OpenCV  3.2.0
Open Source Computer Vision
Features2D + Homography to find a known object

.2.0+dfsg_doc_tutorials_features2d_feature_homography_feature_homography

Goal

In this tutorial you will learn how to:

Theory

Code

This tutorial code's is shown lines below.

#include <stdio.h>
#include <iostream>
#include "opencv2/core.hpp"
#include "opencv2/xfeatures2d.hpp"
using namespace cv;
using namespace cv::xfeatures2d;
void readme();
/* @function main */
int main( int argc, char** argv )
{
if( argc != 3 )
{ readme(); return -1; }
Mat img_object = imread( argv[1], IMREAD_GRAYSCALE );
Mat img_scene = imread( argv[2], IMREAD_GRAYSCALE );
if( !img_object.data || !img_scene.data )
{ std::cout<< " --(!) Error reading images " << std::endl; return -1; }
//-- Step 1: Detect the keypoints and extract descriptors using SURF
int minHessian = 400;
Ptr<SURF> detector = SURF::create( minHessian );
std::vector<KeyPoint> keypoints_object, keypoints_scene;
Mat descriptors_object, descriptors_scene;
detector->detectAndCompute( img_object, Mat(), keypoints_object, descriptors_object );
detector->detectAndCompute( img_scene, Mat(), keypoints_scene, descriptors_scene );
//-- Step 2: Matching descriptor vectors using FLANN matcher
std::vector< DMatch > matches;
matcher.match( descriptors_object, descriptors_scene, matches );
double max_dist = 0; double min_dist = 100;
//-- Quick calculation of max and min distances between keypoints
for( int i = 0; i < descriptors_object.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 3*min_dist )
std::vector< DMatch > good_matches;
for( int i = 0; i < descriptors_object.rows; i++ )
{ if( matches[i].distance <= 3*min_dist )
{ good_matches.push_back( matches[i]); }
}
Mat img_matches;
drawMatches( img_object, keypoints_object, img_scene, keypoints_scene,
good_matches, img_matches, Scalar::all(-1), Scalar::all(-1),
//-- Localize the object
std::vector<Point2f> obj;
std::vector<Point2f> scene;
for( size_t i = 0; i < good_matches.size(); i++ )
{
//-- Get the keypoints from the good matches
obj.push_back( keypoints_object[ good_matches[i].queryIdx ].pt );
scene.push_back( keypoints_scene[ good_matches[i].trainIdx ].pt );
}
Mat H = findHomography( obj, scene, RANSAC );
//-- Get the corners from the image_1 ( the object to be "detected" )
std::vector<Point2f> obj_corners(4);
obj_corners[0] = cvPoint(0,0); obj_corners[1] = cvPoint( img_object.cols, 0 );
obj_corners[2] = cvPoint( img_object.cols, img_object.rows ); obj_corners[3] = cvPoint( 0, img_object.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_object.cols, 0), scene_corners[1] + Point2f( img_object.cols, 0), Scalar(0, 255, 0), 4 );
line( img_matches, scene_corners[1] + Point2f( img_object.cols, 0), scene_corners[2] + Point2f( img_object.cols, 0), Scalar( 0, 255, 0), 4 );
line( img_matches, scene_corners[2] + Point2f( img_object.cols, 0), scene_corners[3] + Point2f( img_object.cols, 0), Scalar( 0, 255, 0), 4 );
line( img_matches, scene_corners[3] + Point2f( img_object.cols, 0), scene_corners[0] + Point2f( img_object.cols, 0), Scalar( 0, 255, 0), 4 );
//-- Show detected matches
imshow( "Good Matches & Object detection", img_matches );
waitKey(0);
return 0;
}
/* @function readme */
void readme()
{ std::cout << " Usage: ./SURF_descriptor <img1> <img2>" << std::endl; }

Explanation

Result

  1. And here is the result for the detected object (highlighted in green)

cv::Mat::rows
int rows
the number of rows and columns or (-1, -1) when the matrix has more than 2 dimensions
Definition: mat.hpp:1959
calib3d.hpp
cv::Point_< float >
cv::Scalar_< double >::all
static Scalar_< double > all(double v0)
returns a scalar with all elements set to v0
imgproc.hpp
cv::Point2f
Point_< float > Point2f
Definition: types.hpp:181
cv::waitKey
int waitKey(int delay=0)
Waits for a pressed key.
highgui.hpp
cv::IMREAD_GRAYSCALE
@ IMREAD_GRAYSCALE
If set, always convert image to the single channel grayscale image.
Definition: imgcodecs.hpp:66
cv::Scalar_< double >
cv::DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS
@ NOT_DRAW_SINGLE_POINTS
Single keypoints will not be drawn.
Definition: features2d.hpp:1124
cv::FlannBasedMatcher
Flann-based descriptor matcher.
Definition: features2d.hpp:1069
cv::findHomography
Mat findHomography(InputArray srcPoints, InputArray dstPoints, int method=0, double ransacReprojThreshold=3, OutputArray mask=noArray(), const int maxIters=2000, const double confidence=0.995)
Finds a perspective transformation between two planes.
cv::line
void line(InputOutputArray img, Point pt1, Point pt2, const Scalar &color, int thickness=1, int lineType=LINE_8, int shift=0)
Draws a line segment connecting two points.
cv::imread
Mat imread(const String &filename, int flags=IMREAD_COLOR)
Loads an image from a file.
cv::Mat::cols
int cols
Definition: mat.hpp:1959
cv::drawMatches
void drawMatches(InputArray img1, const std::vector< KeyPoint > &keypoints1, InputArray img2, const std::vector< KeyPoint > &keypoints2, const std::vector< DMatch > &matches1to2, InputOutputArray outImg, const Scalar &matchColor=Scalar::all(-1), const Scalar &singlePointColor=Scalar::all(-1), const std::vector< char > &matchesMask=std::vector< char >(), int flags=DrawMatchesFlags::DEFAULT)
Draws the found matches of keypoints from two images.
cv::DescriptorMatcher::match
void match(InputArray queryDescriptors, InputArray trainDescriptors, std::vector< DMatch > &matches, InputArray mask=noArray()) const
Finds the best match for each descriptor from a query set.
cvPoint
CvPoint cvPoint(int x, int y)
Definition: types_c.h:882
cv::Ptr
Template class for smart pointers with shared ownership.
Definition: cvstd.hpp:281
cv::RANSAC
@ RANSAC
RANSAC algorithm.
Definition: calib3d.hpp:231
cv::imshow
void imshow(const String &winname, InputArray mat)
Displays an image in the specified window.
features2d.hpp
cv::Mat
n-dimensional dense array class
Definition: mat.hpp:741
i
for i
Definition: modelConvert.m:63
cv::perspectiveTransform
void perspectiveTransform(InputArray src, OutputArray dst, InputArray m)
Performs the perspective matrix transformation of vectors.
core.hpp
cv
Definition: affine.hpp:52
cv::Mat::data
uchar * data
pointer to the data
Definition: mat.hpp:1961