学习OpenCV——学习grabcut算法

由于make paper的需要，又把以前只大概了解的grabcut算法重新拿出来研究了一下~

grabcut主要是通过Min Cut: Global minimal enegry in polynomial time实现，具体参考论文

OpenCV中的GrabCut算法是依据《"GrabCut" - Interactive Foreground Extraction using Iterated Graph Cuts》这篇文章来实现的。该算法利用了图像中的纹理（颜色）信息和边界（反差）信息，只要少量的用户交互操作即可得到比较好的分割结果。如果前景和背景之间的颜色反差不大，分割的效果不好；不过，这种情况下允许手工标记一些前景或背景区域，这样能得到较好的结果。

 

 

GrabCut函数说明

void grabCut(InputArray img, InputOutputArray mask, Rect rect, InputOutputArraybgdModel, InputOutputArrayfgdModel, intiterCount, intmode=GC_EVAL)

Parameters:

image – Input 8-bit 3-channel image. mask – Input/output 8-bit single-channel mask. The mask is initialized by the function whenmode is set to GC_INIT_WITH_RECT. Its elements may have one of following values: GC_BGD defines an obvious background pixels. GC_FGD defines an obvious foreground (object) pixel. GC_PR_BGD defines a possible background pixel. GC_PR_BGD defines a possible foreground pixel. rect – ROI containing a segmented object. The pixels outside of the ROI are marked as “obvious background”. The parameter is only used whenmode==GC_INIT_WITH_RECT . bgdModel – Temporary array for the background model. Do not modify it while you are processing the same image. fgdModel – Temporary arrays for the foreground model. Do not modify it while you are processing the same image. iterCount – Number of iterations the algorithm should make before returning the result. Note that the result can be refined with further calls withmode==GC_INIT_WITH_MASK ormode==GC_EVAL . mode – Operation mode that could be one of the following: GC_INIT_WITH_RECT The function initializes the state and the mask using the provided rectangle. After that it runsiterCountiterations of the algorithm. GC_INIT_WITH_MASK The function initializes the state using the provided mask. Note thatGC_INIT_WITH_RECT andGC_INIT_WITH_MASK can be combined. Then, all the pixels outside of the ROI are automatically initialized withGC_BGD . GC_EVAL The value means that the algorithm should just resume.

函数原型：
    void cv::grabCut( const Mat& img, Mat& mask, Rect rect,
             Mat& bgdModel, Mat& fgdModel,
             int iterCount, int mode )
其中：
img——待分割的源图像，必须是8位3通道（CV_8UC3）图像，在处理的过程中不会被修改；
mask——掩码图像，如果使用掩码进行初始化，那么mask保存初始化掩码信息；在执行分割的时候，也可以将用户交互所设定的前景与背景保存到mask中，然后再传入grabCut函数；在处理结束之后，mask中会保存结果。mask只能取以下四种值：
GCD_BGD（=0），背景；
GCD_FGD（=1），前景；
GCD_PR_BGD（=2），可能的背景；
GCD_PR_FGD（=3），可能的前景。
如果没有手工标记GCD_BGD或者GCD_FGD，那么结果只会有GCD_PR_BGD或GCD_PR_FGD；
rect——用于限定需要进行分割的图像范围，只有该矩形窗口内的图像部分才被处理；
bgdModel——背景模型，如果为null，函数内部会自动创建一个bgdModel；bgdModel必须是单通道浮点型（CV_32FC1）图像，且行数只能为1，列数只能为13x5；
fgdModel——前景模型，如果为null，函数内部会自动创建一个fgdModel；fgdModel必须是单通道浮点型（CV_32FC1）图像，且行数只能为1，列数只能为13x5；
iterCount——迭代次数，必须大于0；
mode——用于指示grabCut函数进行什么操作，可选的值有：
GC_INIT_WITH_RECT（=0），用矩形窗初始化GrabCut；
GC_INIT_WITH_MASK（=1），用掩码图像初始化GrabCut；
GC_EVAL（=2），执行分割。

 

sample/cpp/grabcut.cpp

#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"

#include <iostream>

using namespace std;
using namespace cv;

void help()
{
    cout << "\nThis program demonstrates GrabCut segmentation -- select an object in a region\n"
    		"and then grabcut will attempt to segment it out.\n"
    		"Call:\n"
    		"./grabcut <image_name>\n"
    	"\nSelect a rectangular area around the object you want to segment\n" <<
        "\nHot keys: \n"
        "\tESC - quit the program\n"
        "\tr - restore the original image\n"
        "\tn - next iteration\n"
        "\n"
        "\tleft mouse button - set rectangle\n"
        "\n"
        "\tCTRL+left mouse button - set GC_BGD pixels\n"
        "\tSHIFT+left mouse button - set CG_FGD pixels\n"
        "\n"
        "\tCTRL+right mouse button - set GC_PR_BGD pixels\n"
        "\tSHIFT+right mouse button - set CG_PR_FGD pixels\n" << endl;
}

const Scalar RED = Scalar(0,0,255);
const Scalar PINK = Scalar(230,130,255);
const Scalar BLUE = Scalar(255,0,0);
const Scalar LIGHTBLUE = Scalar(255,255,160);
const Scalar GREEN = Scalar(0,255,0);

const int BGD_KEY = CV_EVENT_FLAG_CTRLKEY;
const int FGD_KEY = CV_EVENT_FLAG_SHIFTKEY;

