OpenCV: how to use createBackgroundSubtractorMOG

Question

I was trying to go through this tutorial på OpenCV.org:

http://docs.opencv.org/trunk/doc/tutorials/video/background_subtraction/background_subtraction.html#background-subtraction

The MOG pointer is initialized as

Ptr<BackgroundSubtractor> pMOG; //MOG Background subtractor

and in main, it is used in the following manner:

pMOG = createBackgroundSubtractorMOG();

However, this yields the following error:

    Error: Identifier "createBackgroundSubtractorMOG" is undefined

Also, when the background model is to be updated, the following command is used:

pMOG->apply(frame, fgMaskMOG);

Which in turn yields the following error:

    Error: class "cv::BackgroundSubtractor" has no member "apply"

Any idea of what can be done about this? Many thanks in advance!

Here is the entire tutorial code:

//opencv
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/video/background_segm.hpp>
//C
#include <stdio.h>
//C++
#include <iostream>
#include <sstream>

using namespace cv;
using namespace std;

//global variables
Mat frame; //current frame
Mat fgMaskMOG; //fg mask generated by MOG method
Mat fgMaskMOG2; //fg mask fg mask generated by MOG2 method
Ptr<BackgroundSubtractor> pMOG; //MOG Background subtractor
Ptr<BackgroundSubtractor> pMOG2; //MOG2 Background subtractor
int keyboard;

//function declarations
void help();
void processVideo(char* videoFilename);
void processImages(char* firstFrameFilename);

void help()
{
  cout
  << "--------------------------------------------------------------------------"  << endl
  << "This program shows how to use background subtraction methods provided by "   << endl
  << " OpenCV. You can process both videos (-vid) and images (-img)."              << endl
                                                                                   << endl
  << "Usage:"                                                                      << endl
  << "./bs {-vid <video filename>|-img <image filename>}"                          << endl
  << "for example: ./bs -vid video.avi"                                            << endl
  << "or: ./bs -img /data/images/1.png"                                            << endl
  << "--------------------------------------------------------------------------"  << endl
  << endl;
}

int main(int argc, char* argv[])
{
  //print help information
  help();

  //check for the input parameter correctness
  if(argc != 3) {
    cerr <<"Incorret input list" << endl;
    cerr <<"exiting..." << endl;
    return EXIT_FAILURE;
  }

  //create GUI windows
  namedWindow("Frame");
  namedWindow("FG Mask MOG");
  namedWindow("FG Mask MOG 2");

  //create Background Subtractor objects
  pMOG = createBackgroundSubtractorMOG(); //MOG approach
  pMOG2 = createBackgroundSubtractorMOG2(); //MOG2 approach

  if(strcmp(argv[1], "-vid") == 0) {
    //input data coming from a video
    processVideo(argv[2]);
  }
  else if(strcmp(argv[1], "-img") == 0) {
    //input data coming from a sequence of images
    processImages(argv[2]);
  }
  else {
    //error in reading input parameters
    cerr <<"Please, check the input parameters." << endl;
    cerr <<"Exiting..." << endl;
    return EXIT_FAILURE;
  }
  //destroy GUI windows
  destroyAllWindows();
  return EXIT_SUCCESS;
}

void processVideo(char* videoFilename) {
  //create the capture object
  VideoCapture capture(videoFilename);
  if(!capture.isOpened()){
    //error in opening the video input
    cerr << "Unable to open video file: " << videoFilename << endl;
    exit(EXIT_FAILURE);
  }
  //read input data. ESC or 'q' for quitting
  while( (char)keyboard != 'q' && (char)keyboard != 27 ){
    //read the current frame
    if(!capture.read(frame)) {
      cerr << "Unable to read next frame." << endl;
      cerr << "Exiting..." << endl;
      exit(EXIT_FAILURE);
    }
    //update the background model
    pMOG->apply(frame, fgMaskMOG);
    pMOG2->apply(frame, fgMaskMOG2);
    //get the frame number and write it on the current frame
    stringstream ss;
    rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
              cv::Scalar(255,255,255), -1);
    ss << capture.get(CAP_PROP_POS_FRAMES);
    string frameNumberString = ss.str();
    putText(frame, frameNumberString.c_str(), cv::Point(15, 15),
            FONT_HERSHEY_SIMPLEX, 0.5 , cv::Scalar(0,0,0));
    //show the current frame and the fg masks
    imshow("Frame", frame);
    imshow("FG Mask MOG", fgMaskMOG);
    imshow("FG Mask MOG 2", fgMaskMOG2);
    //get the input from the keyboard
    keyboard = waitKey( 30 );
  }
  //delete capture object
  capture.release();
}

