OpenCV cv::findHomography 运行时错误答案

【问题标题】：OpenCV cv::findHomography runtime errorOpenCV cv::findHomography 运行时错误
【发布时间】：2012-01-21 03:48:03
【问题描述】：

我正在使用 Features2D + Homography to find a known object 教程编译和运行代码，我得到了这个

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

运行时错误。调试后发现程序在 findHomography 函数处崩溃。

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

在 OpenCV 的 Introduction 中，“cv 命名空间”一章说

一些当前或未来的 OpenCV 外部名称可能与 STL 或其他库冲突。在这种情况下，使用显式命名空间说明符来解决名称冲突：

我更改了我的代码并在任何地方使用显式命名空间说明符，但问题没有解决。如果可以的话，请帮我解决这个问题，或者说哪个函数和 findHomography 做同样的事情，并且不要让程序崩溃。

这是我的代码

#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; }

【问题讨论】：

看起来不像是命名空间问题。如果您查看第一条错误消息，它表示断言失败（可能是findHomography 函数）：看起来您的findHomography 的至少一个输入点数组中没有足够的点。您能否发布一个 sn-p 显示您如何使用 findHomography 以及如何生成积分？
见上文，我编辑了我的问题
Hmmm... 在执行 findHomography 之前尝试 std::couting obj.size() 和 scene.size() - 也许优化器在 obj 和 @987654334 之间找不到任何好的匹配项@ 和所以 findHomography 没有足够的资源来进行计算。

标签： c++ opencv object-detection homography

【解决方案1】：

今天我在这个示例代码中遇到了同样的问题。 @mathematical-coffee 是对的，没有提取任何特征，因此 obj 和场景是空的。我更换了测试图片，它起作用了。您无法从纹理样式图像中提取 SURF 特征。

另一种方法是降低参数 minHessianve.g。 `int minHessian = 20;

或通过更改几行来使用 FAST 特征检测器：

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

  FastFeatureDetector detector( minHessian );

【讨论】：

【解决方案2】：

我遇到了同样的问题，我遵循了 MMH 的解决方案。随便写

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

解决了问题。

【讨论】：

【解决方案3】：

实际答案在错误信息中：

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

人类可读的翻译，你必须满足这些断言：

您的输入必须具有正数的点数（实际上 findHomography 需要 4 个或更多点）。
您的“对象”和“场景”点列表必须具有相同的点数。
您的“对象”和“场景”点列表必须具有相同类型的点。

【讨论】：

【解决方案4】：

更有可能是问题出在这里：

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

严格的不等式不是你想要的。如果min_dist == 0，一个很好的匹配，你会忽略所有的零距离点。替换为：

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

您应该会看到匹配良好的图像的良好结果。

为了优雅地退出，我还要添加，例如：

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

【讨论】：

【解决方案5】：

需要在findHomography前加一个条件

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 );
}

【讨论】：