//把comMask赋给binMak
void getBinMask( const Mat& comMask, Mat& binMask )
{
    if( comMask.empty() || comMask.type()!=CV_8UC1 )
        CV_Error( CV_StsBadArg, "comMask is empty or has incorrect type (not CV_8UC1)" );
    if( binMask.empty() || binMask.rows!=comMask.rows || binMask.cols!=comMask.cols )
	//设置Mat大小★★★★
        binMask.create( comMask.size(), CV_8UC1 );
    binMask = comMask & 1;//★★★★很重要
}

class GCApplication
{
public:
    enum{ NOT_SET = 0, IN_PROCESS = 1, SET = 2 };
    static const int radius = 2;
    static const int thickness = -1;

    void reset();
    void setImageAndWinName( const Mat& _image, const string& _winName );
    void showImage() const;
    void mouseClick( int event, int x, int y, int flags, void* param );
    int nextIter();
    int getIterCount() const { return iterCount; }
private:
    void setRectInMask();
    void setLblsInMask( int flags, Point p, bool isPr );

    const string* winName;
    const Mat* image;
    Mat mask;
    Mat bgdModel, fgdModel;

    uchar rectState, lblsState, prLblsState;
    bool isInitialized;

    Rect rect;
    vector<Point> fgdPxls, bgdPxls, prFgdPxls, prBgdPxls;
    int iterCount;
};

void GCApplication::reset()
{
    if( !mask.empty() )
		//mask设定为GC_BGD，GC_FGD，GC_PR_BGD中的一种;
        mask.setTo(Scalar::all(GC_BGD));
    bgdPxls.clear(); fgdPxls.clear();
    prBgdPxls.clear();  prFgdPxls.clear();

    isInitialized = false;
    rectState = NOT_SET;
    lblsState = NOT_SET;
    prLblsState = NOT_SET;
    iterCount = 0;
}

void GCApplication::setImageAndWinName( const Mat& _image, const string& _winName  )
{
	if( _image.empty() || _winName.empty() )
		return;
	image = &_image;
	winName = &_winName;
	mask.create( image->size(), CV_8UC1);
	reset();
}

//绘制显示的图像
void GCApplication::showImage() const
{
    if( image->empty() || winName->empty() )
        return;

    Mat res;
    Mat binMask;
    if( !isInitialized )
        image->copyTo( res );
    else
    {
        getBinMask( mask, binMask );
        image->copyTo( res, binMask );
    }

    vector<Point>::const_iterator it;
    for( it = bgdPxls.begin(); it != bgdPxls.end(); ++it )
        circle( res, *it, radius, BLUE, thickness );
    for( it = fgdPxls.begin(); it != fgdPxls.end(); ++it )
        circle( res, *it, radius, RED, thickness );
    for( it = prBgdPxls.begin(); it != prBgdPxls.end(); ++it )
        circle( res, *it, radius, LIGHTBLUE, thickness );
    for( it = prFgdPxls.begin(); it != prFgdPxls.end(); ++it )
        circle( res, *it, radius, PINK, thickness );

    if( rectState == IN_PROCESS || rectState == SET )
        rectangle( res, Point( rect.x, rect.y ), Point(rect.x + rect.width, rect.y + rect.height ), GREEN, 2);

    imshow( *winName, res );
}

//rect中包含要分割的对象，rect外都被认为是（GC_FGD）明显的背景，这个参数只在mode==GC_INIT_WITH_RECT时使用;
void GCApplication::setRectInMask()
{
    assert( !mask.empty() );
    mask.setTo( GC_BGD );
    rect.x = max(0, rect.x);
    rect.y = max(0, rect.y);
    rect.width = min(rect.width, image->cols-rect.x);
    rect.height = min(rect.height, image->rows-rect.y);
    (mask(rect)).setTo( Scalar(GC_PR_FGD) );
}

//保存标注的前景或者背景，保存在mask上;
void GCApplication::setLblsInMask( int flags, Point p, bool isPr )
{
    vector<Point> *bpxls, *fpxls;
    uchar bvalue, fvalue;
    if( !isPr )
    {
        bpxls = &bgdPxls;
        fpxls = &fgdPxls;
        bvalue = GC_BGD;
        fvalue = GC_FGD;
    }
    else
    {
        bpxls = &prBgdPxls;
        fpxls = &prFgdPxls;
        bvalue = GC_PR_BGD;
        fvalue = GC_PR_FGD;
    }
    if( flags & BGD_KEY )
    {
        bpxls->push_back(p);
        circle( mask, p, radius, bvalue, thickness );
    }
    if( flags & FGD_KEY )
    {
        fpxls->push_back(p);
        circle( mask, p, radius, fvalue, thickness );
    }
}