void processImages(char* fistFrameFilename) {
  //read the first file of the sequence
  frame = imread(fistFrameFilename);
  if(!frame.data){
    //error in opening the first image
    cerr << "Unable to open first image frame: " << fistFrameFilename << endl;
    exit(EXIT_FAILURE);
  }
  //current image filename
  string fn(fistFrameFilename);
  //read input data. ESC or 'q' for quitting
  while( (char)keyboard != 'q' && (char)keyboard != 27 ){
    //update the background model
    pMOG->apply(frame, fgMaskMOG);
    pMOG2->apply(frame, fgMaskMOG2);
    //get the frame number and write it on the current frame
    size_t index = fn.find_last_of("/");
    if(index == string::npos) {
      index = fn.find_last_of("\\");
    }
    size_t index2 = fn.find_last_of(".");
    string prefix = fn.substr(0,index+1);
    string suffix = fn.substr(index2);
    string frameNumberString = fn.substr(index+1, index2-index-1);
    istringstream iss(frameNumberString);
    int frameNumber = 0;
    iss >> frameNumber;
    rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
              cv::Scalar(255,255,255), -1);
    putText(frame, frameNumberString.c_str(), cv::Point(15, 15),
            FONT_HERSHEY_SIMPLEX, 0.5 , cv::Scalar(0,0,0));
    //show the current frame and the fg masks
    imshow("Frame", frame);
    imshow("FG Mask MOG", fgMaskMOG);
    imshow("FG Mask MOG 2", fgMaskMOG2);
    //get the input from the keyboard
    keyboard = waitKey( 30 );
    //search for the next image in the sequence
    ostringstream oss;
    oss << (frameNumber + 1);
    string nextFrameNumberString = oss.str();
    string nextFrameFilename = prefix + nextFrameNumberString + suffix;
    //read the next frame
    frame = imread(nextFrameFilename);
    if(!frame.data){
      //error in opening the next image in the sequence
      cerr << "Unable to open image frame: " << nextFrameFilename << endl;
      exit(EXIT_FAILURE);
    }
    //update the path of the current frame
    fn.assign(nextFrameFilename);
  }
}

Le

Answer 1

I happened to meet this problem today. This tutorial is for opencv 3.0, not for opencv 2.4+, make a few changes as follows:

//opencv
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/video/background_segm.hpp>
//C
#include <stdio.h>
//C++
#include <iostream>
#include <sstream>

using namespace cv;
using namespace std;

//global variables
Mat frame; //current frame
Mat fgMaskMOG; //fg mask generated by MOG method
Mat fgMaskMOG2; //fg mask fg mask generated by MOG2 method
Ptr<BackgroundSubtractor> pMOG; //MOG Background subtractor
Ptr<BackgroundSubtractor> pMOG2; //MOG2 Background subtractor
int keyboard;

//function declarations
void help();
void processVideo(char* videoFilename);
void processImages(char* firstFrameFilename);

void help()
{
    cout
        << "--------------------------------------------------------------------------"  << endl
        << "This program shows how to use background subtraction methods provided by "   << endl
        << " OpenCV. You can process both videos (-vid) and images (-img)."              << endl
        << endl
        << "Usage:"                                                                      << endl
        << "./bs {-vid <video filename>|-img <image filename>}"                          << endl
        << "for example: ./bs -vid video.avi"                                            << endl
        << "or: ./bs -img /data/images/1.png"                                            << endl
        << "--------------------------------------------------------------------------"  << endl
        << endl;
}

int main(int argc, char* argv[])
{
    //print help information
    help();

