How To Implement Simple Background Subtraction?¶

Introduction

A simple background subtraction can help to you extract foreground pixels. Sometimes, we need to extract foreground pixels for an approach to analysis. To know the foreground pixels that are our interesting things. Let’s do it.

Equipment

Operation System: Microsoft Windows 7 (64 bit)
Development Utility: Microsoft Visual Studio 2010

Usage

    // The height of the image.
    for ( int iY = 0; iY < imageA->DibInfo->bmiHeader.biHeight; iY++ )
    {
        // The width of the image.
        for ( int iX = 0; iX < imageA->DibInfo->bmiHeader.biWidth; iX++ )
        {
            // The index of pixels of the image, if your bit depth is not three bit depth, you should change it and fit your bitmap format.
            lIDXA = ( iX * 3 ) + ( iY * imageA->DibInfo->bmiHeader.biWidth * 3 );
            // To get the pixel of the blue channel of the background image.
            byteRGB_BA = imageA->DibArry[lIDXA+0];
            // To get the pixel of the green channel of the background image.
            byteRGB_GA = imageA->DibArry[lIDXA+1];
            // To get the pixel of the red channel of the background image.
            byteRGB_RA = imageA->DibArry[lIDXA+2];
            // Transform RGB to Y (gray scale).
            dobYUV_YA =  (0.299 * byteRGB_RA + 0.587 * byteRGB_GA + 0.114 * byteRGB_BA);

            // The index of pixels of the image, if your bit depth is not three bit depth, you should change it and fit your bitmap format.
            lIDXB = ( iX * 3 ) + ( iY * imageB->DibInfo->bmiHeader.biWidth * 3 );
            // To get the pixel of the blue channel of the foreground image.
            byteRGB_BB = imageB->DibArry[lIDXB+0];
            // To get the pixel of the green channel of the foreground image.
            byteRGB_GB = imageB->DibArry[lIDXB+1];
            // To get the pixel of the red channel of the foreground image.
            byteRGB_RB = imageB->DibArry[lIDXB+2];
            // Transform RGB to Y (gray scale).
            dobYUV_YB = (0.299 * byteRGB_RB + 0.587 * byteRGB_GB + 0.114 * byteRGB_BB);

            // The index of pixels of the image, if your bit depth is not three bit depth, you should change it and fit your bitmap format.
            lIDXC = ( iX * 3 ) + ( iY * imageC->DibInfo->bmiHeader.biWidth * 3 );
            // To subtraction of background of the blue channel.
            imageC->DibArry[lIDXC+0] = ( dobYUV_YA - dobYUV_YB );
            // To subtraction of background of the green channel.
            imageC->DibArry[lIDXC+1] = ( dobYUV_YA - dobYUV_YB );
            // To subtraction of background of the red channel.
            imageC->DibArry[lIDXC+2] = ( dobYUV_YA - dobYUV_YB );
        } // for ( int iX = 0; iX < imageA->DibInfo->bmiHeader.biWidth; iX++ )
    } // for ( int iY = 0; iY < imageA->DibInfo->bmiHeader.biHeight; iY++ )

You can download source code and binary code form this hyperlink as below.
https://drive.google.com/file/d/0BzHb_OyLyVZlYVJCVmtQU3lTNkU/view?usp=sharing

Exception

1. There is a notice, if your bit depth of bitmap file are not 24 bits, you should change your bitmap files to adapt this program, or you could rewrite this source code to fit your bitmap format.

2. You have to install Microsoft SDK v7.1, because I include windowscodes.lib.
   #pragma comment(lib, "windowscodecs.lib")

Reference

[1] Gary Bradski and Adrian Kaehler, “Learning OpenCV: Computer Vision with the OpenCV Library,” O’REILLY, September 2008, ISBN:978-0-596-51613-0

Acknowledge

Thank you (Microsoft Visual Studio) very much for this great development utility.