//鼠标事件;
void GCApplication::mouseClick( int event, int x, int y, int flags, void* )
{
    // TODO add bad args check
    switch( event )
    {
    case CV_EVENT_LBUTTONDOWN: // set rect or GC_BGD(GC_FGD) labels
        {
            bool isb = (flags & BGD_KEY) != 0,
                 isf = (flags & FGD_KEY) != 0;
            if( rectState == NOT_SET && !isb && !isf )
            {
                rectState = IN_PROCESS;
                rect = Rect( x, y, 1, 1 );
            }
            if ( (isb || isf) && rectState == SET )
                lblsState = IN_PROCESS;
        }
        break;
    case CV_EVENT_RBUTTONDOWN: // set GC_PR_BGD(GC_PR_FGD) labels
        {
            bool isb = (flags & BGD_KEY) != 0,
                 isf = (flags & FGD_KEY) != 0;
            if ( (isb || isf) && rectState == SET )
                prLblsState = IN_PROCESS;
        }
        break;
    case CV_EVENT_LBUTTONUP:
        if( rectState == IN_PROCESS )
        {
            rect = Rect( Point(rect.x, rect.y), Point(x,y) );
            rectState = SET;
            setRectInMask();
            assert( bgdPxls.empty() && fgdPxls.empty() && prBgdPxls.empty() && prFgdPxls.empty() );
            showImage();
        }
        if( lblsState == IN_PROCESS )
        {
            setLblsInMask(flags, Point(x,y), false);
            lblsState = SET;
            showImage();
        }
        break;
    case CV_EVENT_RBUTTONUP:
        if( prLblsState == IN_PROCESS )
        {
            setLblsInMask(flags, Point(x,y), true);
            prLblsState = SET;
            showImage();
        }
        break;
    case CV_EVENT_MOUSEMOVE:
        if( rectState == IN_PROCESS )
        {
            rect = Rect( Point(rect.x, rect.y), Point(x,y) );
            assert( bgdPxls.empty() && fgdPxls.empty() && prBgdPxls.empty() && prFgdPxls.empty() );
            showImage();
        }
        else if( lblsState == IN_PROCESS )
        {
            setLblsInMask(flags, Point(x,y), false);
            showImage();
        }
        else if( prLblsState == IN_PROCESS )
        {
            setLblsInMask(flags, Point(x,y), true);
            showImage();
        }
        break;
    }
}

//真正完成grabcut的部分;
int GCApplication::nextIter()
{
	//mask设置的掩膜，标注有前景和背景;
	//如果没有手工标记GCD_BGD或者GCD_FGD，那么结果只会有GCD_PR_BGD或GCD_PR_FGD

	
    if( isInitialized )//如果已经迭代过至少一次，isInitialized ==true，则使用mask迭代;
        grabCut( *image, mask, rect, bgdModel, fgdModel, 1 );
    else
    {
        if( rectState != SET )//必须有Rect
            return iterCount;
		
        if( lblsState == SET || prLblsState == SET )//有Rect，有标注的前景和背景
            grabCut( *image, mask, rect, bgdModel, fgdModel, 1, GC_INIT_WITH_MASK );
        else//有Rect，只能利用可能的前景和背景;
            grabCut( *image, mask, rect, bgdModel, fgdModel, 1, GC_INIT_WITH_RECT );

        isInitialized = true;
    }
    iterCount++;

    bgdPxls.clear(); fgdPxls.clear();
    prBgdPxls.clear(); prFgdPxls.clear();

    return iterCount;
}

GCApplication gcapp;

void on_mouse( int event, int x, int y, int flags, void* param )
{
    gcapp.mouseClick( event, x, y, flags, param );
}

int main( int argc, char** argv )
{
// 	if( argc!=2 )
// 	{
// 		help();
// 		return 1;
// 	}
//     string filename = argv[1];
	string filename="D:/test_grabcut.jpg";
    if( filename.empty() )
    {
    	cout << "\nDurn, couldn't read in " << filename << endl;
        return 1;
    }
    Mat image0 = imread( filename, 0 );
	Mat image;
	cvtColor(image0,image,CV_GRAY2BGR);

    if( image.empty() )
    {
        cout << "\n Durn, couldn't read image filename " << filename << endl;
    	return 1;
    }

    help();

    const string winName = "image";
    cvNamedWindow( winName.c_str(), CV_WINDOW_AUTOSIZE );
    cvSetMouseCallback( winName.c_str(), on_mouse, 0 );

    gcapp.setImageAndWinName( image, winName );
    gcapp.showImage();

    for(;;)
    {
        int c = cvWaitKey(0);
        switch( (char) c )
        {
        case '\x1b':
            cout << "Exiting ..." << endl;
            goto exit_main;
        case 'r':
			cout << endl;
			gcapp.reset();
			gcapp.showImage();
            break;
        case 'n':
            int iterCount = gcapp.getIterCount();
            cout << "<" << iterCount << "... ";
            int newIterCount = gcapp.nextIter();
            if( newIterCount > iterCount )
            {
                gcapp.showImage();
                cout << iterCount << ">" << endl;
            }
            else
                cout << "rect must be determined>" << endl;
            break;
        }
    }

exit_main:
    cvDestroyWindow( winName.c_str() );
    return 0;
}