How to detect multiple objects with OpenCV in C++?

Question

I got inspiration from this answer here, which is a Python implementation, but I need C++, that answer works very well, I got the thought is that: detectAndCompute to get keypoints, use kmeans to segment them to clusters, then for each cluster do matcher->knnMatch with each's descriptors, then do the other stuffs like the common single detecting method. The main problem is, how to provide descriptors for each cluster's matcher->knnMatch process? I thought we should set value of the other keypoints corresponding descriptor to 0(useless), am I right? And got some problems in my trying:

how to estimate cluster count for kmeans?
Why can create Mat array for clusters like this Mat descriptors_scene_clusters[3] = { Mat(descriptors_scene.rows, descriptors_scene.cols, CV_8U, Scalar(0)) };?

Very appreciate any help, pls!

#include <stdio.h>
#include <iostream>
#include <opencv2/core/core.hpp>
#include <opencv2/features2d/features2d.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/calib3d/calib3d.hpp>
#include <opencv2/xfeatures2d.hpp>

using namespace cv;
using namespace cv::xfeatures2d;

#define MIN_MATCH_COUNT 10

int main()
{
    Mat img_object = imread("./2.PNG", IMREAD_GRAYSCALE);
    Mat img_scene = imread("./1.PNG", IMREAD_GRAYSCALE);

    Ptr<ORB> detector = ORB::create();
    std::vector<KeyPoint> keypoints_object, keypoints_scene;
    Mat descriptors_object, descriptors_scene;
    detector->detectAndCompute(img_object, cv::Mat(), keypoints_object, descriptors_object);
    detector->detectAndCompute(img_scene, cv::Mat(), keypoints_scene, descriptors_scene);


    std::cout << descriptors_scene.row(0) << "\n";
    std::cout << descriptors_scene.cols << "\n";


    std::vector<Point2f> keypoints_scene_points_;
    for (int i=0; i<keypoints_scene.size(); i++) {
        keypoints_scene_points_.push_back(keypoints_scene[i].pt);
    }
    Mat keypoints_scene_points(keypoints_scene_points_);

    Mat labels;
    int estimate_cluster_count = 3; // estimated ??????????
    kmeans(keypoints_scene_points, estimate_cluster_count, labels, TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 10, 1.0), 3, KMEANS_RANDOM_CENTERS);

    std::cout << "==================================111111\n";

    Mat descriptors_scene_clusters[3] = { Mat(descriptors_scene.rows, descriptors_scene.cols, CV_8U, Scalar(0)) };

    std::cout << "==================================111111------\n";

    for (int i=0; i<labels.rows; i++) {
        int clusterIndex = labels.at<int>(i);
        Point2f pt = keypoints_scene_points.at<Point2f>(i);
        descriptors_scene_clusters[clusterIndex].at<uchar>(pt) = descriptors_scene.at<uchar>(pt);  // ?????? error
    }

    std::cout << descriptors_scene_clusters[0] << "\n";
    std::cout << "==================================22222222\n";
    // return 0;

    Mat img_matches = img_scene;
    std::vector<DMatch> all_good_matches;
    for (int i=0; i<estimate_cluster_count; i++) {
        std::cout << "==================================33333\n";

        Ptr<flann::IndexParams> indexParams = makePtr<flann::KDTreeIndexParams>(5);
        Ptr<flann::SearchParams> searchParams = makePtr<flann::SearchParams>(50);
        Ptr<FlannBasedMatcher> matcher = makePtr<FlannBasedMatcher>(indexParams, searchParams);
        // BFMatcher matcher;
        std::vector<std::vector<DMatch>> matches;

        std::cout << "==================================444444\n";
        matcher->knnMatch(descriptors_object, descriptors_scene_clusters[i], matches, 2);
        std::cout << "==================================555555\n";
        std::vector<DMatch> good_matches;

        for (auto &match : matches) {
            if (match[0].distance < 0.7 * match[1].distance) {
                good_matches.push_back(match[0]);
            }
        }

        all_good_matches.insert(all_good_matches.end(), good_matches.begin(), good_matches.end());

        std::cout << "==================================66666\n";

        if (good_matches.size() > MIN_MATCH_COUNT) {

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

            for (auto &match : good_matches) {
                //-- Get the keypoints from the good matches
                obj.push_back(keypoints_object[match.queryIdx].pt);
                scene.push_back(keypoints_scene[match.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);

