Пример #1
0
void StereoCalib(const vector<string>& imagelist, Size boardSize, bool useCalibrated=true, bool showRectified=true)
{
    if( imagelist.size() % 2 != 0 )
    {
        cout << "Error: the image list contains odd (non-even) number of elements\n";
        return;
    }
    printf("board size: %d x %d", boardSize.width, boardSize.height);
    bool displayCorners = true;
    const int maxScale = 2;
    const float squareSize = 1.f;  // Set this to your actual square size
    // ARRAY AND VECTOR STORAGE:

    vector<vector<Point2f> > imagePoints[2];
    vector<vector<Point3f> > objectPoints;
    Size imageSize;

    int i, j, k, nimages = (int)imagelist.size()/2;

    imagePoints[0].resize(nimages);
    imagePoints[1].resize(nimages);
    vector<string> goodImageList;

    for( i = j = 0; i < nimages; i++ )
    {
        for( k = 0; k < 2; k++ )
        {
            const string& filename = imagelist[i*2+k];
            Mat img = imread(filename, 0);
            if(img.empty())
                break;
            if( imageSize == Size() )
                imageSize = img.size();
            else if( img.size() != imageSize )
            {
                cout << "The image " << filename << " has the size different from the first image size. Skipping the pair\n";
                break;
            }
            bool found = false;
            vector<Point2f>& corners = imagePoints[k][j];
            for( int scale = 1; scale <= maxScale; scale++ )
            {
                Mat timg;
                if( scale == 1 )
                    timg = img;
                else
                    resize(img, timg, Size(), scale, scale);
                found = findChessboardCorners(timg, boardSize, corners,
                    CV_CALIB_CB_ADAPTIVE_THRESH | CV_CALIB_CB_NORMALIZE_IMAGE);
                if( found )
                {
                    if( scale > 1 )
                    {
                        Mat cornersMat(corners);
                        cornersMat *= 1./scale;
                    }
                    break;
                }
            }
            if( displayCorners )
            {
                cout << filename << endl;
                Mat cimg, cimg1;
                cvtColor(img, cimg, CV_GRAY2BGR);
                drawChessboardCorners(cimg, boardSize, corners, found);
                double sf = 640./MAX(img.rows, img.cols);
                resize(cimg, cimg1, Size(), sf, sf);
                imshow("corners", cimg1);
                char c = (char)waitKey(500);
                if( c == 27 || c == 'q' || c == 'Q' ) //Allow ESC to quit
                    exit(-1);
            }
            else
                putchar('.');
            if( !found )
                break;
            cornerSubPix(img, corners, Size(11,11), Size(-1,-1),
                         TermCriteria(CV_TERMCRIT_ITER+CV_TERMCRIT_EPS,
                                      30, 0.01));
        }
        if( k == 2 )
        {
            goodImageList.push_back(imagelist[i*2]);
            goodImageList.push_back(imagelist[i*2+1]);
            j++;
        }
    }
    cout << j << " pairs have been successfully detected.\n";
    nimages = j;
    if( nimages < 2 )
    {
        cout << "Error: too little pairs to run the calibration\n";
        return;
    }

    imagePoints[0].resize(nimages);
    imagePoints[1].resize(nimages);
    objectPoints.resize(nimages);

    for( i = 0; i < nimages; i++ )
    {
        for( j = 0; j < boardSize.height; j++ )
            for( k = 0; k < boardSize.width; k++ )
                objectPoints[i].push_back(Point3f(j*squareSize, k*squareSize, 0));
    }

    cout << "Running stereo calibration ...\n";

    Mat cameraMatrix[2], distCoeffs[2];
    cameraMatrix[0] = Mat::eye(3, 3, CV_64F);
    cameraMatrix[1] = Mat::eye(3, 3, CV_64F);
    Mat R, T, E, F;

    double rms = stereoCalibrate(objectPoints, imagePoints[0], imagePoints[1],
                    cameraMatrix[0], distCoeffs[0],
                    cameraMatrix[1], distCoeffs[1],
                    imageSize, R, T, E, F,
                    TermCriteria(CV_TERMCRIT_ITER+CV_TERMCRIT_EPS, 100, 1e-5),
                    CV_CALIB_FIX_ASPECT_RATIO +
                    CV_CALIB_ZERO_TANGENT_DIST +
                    //CV_CALIB_SAME_FOCAL_LENGTH +
                    CV_CALIB_RATIONAL_MODEL +
                    CV_CALIB_FIX_K3 + CV_CALIB_FIX_K4 + CV_CALIB_FIX_K5);
    cout << "done with RMS error=" << rms << endl;

