How to realize FLANN feature matching with opencv3/C++
This article mainly introduces opencv3/C++ how to achieve FLANN feature matching related knowledge, the content is detailed and easy to understand, the operation is simple and fast, has a certain reference value, I believe that everyone after reading this opencv3/C++ how to achieve FLANN feature matching article will have a harvest, let's take a look.
Use the function detectAndCompute () to detect key points and calculate descriptors
The function detectAndCompute () argument states:
Void detectAndCompute (InputArray image, / / Image InputArray mask, / / Mask CV_OUT std::vector& keypoints,// set of output key points OutputArray descriptors,// calculation descriptor (descriptors [I] is a calculation descriptor for keypoints [I]) bool useProvidedKeypoints=false / / use key points)
Match () looks for the best match for each descriptor from the query set.
Parameter description:
Void match (InputArray queryDescriptors, / / query descriptor set InputArray trainDescriptors, / / training descriptor collection CV_OUT std::vector& matches, / / match InputArray mask=noArray () / / specify the allowed matching mask between the input query and the list matrix of descriptors) const
Example of FLANN feature matching:
# include#includeusing namespace cv;using namespace cv::xfeatures2d;//FLANN is faster for high-dimensional data int main () {Mat src1,src2; src1 = imread ("E:/image/image/card2.jpg"); src2 = imread ("E:/image/image/cards.jpg"); if (src1.empty () | | src2.empty ()) {printf ("can ont load images....\ n"); return-1;} imshow ("image1", src1) Imshow ("image2", src2); int minHessian = 400; / Select SURF feature Ptrdetector = SURF::create (minHessian); std::vectorkeypoints1; std::vectorkeypoints2; Mat descriptor1, descriptor2; / / detect key points and calculate descriptors detector- > detectAndCompute (src1, Mat (), keypoints1, descriptor1); detector- > detectAndCompute (src2, Mat (), keypoints2, descriptor2); / / Flann-based descriptor matcher FlannBasedMatcher matcher; std::vectormatches / / find the best match for each descriptor from the query set matcher.match (descriptor1, descriptor2, matches); double minDist = 1000; double maxDist = 0; for (int I = 0; I
< descriptor1.rows; i++) { double dist = matches[i].distance; printf("%f \n", dist); if (dist >MaxDist) {maxDist = dist;} if (dist
< minDist) { minDist = dist; } } //DMatch类用于匹配关键点描述符的 std::vectorgoodMatches; for (int i = 0; i < descriptor1.rows; i++) { double dist = matches[i].distance; if (dist < max(2.5*minDist, 0.02)) { goodMatches.push_back(matches[i]); } } Mat matchesImg; drawMatches(src1, keypoints1, src2, keypoints2, goodMatches, matchesImg, Scalar::all(-1), Scalar::all(-1), std::vector(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS); imshow("output", matchesImg); waitKey(); return 0;}
This is the end of the article on "how to achieve FLANN feature matching in opencv3/C++". Thank you for reading! I believe that everyone has a certain understanding of the knowledge of "how to achieve FLANN feature matching in opencv3/C++". If you want to learn more knowledge, welcome to follow the industry information channel.