    //check for the input parameter correctness
    if(argc != 3) {
        cerr <<"Incorret input list" << endl;
        cerr <<"exiting..." << endl;
        return EXIT_FAILURE;
    }

    //create GUI windows
    namedWindow("Frame");
    namedWindow("FG Mask MOG");
    namedWindow("FG Mask MOG 2");

    //create Background Subtractor objects
   //NOTE HERE!!!!
    pMOG= new BackgroundSubtractorMOG(); //MOG approach
    pMOG2 = new BackgroundSubtractorMOG2(); //MOG2 approach

    if(strcmp(argv[1], "-vid") == 0) {
        //input data coming from a video
        processVideo(argv[2]);
    }
    else if(strcmp(argv[1], "-img") == 0) {
        //input data coming from a sequence of images
        processImages(argv[2]);
    }
    else {
        //error in reading input parameters
        cerr <<"Please, check the input parameters." << endl;
        cerr <<"Exiting..." << endl;
        return EXIT_FAILURE;
    }
    //destroy GUI windows
    destroyAllWindows();
    return EXIT_SUCCESS;
}

void processVideo(char* videoFilename) {
    //create the capture object
    VideoCapture capture(videoFilename);
    if(!capture.isOpened()){
        //error in opening the video input
        cerr << "Unable to open video file: " << videoFilename << endl;
        exit(EXIT_FAILURE);
    }
    //read input data. ESC or 'q' for quitting
    while( (char)keyboard != 'q' && (char)keyboard != 27 ){
        //read the current frame
        if(!capture.read(frame)) {
            cerr << "Unable to read next frame." << endl;
            cerr << "Exiting..." << endl;
            exit(EXIT_FAILURE);
        }
        //update the background model
           //AND HERE!!!
        pMOG->operator()(frame, fgMaskMOG);
        pMOG2->operator()(frame, fgMaskMOG2);
        //get the frame number and write it on the current frame
        stringstream ss;
        rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
            cv::Scalar(255,255,255), -1);
        ss << capture.get(CV_CAP_PROP_POS_FRAMES);
        string frameNumberString = ss.str();
        putText(frame, frameNumberString.c_str(), cv::Point(15, 15),
            FONT_HERSHEY_SIMPLEX, 0.5 , cv::Scalar(0,0,0));
        //show the current frame and the fg masks
        imshow("Frame", frame);
        imshow("FG Mask MOG", fgMaskMOG);
        imshow("FG Mask MOG 2", fgMaskMOG2);
        //get the input from the keyboard
        keyboard = waitKey( 30 );
    }
    //delete capture object
    capture.release();
}

void processImages(char* fistFrameFilename) {
    //read the first file of the sequence
    frame = imread(fistFrameFilename);
    if(!frame.data){
        //error in opening the first image
        cerr << "Unable to open first image frame: " << fistFrameFilename << endl;
        exit(EXIT_FAILURE);
    }
    //current image filename
    string fn(fistFrameFilename);
    //read input data. ESC or 'q' for quitting
    while( (char)keyboard != 'q' && (char)keyboard != 27 ){
        //update the background model
            //ALSO HERE!!!!
        pMOG->operator()(frame, fgMaskMOG);
        pMOG2->operator()(frame, fgMaskMOG2);
        //get the frame number and write it on the current frame
        size_t index = fn.find_last_of("/");
        if(index == string::npos) {
            index = fn.find_last_of("\\");
        }
        size_t index2 = fn.find_last_of(".");
        string prefix = fn.substr(0,index+1);
        string suffix = fn.substr(index2);
        string frameNumberString = fn.substr(index+1, index2-index-1);
        istringstream iss(frameNumberString);
        int frameNumber = 0;
        iss >> frameNumber;
        rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
            cv::Scalar(255,255,255), -1);
        putText(frame, frameNumberString.c_str(), cv::Point(15, 15),
            FONT_HERSHEY_SIMPLEX, 0.5 , cv::Scalar(0,0,0));
        //show the current frame and the fg masks
        imshow("Frame", frame);
        imshow("FG Mask MOG", fgMaskMOG);
        imshow("FG Mask MOG 2", fgMaskMOG2);
        //get the input from the keyboard
        keyboard = waitKey( 30 );
        //search for the next image in the sequence
        ostringstream oss;
        oss << (frameNumber + 1);
        string nextFrameNumberString = oss.str();
        string nextFrameFilename = prefix + nextFrameNumberString + suffix;
        //read the next frame
        frame = imread(nextFrameFilename);
        if(!frame.data){
            //error in opening the next image in the sequence
            cerr << "Unable to open image frame: " << nextFrameFilename << endl;
            exit(EXIT_FAILURE);
        }
        //update the path of the current frame
        fn.assign(nextFrameFilename);
    }
}

