How to Use Background Subtraction Methods

• Background subtraction (BS) is a common and widely used technique for generating a foreground mask (namely, a binary image containing the pixels belonging to moving objects in the scene) by using static cameras.

• As the name suggests, BS calculates the foreground mask performing a subtraction between the current frame and a background model, containing the static part of the scene or, more in general, everything that can be considered as background given the characteristics of the observed scene.

  

• Background modeling consists of two main steps:

  1. Background Initialization;
  2. Background Update.

  In the first step, an initial model of the background is computed, while in the second step that model is updated in order to adapt to possible changes in the scene.

• In this tutorial we will learn how to perform BS by using OpenCV.

Goals

In this tutorial you will learn how to:

1. Read data from videos or image sequences by using cv::VideoCapture ;
2. Create and update the background model by using cv::BackgroundSubtractor class;
3. Get and show the foreground mask by using cv::imshow ;

Code

In the following you can find the source code. We will let the user choose to process either a video file or a sequence of images.

We will use cv::BackgroundSubtractorMOG2 in this sample, to generate the foreground mask.

The results as well as the input data are shown on the screen.

[block]

C++

• Downloadable code: Click here

• Code at glance:

  
  #include <iostream>
  #include <sstream>
  #include <opencv2/imgcodecs.hpp>
  #include <opencv2/imgproc.hpp>
  #include <opencv2/videoio.hpp>
  #include <opencv2/highgui.hpp>
  #include <opencv2/video.hpp>
  
  using namespace cv;
  using namespace std;
  
  const char* params
      = "{ help h         |                   | Print usage }"
        "{ input          | ../data/vtest.avi | Path to a video or a sequence of image }"
        "{ algo           | MOG2              | Background subtraction method (KNN, MOG2) }";
  
  int main(int argc, char* argv[])
  {
      CommandLineParser parser(argc, argv, params);
      parser.about( "This program shows how to use background subtraction methods provided by "
                    " OpenCV. You can process both videos and images.\n" );
      if (parser.has("help"))
      {
          //print help information
          parser.printMessage();
      }
  
      //create Background Subtractor objects
      Ptr<BackgroundSubtractor> pBackSub;
      if (parser.get<String>("algo") == "MOG2")
          pBackSub = createBackgroundSubtractorMOG2();
      else
          pBackSub = createBackgroundSubtractorKNN();
  
      VideoCapture capture(parser.get<String>("input"));
      if (!capture.isOpened()){
          //error in opening the video input
          cerr << "Unable to open: " << parser.get<String>("input") << endl;
          return 0;
      }
  
      Mat frame, fgMask;
      while (true) {
          capture >> frame;
          if (frame.empty())
              break;
  
          //update the background model
          pBackSub->apply(frame, fgMask);
  
          //get the frame number and write it on the current frame
          rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
                    cv::Scalar(255,255,255), -1);
          stringstream ss;
          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", fgMask);
  
          //get the input from the keyboard
          int keyboard = waitKey(30);
          if (keyboard == 'q' || keyboard == 27)
              break;
      }
  
      return 0;
  }

  [block]

[block]

Java

• Downloadable code: Click here

• Code at glance:

  import org.opencv.core.Core;
  import org.opencv.core.Mat;
  import org.opencv.core.Point;
  import org.opencv.core.Scalar;
  import org.opencv.highgui.HighGui;
  import org.opencv.imgproc.Imgproc;
  import org.opencv.video.BackgroundSubtractor;
  import org.opencv.video.Video;
  import org.opencv.videoio.VideoCapture;
  import org.opencv.videoio.Videoio;
  
  class BackgroundSubtraction {
      public void run(String[] args) {
          String input = args.length > 0 ? args[0] : "../data/vtest.avi";
          boolean useMOG2 = args.length > 1 ? args[1] == "MOG2" : true;
  