            print(scene_corners);
        }
    }

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


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

    waitKey(0);
    return 0;
}

Try this question, it has some theory in the answers, hope it will help — stackoverflower
– stackoverflower, Commented Sep 28, 2018 at 18:48
Can you attach some sample images and expected output as well ? — ZdaR
– ZdaR, Commented Oct 4, 2018 at 8:04
Your question is about detecting multiple objects? So do you want to detect if the given screenshot contains the desired set of icons? — ZdaR
– ZdaR, Commented Oct 4, 2018 at 9:15
@ZdaR, yes, I need to detect multiple objects from a given scene. — Suge
– Suge, Commented Oct 4, 2018 at 9:16

Cristi · Accepted Answer · 2018-10-06 04:13:42Z

You can use a simple clusterer to either directly compute the clusters, find the number of clusters and / or the cluster centers initialization for kmeans. Here below a possible implementation of an agglomerative clusterer, which groups together points closer to a specified distance - see parameter dist in constructor. In your case dist can be the biggest distance between keypoints in the small image.

Header file:

class PointsClusterer {
public:
     PointsClusterer (int dist, std::vector <cv::Point2f> points);
     bool cluster();
     std::map <int, std::vector <cv::Point2f>> getClusters ();

private:

    double distance (int i, int j);
    void merge (int i, int j);

private:

    std::vector <cv::Point2f> m_Points;
    std::map <int, std::vector <int>> m_Clusters;
    std::map <int, cv::Point2f> m_Sums;
    int m_dist = 0;
};

Cpp file:

PointsClusterer::PointsClusterer (int dist, std::vector <cv::Point2f> points) :
m_dist(dist), m_Points (points)
{}

bool PointsClusterer::cluster()
{
//initialization
    for (int i = 0; i < m_Points.size(); ++i)
    {
        clusters[i] = std::vector<int>(1, i);
        sum_clusters[i] = m_Points[i];
    }

    bool still_merge = true;
    //Merge clusters
    while (still_merge)
    {
        still_merge = false;
        bool break_i = false;

        for (int i=0; i < m_Clusters.size () && !break_i ;++i)
        for (int j=i+1; j < m_Clusters.size ();++j)
        {
            if (distance(i, j) < m_dist)
            {
                merge(i, j);
                break_i = true;
                still_merge = true;
                break;
            }
        }
    }
//final conversion to std::map <int, std::vector <cv::Point2f>> is missing

}


void PointsClusterer::merge(int i, int j)
{
    auto it = m_Clusters.begin();
    auto iti = it+i;
    auto itj = it+j;

    for (val : itj->second)
    {
         iti->second.push_back(val);
         m_Sums[iti->first]+=m_Points[val];
    }
    m_Clusters.erase(itj);
}

double PointsClusterer::distance(int i, int j)
{
    auto it = m_Clusters.begin();
    auto iti = it + i;
    auto itj = it + j;
    auto vali = m_Sums[iti->first] / iti->second.size();
    auto valj = m_Sums[itj->first] / itj->second.size();
    return cv::norm(vali - valj);
}

The implementation of the cluster method was oversimplified such that it is obvious how it works. Its performance can be improved, but I believe that is beyond the scope of your question.

krjw · Accepted Answer · 2018-10-17 20:08:04Z

I don't know a solution to your problem, but the following might help answer the questions you've asked.

In the comments it says that you might need an implementation of meanshift, which opencv already has. Here an example, here the documentation with a tutorial.

The clusterCount for kmeansis the number of clusters you want to create link. I don't know how to estimate the number you want to create, but I guess you could know.
You initialize descriptors_scene_clusters only with one element:

Mat descriptors_scene_clusters[3] = { Mat(descriptors_scene.rows, descriptors_scene.cols, CV_8U, Scalar(0)) };

And when you iterate over it:

for (int i=0; i<labels.rows; i++) {
    int clusterIndex = labels.at<int>(i);
    Point2f pt = keypoints_scene_points.at<Point2f>(i);
    descriptors_scene_clusters[clusterIndex].at<uchar>(pt) = descriptors_scene.at<uchar>(pt);  // ?????? error
}

clusterIndex is 2 and you access an uninitialized element in the array, which results in the EXEC_BAD_ACCESS error.

I hope this helps for further investigation!

Collectives™ on Stack Overflow

How to detect multiple objects with OpenCV in C++?

2 Answers 2

Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related