Ganger

Though it doesn't work that well, at least not for tracking a person in front of the web cam, maybe it is better when tracking people in the streets or similar. It seems like it never really forgets the first frame. No matter what parameter values I use, the first frame is like a constant mask. I am assuming that i without any other changes just use VideoCapture capture(0); instead of VideoCapture capture(videoFilename); – Le

Ok, I got it! Just changed the learning rate: pMOG->operator()(frame, fgMaskMOG, 0.1); Don't really get why 0.0 would be default, but anyway, I'm happy now :) – Le

hello.how can I run the program? I mean how can I input a command like -vid Video_001.avi. Thank you – League

you can parse argv in main(int argc, char **argv) as you want; if you are using linux, function getopt_long may be a good help. – Ganger

I found a tutorial about background extraction in youtube.com/watch?v=YA_lWWhePW8. Do you think he use MOG method. As my see, he capture the first frame and used as background and compare with other frame to get object by using threshold. Anyone used that way? – Ancona

after the 3.0-gold-release come out, there is no BackgroundSubtractorMOG now, only MOG2 left, and you cannot new it manually, but with createBackgroundSubtractorMOG2 method – Frescobaldi

Answer 2

Accordingly to the previous answer the background subtractor can be also defined as:

BackgroundSubtractorMOG MOG;

instead of:

Ptr<BackgroundSubtractor> pMOG;
pMOG= new BackgroundSubtractorMOG(); //MOG approach

that would also require to delete pMOG when it is not used anymore, furthermore functor can be used to update foreground mask in a bit smarter way:

MOG(newFrame, foregroundMask);

insted of:

pMOG->operator()(frame, fgMaskMOG);

The default assumption of openCV is that the background is quite constant and does not need any update, so, after the learning initial phase the Mixture of Gaussians is not changed any more. A detailed and clear description can be also be found here:

http://hal.archives-ouvertes.fr/docs/00/33/82/06/PDF/RPCS_2008.pdf

Comprehensive

The officially recommended approach is to use makePtr<> or Algorithm::create, NOT new. See the OpenCV 3 Transition Guide. – Gravimeter

Answer 3

I also had the same issue: Error: Identifier "createBackgroundSubtractorMOG" is undefined which was because I was missing link to opencv library libopencv_video.so in my algorithm.

I solved this by including libopencv_video.so during linking of the project which can be done in your Makefile like this: -L/usr/local/lib/libopencv_video.so

It resolved the error and I am able to use the original tutorial as given here: http://docs.opencv.org/3.0-beta/doc/tutorials/video/background_subtraction/background_subtraction.html

Oxus

Funny that the correct answer (linking with the required video module) has just now been suggested. +1 – Gravimeter

But note that the function in the current tutorial (as of 3.1) is createBackgroundSubtractorMOG2, which incidentally is declared in opencv2/video/background_segm.hpp, which should make it fairly obvious with which module you should link. :) – Gravimeter

Answer 4

If you want the MOG method to work, you should

#include "opencv2/bgsegm.hpp"

and then

pMOG = bgsegm::createBackgroundSubtractorMOG();

Alit