          BackgroundSubtractor backSub;
          if (useMOG2) {
              backSub = Video.createBackgroundSubtractorMOG2();
          } else {
              backSub = Video.createBackgroundSubtractorKNN();
          }
  
          VideoCapture capture = new VideoCapture(input);
          if (!capture.isOpened()) {
              System.err.println("Unable to open: " + input);
              System.exit(0);
          }
  
          Mat frame = new Mat(), fgMask = new Mat();
          while (true) {
              capture.read(frame);
              if (frame.empty()) {
                  break;
              }
  
              // update the background model
              backSub.apply(frame, fgMask);
  
              // get the frame number and write it on the current frame
              Imgproc.rectangle(frame, new Point(10, 2), new Point(100, 20), new Scalar(255, 255, 255), -1);
              String frameNumberString = String.format("%d", (int)capture.get(Videoio.CAP_PROP_POS_FRAMES));
              Imgproc.putText(frame, frameNumberString, new Point(15, 15), Core.FONT_HERSHEY_SIMPLEX, 0.5,
                      new Scalar(0, 0, 0));
  
              // show the current frame and the fg masks
              HighGui.imshow("Frame", frame);
              HighGui.imshow("FG Mask", fgMask);
  
              // get the input from the keyboard
              int keyboard = HighGui.waitKey(30);
              if (keyboard == 'q' || keyboard == 27) {
                  break;
              }
          }
  
          HighGui.waitKey();
          System.exit(0);
      }
  }
  
  public class BackgroundSubtractionDemo {
      public static void main(String[] args) {
          // Load the native OpenCV library
          System.loadLibrary(Core.NATIVE_LIBRARY_NAME);
  
          new BackgroundSubtraction().run(args);
      }
  }

  [block]

[block]

Python

• Downloadable code: Click here

• Code at glance:

  from __future__ import print_function
  import cv2 as cv
  import argparse
  
  parser = argparse.ArgumentParser(description='This program shows how to use background subtraction methods provided by \
                                                OpenCV. You can process both videos and images.')
  parser.add_argument('--input', type=str, help='Path to a video or a sequence of image.', default='vtest.avi')
  parser.add_argument('--algo', type=str, help='Background subtraction method (KNN, MOG2).', default='MOG2')
  args = parser.parse_args()
  
  ## [create]
  #create Background Subtractor objects
  if args.algo == 'MOG2':
      backSub = cv.createBackgroundSubtractorMOG2()
  else:
      backSub = cv.createBackgroundSubtractorKNN()
  ## [create]
  
  ## [capture]
  capture = cv.VideoCapture(cv.samples.findFileOrKeep(args.input))
  if not capture.isOpened:
      print('Unable to open: ' + args.input)
      exit(0)
  ## [capture]
  
  while True:
      ret, frame = capture.read()
      if frame is None:
          break
  
      ## [apply]
      #update the background model
      fgMask = backSub.apply(frame)
      ## [apply]
  
      ## [display_frame_number]
      #get the frame number and write it on the current frame
      cv.rectangle(frame, (10, 2), (100,20), (255,255,255), -1)
      cv.putText(frame, str(capture.get(cv.CAP_PROP_POS_FRAMES)), (15, 15),
                 cv.FONT_HERSHEY_SIMPLEX, 0.5 , (0,0,0))
      ## [display_frame_number]
  
      ## [show]
      #show the current frame and the fg masks
      cv.imshow('Frame', frame)
      cv.imshow('FG Mask', fgMask)
      ## [show]
  
      keyboard = cv.waitKey(30)
      if keyboard == 'q' or keyboard == 27:
          break

  [block]

Explanation

We discuss the main parts of the code above:

• A cv::BackgroundSubtractor object will be used to generate the foreground mask. In this example, default parameters are used, but it is also possible to declare specific parameters in the create function.

