keypoints.size());
Mat resultImg;
drawKeypoints(src, keypoints, resultImg, Scalar::all(-1), DrawMatchesFlags::DEFAULT); //特征点颜色随机
imshow("SIFT特征点提取", resultImg);
imwrite("./效果图/SIFT特征点提取.jpg", resultImg);
waitKey(0);
return 0;
}
IFT特征点提取", resultImg);
imwrite(“./效果图/SIFT特征点提取.jpg”, resultImg);
waitKey(0);
return 0;
}
-