OpenCV特征點(diǎn)檢測匹配圖像-----添加包圍盒

最終效果：

其實(shí)這個小功能非常有用，甚至加上只有給人感覺好像人臉檢測，目標(biāo)檢測直接成了demo了，主要代碼如下：
// localize the objectstd::vector<Point2f> obj;std::vector<Point2f> scene;for (size_t i = 0; i < good_matches.size(); ++i){// get the keypoints from the good matchesobj.push_back(keyPoints_1[ good_matches[i].queryIdx ].pt);scene.push_back(keyPoints_2[ good_matches[i].trainIdx ].pt);}Mat H = findHomography( obj, scene, CV_RANSAC );// get the corners from the image_1std::vector<Point2f> obj_corners(4);obj_corners[0] = cvPoint(0,0);obj_corners[1] = cvPoint( img_1.cols, 0);obj_corners[2] = cvPoint( img_1.cols, img_1.rows);obj_corners[3] = cvPoint( 0, img_1.rows);std::vector<Point2f> scene_corners(4);perspectiveTransform( obj_corners, scene_corners, H);// draw lines between the corners (the mapped object in the scene - image_2)line( img_matches, scene_corners[0] + Point2f( img_1.cols, 0), scene_corners[1] + Point2f( img_1.cols, 0),Scalar(0,255,0));line( img_matches, scene_corners[1] + Point2f( img_1.cols, 0), scene_corners[2] + Point2f( img_1.cols, 0),Scalar(0,255,0));line( img_matches, scene_corners[2] + Point2f( img_1.cols, 0), scene_corners[3] + Point2f( img_1.cols, 0),Scalar(0,255,0));line( img_matches, scene_corners[3] + Point2f( img_1.cols, 0), scene_corners[0] + Point2f( img_1.cols, 0),Scalar(0,255,0));



? ? 基本原理是利用函數(shù)：findHomography，該?函數(shù)是求兩幅圖像的單應(yīng)性矩陣或者叫（單映射矩陣），它是一個3*3的矩陣。 findHomography：?計(jì)算多個二維點(diǎn)對之間的 最優(yōu)單映射變換 矩陣?H（3行x3列）?，使用最小均方誤差或者RANSAC方法?。 單應(yīng)性矩陣算過后的投影點(diǎn)的偏移量 scene_corners[0]，就是在匹配圖像中的點(diǎn)的位置，因?yàn)樾Ч麍D像相當(dāng)于增加了一個待匹配圖像的寬度，所以每一個點(diǎn)都要加上Point2f( img_1.cols, 0) 兩個重要函數(shù)的介紹：

findHomography

功能：在兩個平面之間尋找單映射變換矩陣

結(jié)構(gòu)：

Mat findHomography(InputArray srcPoints, InputArray dstPoints, int method=0, double ransacReprojThreshold=3, OutputArray mask=noArray() )
srcPoints ：在原平面上點(diǎn)的坐標(biāo)，CV_32FC2 的矩陣或者vector<Point2f>?
dstPoints ：在目標(biāo)平面上點(diǎn)的坐標(biāo)，CV_32FC2 的矩陣或者 vector<Point2f> .?
method –?
用于計(jì)算單映射矩陣的方法.??
0 - 使用所有的點(diǎn)的常規(guī)方法?
CV_RANSAC - 基于 RANSAC 的方法

CV_LMEDS - 基于Least-Median 的方法

ransacReprojThreshold：?處理一組點(diǎn)對為內(nèi)部點(diǎn)的最大容忍重投影誤差（只在RANSAC方法中使用），其形式為：?

? ?如果 ? ??

那么點(diǎn)i則被考慮為內(nèi)部點(diǎn)，如果srcPoints和dstPoints是以像素為單位，通常把參數(shù)設(shè)置為1-10范圍內(nèi)??

這個函數(shù)的作用是在原平面和目標(biāo)平面之間返回一個單映射矩陣

?

因此反投影誤差 是最小的。

如果參數(shù)被設(shè)置為0，那么這個函數(shù)使用所有的點(diǎn)和一個簡單的最小二乘算法來計(jì)算最初的單應(yīng)性估計(jì)，但是，如果不是所有的點(diǎn)對都完全符合透視變換，那么這個初始的估計(jì)會很差，在這種情況下，你可以使用兩個robust算法中的一個。?RANSAC 和LMeDS , 使用坐標(biāo)點(diǎn)對生成了很多不同的隨機(jī)組合子集（每四對一組），使用這些子集和一個簡單的最小二乘法來估計(jì)變換矩陣，然后計(jì)算出單應(yīng)性的質(zhì)量，最好的子集被用來產(chǎn)生初始單應(yīng)性的估計(jì)和掩碼。?
RANSAC方法幾乎可以處理任何異常，但是需要一個閾值，?LMeDS 方法不需要任何閾值，但是只有在inliers大于50%時才能計(jì)算正確，最后，如果沒有outliers和噪音非常小，則可以使用默認(rèn)的方法。

PerspectiveTransform

功能：向量數(shù)組的透視變換?

結(jié)構(gòu)：

void perspectiveTransform(InputArray src, OutputArray dst, InputArray m)
src ：輸入兩通道或三通道的浮點(diǎn)數(shù)組，每一個元素是一個2D/3D 的矢量轉(zhuǎn)換

dst ：輸出和src同樣的size和type?
m ：3x3 或者4x4浮點(diǎn)轉(zhuǎn)換矩陣?
轉(zhuǎn)換方法為：

?

