OpenCV cv::findHomography runtime error

Question

I am using to compile and run code from Features2D + Homography to find a known object tutorial, and I am getting this

OpenCV Error: Assertion failed (npoints >= 0 && points2.checkVector(2) == npoint
s && points1.type() == points2.type()) in unknown function, file c:\Users\vp\wor
k\ocv\opencv\modules\calib3d\src\fundam.cpp, line 1062

run-time error. after debugging I find that the program is crashing at findHomography function.

Unhandled exception at 0x760ab727 in OpenCVTemplateMatch.exe: Microsoft C++ exception: cv::Exception at memory location 0x0029eb3c..

in the Introduction of OpenCV, the "cv Namespace" chapter says that

Some of the current or future OpenCV external names may conflict with STL or other libraries. In this case, use explicit namespace specifiers to resolve the name conflicts:

I changed my code and use everywhere explicit namespace specifiers, but problem did not solved. If you can, please help me in this problem, or say which function do same thing as findHomography, and do not crash program.

And this is my code

#include <stdio.h>
#include <iostream>
#include "opencv2/core/core.hpp"
#include "opencv2/features2d/features2d.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/calib3d/calib3d.hpp"

void readme();

/** @function main */
int main( int argc, char** argv )
{
    if( argc != 3 )
    { readme(); return -1; }

    cv::Mat img_object = cv::imread( argv[1], CV_LOAD_IMAGE_GRAYSCALE );
    cv::Mat img_scene = cv::imread( argv[2], CV_LOAD_IMAGE_GRAYSCALE );

    if( !img_object.data || !img_scene.data )
    { std::cout<< " --(!) Error reading images " << std::endl; return -1; }

    //-- Step 1: Detect the keypoints using SURF Detector
    int minHessian = 400;

    cv::SurfFeatureDetector detector( minHessian );

    std::vector<cv::KeyPoint> keypoints_object, keypoints_scene;

    detector.detect( img_object, keypoints_object );
    detector.detect( img_scene, keypoints_scene );

    //-- Step 2: Calculate descriptors (feature vectors)
    cv::SurfDescriptorExtractor extractor;

    cv::Mat descriptors_object, descriptors_scene;

    extractor.compute( img_object, keypoints_object, descriptors_object );
    extractor.compute( img_scene, keypoints_scene, descriptors_scene );

    //-- Step 3: Matching descriptor vectors using FLANN matcher
    cv::FlannBasedMatcher matcher;
    std::vector< cv::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< cv::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]); }
    }

    cv::Mat img_matches;
    cv::drawMatches( img_object, keypoints_object, img_scene, keypoints_scene,
        good_matches, img_matches, cv::Scalar::all(-1), cv::Scalar::all(-1),
        std::vector<char>(), cv::DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS );

    //-- Localize the object
    std::vector<cv::Point2f> obj;
    std::vector<cv::Point2f> scene;

    for( int 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 );
    }

    cv::Mat H = cv::findHomography( obj, scene, CV_RANSAC );

    //-- Get the corners from the image_1 ( the object to be "detected" )
    std::vector<cv::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<cv::Point2f> scene_corners(4);

    cv::perspectiveTransform( obj_corners, scene_corners, H);

    //-- Draw lines between the corners (the mapped object in the scene - image_2 )
    cv::line( img_matches, scene_corners[0] + cv::Point2f( img_object.cols, 0), scene_corners[1] + cv::Point2f( img_object.cols, 0), cv::Scalar(0, 255, 0), 4 );
    cv::line( img_matches, scene_corners[1] + cv::Point2f( img_object.cols, 0), scene_corners[2] + cv::Point2f( img_object.cols, 0), cv::Scalar( 0, 255, 0), 4 );
    cv::line( img_matches, scene_corners[2] + cv::Point2f( img_object.cols, 0), scene_corners[3] + cv::Point2f( img_object.cols, 0), cv::Scalar( 0, 255, 0), 4 );
    cv::line( img_matches, scene_corners[3] + cv::Point2f( img_object.cols, 0), scene_corners[0] + cv::Point2f( img_object.cols, 0), cv::Scalar( 0, 255, 0), 4 );

    //-- Show detected matches
    cv::imshow( "Good Matches & Object detection", img_matches );

    cv::waitKey(0);
    return 0;
}

/** @function readme */
void readme()
{ std::cout << " Usage: ./SURF_descriptor <img1> <img2>" << std::endl; }

Answer 1

Today I run into the same problem with this example code. @mathematical-coffee was right there were no features extracted, thus obj and scene were empty. I replaced the test pictures and it worked. From texture style images you can't extract SURF features.

Another way to is to lower the parameter minHessianve.g. `int minHessian = 20;

or use the FAST feature detector by changing a few lines:

  //-- Step 1: Detect the keypoints using SURF Detector
  int minHessian = 15;

  FastFeatureDetector detector( minHessian );

Answer 2

The actual answer is within the error message:

npoints >= 0 && points2.checkVector(2) == npoints && points1.type() == points2.type()

Human readable translation, you have to fulfil these assertions:

• Your input must have a positive number of points (in practice an findHomography needs 4 or more points).

• Your 'object' and 'scene' list of points must have the same number of points.

• Your 'object' and 'scene' list of points must have the same type of points.

Answer 3

I had the same issue and I followed the solution by MMH. Just writing

cv::Mat H = cv::findHomography( cv::Mat(obj), cv::Mat(scene), CV_RANSAC ); cv::perspectiveTransform( cv::Mat(obj_corners), cv::Mat(scene_corners), H);

solved the problem.

Answer 4

More likely, the problem is here:

 if( matches[i].distance < 3*min_dist)

The strict inequality is not what you want. If min_dist == 0 , a very good match, you will disregard all zero-distance points. Replace with:

 if( matches[i].distance <= 3*min_dist)

and you should see good results for images that match well.

To exit gracefully, I would also add, eg:

if (good_matches.size() == 0)
{
  std::cout<< " --(!) No good matches found " << std::endl; return -2; 
}

Answer 5

you need to add a condition before findHomography

if(obj.size()>3){
    ///-- Get the corners from the image_1 ( the object to be "detected" )
    vector<Point2f> obj_corners(4);
    obj_corners[0] = Point(0,0); obj_corners[1] = Point( img_object.cols, 0 );
    obj_corners[2] = Point( img_object.cols, img_object.rows ); obj_corners[3] = Point( 0, img_object.rows );

    Mat H = findHomography( obj, scene,CV_RANSAC  );
    perspectiveTransform( obj_corners, scene_corners, H);
    ///-- Draw lines between the corners (the mapped object in the scene - image_2 )
    for(int i = 0; i < 4; ++i)
        line( fram_tmp, scene_corners[i]+offset, scene_corners[(i + 1) % 4]+offset, Scalar(0, 255, 0), 4 );
}