之前写过一遍关于学习surf算法的blog:http://blog.csdn.net/sangni007/article/details/7482960
但是代码比较麻烦,而且其中还涉及到flann算法(其中的Random KDTree+KNN),虽然能看明白,但是比较费劲,今天在文档中找到一个简化版本:
1.SurfFeatureDetector detector( minHessian );构造surf检测器;
detector.detect( img_1, keypoints_1 ); detector.detect( img_2, keypoints_2 );检测
2.SurfDescriptorExtractor extractor;提取描述结构
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;牛逼的匹配结构啊!!!!可以直接暴力测量距离
std::vector< DMatch > matches;
matcher.match( descriptors_1, descriptors_2, matches );
PS:OpenCV 你是在太强悍了!!!只有我想不到,木有你办不到的啊! 我真心跪了!
- /**
- * @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 <img1> <img2>" << std::endl; }
图像中match的keypoints没有经过过滤。导致匹配点过多
文档中还有一个版本带定位的和过滤Match的,
from: http://blog.csdn.net/yangtrees/article/details/7544133