文檔官方介紹：

?

實(shí)現(xiàn)代碼：

// OpenCV_sift.cpp : 定義控制臺應(yīng)用程序的入口點(diǎn)。 //#include "stdafx.h" #include <iostream>#include <vector> #include "opencv2/core/core.hpp" #include "opencv2/features2d/features2d.hpp" #include "opencv2/highgui/highgui.hpp" #include "opencv2/legacy/legacy.hpp" #include "opencv2/calib3d/calib3d.hpp"using namespace cv; using namespace std;#pragma comment(lib,"opencv_core2410d.lib") #pragma comment(lib,"opencv_highgui2410d.lib") #pragma comment(lib,"opencv_objdetect2410d.lib") #pragma comment(lib,"opencv_imgproc2410d.lib") #pragma comment(lib,"opencv_features2d2410d.lib") #pragma comment(lib,"opencv_legacy2410d.lib") #pragma comment(lib,"opencv_calib3d2410d.lib")int main() {Mat img_1 = imread("1.jpg");Mat img_2 = imread("2.jpg");if (!img_1.data || !img_2.data){cout << "error reading images " << endl;return -1;}ORB orb;vector<KeyPoint> keyPoints_1, keyPoints_2;Mat descriptors_1, descriptors_2;orb(img_1, Mat(), keyPoints_1, descriptors_1);orb(img_2, Mat(), keyPoints_2, descriptors_2);BruteForceMatcher<HammingLUT> matcher;vector<DMatch> matches;matcher.match(descriptors_1, descriptors_2, matches);double max_dist = 0; double min_dist = 100;//-- Quick calculation of max and min distances between keypointsfor( int i = 0; i < descriptors_1.rows; i++ ){ double dist = matches[i].distance;if( dist < min_dist ) min_dist = dist;if( dist > max_dist ) max_dist = dist;}printf("-- Max dist : %f \n", max_dist );printf("-- Min dist : %f \n", min_dist );//-- Draw only "good" matches (i.e. whose distance is less than 0.6*max_dist )//-- PS.- radiusMatch can also be used here.std::vector< DMatch > good_matches;for( int i = 0; i < descriptors_1.rows; i++ ){ if( matches[i].distance < 0.6*max_dist ){ good_matches.push_back( matches[i]); }}Mat img_matches;drawMatches(img_1, keyPoints_1, img_2, keyPoints_2,good_matches, img_matches, Scalar::all(-1), Scalar::all(-1),vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS);// localize the objectstd::vector<Point2f> obj;std::vector<Point2f> scene;for (size_t i = 0; i < good_matches.size(); ++i){// get the keypoints from the good matchesobj.push_back(keyPoints_1[ good_matches[i].queryIdx ].pt);scene.push_back(keyPoints_2[ good_matches[i].trainIdx ].pt);}Mat H = findHomography( obj, scene, CV_RANSAC );// get the corners from the image_1std::vector<Point2f> obj_corners(4);obj_corners[0] = cvPoint(0,0);obj_corners[1] = cvPoint( img_1.cols, 0);obj_corners[2] = cvPoint( img_1.cols, img_1.rows);obj_corners[3] = cvPoint( 0, img_1.rows);std::vector<Point2f> scene_corners(4);perspectiveTransform( obj_corners, scene_corners, H);// draw lines between the corners (the mapped object in the scene - image_2)line( img_matches, scene_corners[0] + Point2f( img_1.cols, 0), scene_corners[1] + Point2f( img_1.cols, 0),Scalar(0,255,0));line( img_matches, scene_corners[1] + Point2f( img_1.cols, 0), scene_corners[2] + Point2f( img_1.cols, 0),Scalar(0,255,0));line( img_matches, scene_corners[2] + Point2f( img_1.cols, 0), scene_corners[3] + Point2f( img_1.cols, 0),Scalar(0,255,0));line( img_matches, scene_corners[3] + Point2f( img_1.cols, 0), scene_corners[0] + Point2f( img_1.cols, 0),Scalar(0,255,0));imshow( "Match", img_matches);cvWaitKey();return 0; }


當(dāng)然也可以用其他特征點(diǎn)檢測的算法來做：/* SIFT sift; sift(img_1, Mat(), keyPoints_1, descriptors_1); sift(img_2, Mat(), keyPoints_2, descriptors_2); BruteForceMatcher<L2<float> > matcher; *//* SURF surf; surf(img_1, Mat(), keyPoints_1); surf(img_2, Mat(), keyPoints_2); SurfDescriptorExtractor extrator; extrator.compute(img_1, keyPoints_1, descriptors_1); extrator.compute(img_2, keyPoints_2, descriptors_2); BruteForceMatcher<L2<float> > matcher; */



圖片：











參考文獻(xiàn)：ORB特征早在，OpenCV2.3RC中已經(jīng)有了實(shí)現(xiàn)OpenCV中ORB特征這個是之前系列中轉(zhuǎn)載整理的文章1.http://blog.csdn.net/wangyaninglm/article/details/448057092.http://docs.opencv.org/2.4.10/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html?highlight=findhomography#cv.FindHomography3.http://www.360doc.com/content/14/0410/14/10724725_367760906.shtml4.http://blog.csdn.net/chenjiazhou12/article/details/22825487?utm_source=tuicool&utm_medium=referral 5.http://blog.csdn.net/merlin_q/article/details/7026375

總結(jié)

以上是生活随笔為你收集整理的OpenCV特征点检测匹配图像-----添加包围盒的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。