Learning opencv-surf simplified version

I wrote a blog about learning surf algorithms: http://blog.csdn.net/sangni007/article/details/7482960.

However, the Code is troublesome and involves the FLANN algorithm (random kdtree + KNN). Although it can be understood, it is difficult to find a simplified version in the document today:

1. surffeaturedetector detector (minhessian); construct a surf detector;

Detector. Detect (img_1, keypoints_1); detector. Detect (img_2, keypoints_2); Detection

2. surfdescriptorextractor extractor; extract the description Structure

Mat descriptors_1, descriptors_2;

Extractor. Compute (img_1, keypoints_1, descriptors_1); extractor. Compute (img_2, keypoints_2, descriptors_2 );

3. bruteforcematcher <L2 <float> matcher; awesome Matching Structure !!!! Distance can be measured by brute force.

STD: vector <dmatch> matches;

Matcher. Match (descriptors_1, descriptors_2, matches );

Document: http://opencv.itseez.com/modules/gpu/doc/feature_detection_and_description.html? Highlight = bruteforce # GPU: bruteforcematcher_gpu

PS: opencv !!! I can't think of it. You can't do it! I really fell down!

 

/** * @file SURF_descriptor * @brief SURF detector + descritpor + BruteForce Matcher + drawing matches with OpenCV functions * @author A. Huaman */#include <stdio.h>#include <iostream>#include "opencv2/core/core.hpp"#include "opencv2/features2d/features2d.hpp"#include "opencv2/highgui/highgui.hpp"using namespace cv;using namespace std;void readme();/** * @function main * @brief Main function */int main( int argc, char** argv ){  //if( argc != 3 )  //{ return -1; }  Mat img_1 = imread( "D:/src.jpg", CV_LOAD_IMAGE_GRAYSCALE );  Mat img_2 = imread( "D:/Demo.jpg", CV_LOAD_IMAGE_GRAYSCALE );    if( !img_1.data || !img_2.data )  { return -1; }  //-- Step 1: Detect the keypoints using SURF Detector  int minHessian = 400;    double t=getTickCount();  SurfFeatureDetector detector( minHessian );  std::vector<KeyPoint> keypoints_1, keypoints_2;  detector.detect( img_1, keypoints_1 );  detector.detect( img_2, keypoints_2 );  //-- Step 2: Calculate descriptors (feature vectors)  SurfDescriptorExtractor extractor;  Mat descriptors_1, descriptors_2;  extractor.compute( img_1, keypoints_1, descriptors_1 );  extractor.compute( img_2, keypoints_2, descriptors_2 );  //-- Step 3: Matching descriptor vectors with a brute force matcher  BruteForceMatcher< L2<float> > matcher;  std::vector< DMatch > matches;  matcher.match( descriptors_1, descriptors_2, matches );  t=getTickCount()-t;  t=t*1000/getTickFrequency();  //-- Draw matches  Mat img_matches;  drawMatches( img_1, keypoints_1, img_2, keypoints_2, matches, img_matches );   cout<<"Cost Time:"<<t<<endl;  //-- Show detected matches  imshow("Matches", img_matches );  waitKey(0);  return 0;}/** * @function readme */void readme(){ std::cout << " Usage: ./SURF_descriptor  

The match keypoints in the image is not filtered. Too many matching points
Document address: http://opencv.itseez.com/doc/tutorials/features2d/feature_description/feature_description.html? Highlight = Description
There is also a version in the document that carries the positioning and filters the match,
: Http://opencv.itseez.com/doc/tutorials/features2d/feature_homography/feature_homography.html? Highlight = drawmatchesflags