[block]

C++

    //create Background Subtractor objects
    Ptr<BackgroundSubtractor> pBackSub;
    if (parser.get<String>("algo") == "MOG2")
        pBackSub = createBackgroundSubtractorMOG2();
    else
        pBackSub = createBackgroundSubtractorKNN();

[block]

[block]

Java

        BackgroundSubtractor backSub;
        if (useMOG2) {
            backSub = Video.createBackgroundSubtractorMOG2();
        } else {
            backSub = Video.createBackgroundSubtractorKNN();
        }

[block]

[block]

Python

#create Background Subtractor objects
if args.algo == 'MOG2':
    backSub = cv.createBackgroundSubtractorMOG2()
else:
    backSub = cv.createBackgroundSubtractorKNN()

[block]

• A cv::VideoCapture object is used to read the input video or input images sequence.

[block]

C++

    VideoCapture capture(parser.get<String>("input"));
    if (!capture.isOpened()){
        //error in opening the video input
        cerr << "Unable to open: " << parser.get<String>("input") << endl;
        return 0;
    }

[block]

[block]

Java

        VideoCapture capture = new VideoCapture(input);
        if (!capture.isOpened()) {
            System.err.println("Unable to open: " + input);
            System.exit(0);
        }

[block]

[block]

Python

capture = cv.VideoCapture(cv.samples.findFileOrKeep(args.input))
if not capture.isOpened:
    print('Unable to open: ' + args.input)
    exit(0)

[block]

• Every frame is used both for calculating the foreground mask and for updating the background. If you want to change the learning rate used for updating the background model, it is possible to set a specific learning rate by passing a parameter to the apply method.

[block]

C++

        //update the background model
        pBackSub->apply(frame, fgMask);

[block]

[block]

Java

            // update the background model
            backSub.apply(frame, fgMask);

[block]

[block]

Python

    #update the background model
    fgMask = backSub.apply(frame)

[block]

• The current frame number can be extracted from the cv::VideoCapture object and stamped in the top left corner of the current frame. A white rectangle is used to highlight the black colored frame number.

[block]

C++

        //get the frame number and write it on the current frame
        rectangle(frame, cv::Point(10, 2), cv::Point(100,20),
                  cv::Scalar(255,255,255), -1);
        stringstream ss;
        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));

[block]

[block]

Java

            // get the frame number and write it on the current frame
            Imgproc.rectangle(frame, new Point(10, 2), new Point(100, 20), new Scalar(255, 255, 255), -1);
            String frameNumberString = String.format("%d", (int)capture.get(Videoio.CAP_PROP_POS_FRAMES));
            Imgproc.putText(frame, frameNumberString, new Point(15, 15), Core.FONT_HERSHEY_SIMPLEX, 0.5,
                    new Scalar(0, 0, 0));

[block]

[block]

Python

    #get the frame number and write it on the current frame
    cv.rectangle(frame, (10, 2), (100,20), (255,255,255), -1)
    cv.putText(frame, str(capture.get(cv.CAP_PROP_POS_FRAMES)), (15, 15),
               cv.FONT_HERSHEY_SIMPLEX, 0.5 , (0,0,0))

[block]

• We are ready to show the current input frame and the results.

[block]

C++

        //show the current frame and the fg masks
        imshow("Frame", frame);
        imshow("FG Mask", fgMask);

[block]

[block]

Java

            // show the current frame and the fg masks
            HighGui.imshow("Frame", frame);
            HighGui.imshow("FG Mask", fgMask);

[block]

[block]

Python

    #show the current frame and the fg masks
    cv.imshow('Frame', frame)
    cv.imshow('FG Mask', fgMask)

[block]

Results

• With the vtest.avi video, for the following frame:

  

  The output of the program will look as the following for MOG2 method (gray areas are detected shadows):

  

  The output of the program will look as the following for the KNN method (gray areas are detected shadows):

  

References

• Background Models Challenge (BMC) website
• A Benchmark Dataset for Foreground/Background Extractionvacavant2013benchmark