// CALIBRATION QUALITY CHECK
// because the output fundamental matrix implicitly
// includes all the output information,
// we can check the quality of calibration using the
// epipolar geometry constraint: m2^t*F*m1=0
    double err = 0;
    int npoints = 0;
    vector<Vec3f> lines[2];
    for( i = 0; i < nimages; i++ )
    {
        int npt = (int)imagePoints[0][i].size();
        Mat imgpt[2];
        for( k = 0; k < 2; k++ )
        {
            imgpt[k] = Mat(imagePoints[k][i]);
            undistortPoints(imgpt[k], imgpt[k], cameraMatrix[k], distCoeffs[k], Mat(), cameraMatrix[k]);
            computeCorrespondEpilines(imgpt[k], k+1, F, lines[k]);
        }
        for( j = 0; j < npt; j++ )
        {
            double errij = fabs(imagePoints[0][i][j].x*lines[1][j][0] +
                                imagePoints[0][i][j].y*lines[1][j][1] + lines[1][j][2]) +
                           fabs(imagePoints[1][i][j].x*lines[0][j][0] +
                                imagePoints[1][i][j].y*lines[0][j][1] + lines[0][j][2]);
            err += errij;
        }
        npoints += npt;
    }
    cout << "average reprojection err = " <<  err/npoints << endl;

    // save intrinsic parameters
    FileStorage fs("calib/intrinsics.yml", CV_STORAGE_WRITE);
    if( fs.isOpened() )
    {
        fs << "M1" << cameraMatrix[0] << "D1" << distCoeffs[0] <<
            "M2" << cameraMatrix[1] << "D2" << distCoeffs[1];
        fs.release();
    }
    else
        cout << "Error: can not save the intrinsic parameters\n";

    Mat R1, R2, P1, P2, Q;
    Rect validRoi[2];

    stereoRectify(cameraMatrix[0], distCoeffs[0],
                  cameraMatrix[1], distCoeffs[1],
                  imageSize, R, T, R1, R2, P1, P2, Q,
                  CALIB_ZERO_DISPARITY, 1, imageSize, &validRoi[0], &validRoi[1]);

    fs.open("calib/extrinsics.yml", CV_STORAGE_WRITE);
    if( fs.isOpened() )
    {
        fs << "R" << R << "T" << T << "R1" << R1 << "R2" << R2 << "P1" << P1 << "P2" << P2 << "Q" << Q;
        fs.release();
    }
    else
        cout << "Error: can not save the intrinsic parameters\n";

    // OpenCV can handle left-right
    // or up-down camera arrangements
    bool isVerticalStereo = fabs(P2.at<double>(1, 3)) > fabs(P2.at<double>(0, 3));

// COMPUTE AND DISPLAY RECTIFICATION
    if( !showRectified )
        return;

    Mat rmap[2][2];
// IF BY CALIBRATED (BOUGUET'S METHOD)
    if( useCalibrated )
    {
        // we already computed everything
    }
// OR ELSE HARTLEY'S METHOD
    else
 // use intrinsic parameters of each camera, but
 // compute the rectification transformation directly
 // from the fundamental matrix
    {
        vector<Point2f> allimgpt[2];
        for( k = 0; k < 2; k++ )
        {
            for( i = 0; i < nimages; i++ )
                std::copy(imagePoints[k][i].begin(), imagePoints[k][i].end(), back_inserter(allimgpt[k]));
        }
        F = findFundamentalMat(Mat(allimgpt[0]), Mat(allimgpt[1]), FM_8POINT, 0, 0);
        Mat H1, H2;
        stereoRectifyUncalibrated(Mat(allimgpt[0]), Mat(allimgpt[1]), F, imageSize, H1, H2, 3);

        R1 = cameraMatrix[0].inv()*H1*cameraMatrix[0];
        R2 = cameraMatrix[1].inv()*H2*cameraMatrix[1];
        P1 = cameraMatrix[0];
        P2 = cameraMatrix[1];
    }

    //Precompute maps for cv::remap()
    initUndistortRectifyMap(cameraMatrix[0], distCoeffs[0], R1, P1, imageSize, CV_16SC2, rmap[0][0], rmap[0][1]);
    initUndistortRectifyMap(cameraMatrix[1], distCoeffs[1], R2, P2, imageSize, CV_16SC2, rmap[1][0], rmap[1][1]);

    Mat canvas;
    double sf;
    int w, h;
    if( !isVerticalStereo )
    {
        sf = 600./MAX(imageSize.width, imageSize.height);
        w = cvRound(imageSize.width*sf);
        h = cvRound(imageSize.height*sf);
        canvas.create(h, w*2, CV_8UC3);
    }
    else
    {
        sf = 300./MAX(imageSize.width, imageSize.height);
        w = cvRound(imageSize.width*sf);
        h = cvRound(imageSize.height*sf);
        canvas.create(h*2, w, CV_8UC3);
    }

    for( i = 0; i < nimages; i++ )
    {
        for( k = 0; k < 2; k++ )
        {
            Mat img = imread(goodImageList[i*2+k], 0), rimg, cimg;
            remap(img, rimg, rmap[k][0], rmap[k][1], CV_INTER_LINEAR);
            cvtColor(rimg, cimg, CV_GRAY2BGR);
            Mat canvasPart = !isVerticalStereo ? canvas(Rect(w*k, 0, w, h)) : canvas(Rect(0, h*k, w, h));
            resize(cimg, canvasPart, canvasPart.size(), 0, 0, CV_INTER_AREA);
            if( useCalibrated )
            {
                Rect vroi(cvRound(validRoi[k].x*sf), cvRound(validRoi[k].y*sf),
                          cvRound(validRoi[k].width*sf), cvRound(validRoi[k].height*sf));
                rectangle(canvasPart, vroi, Scalar(0,0,255), 3, 8);
            }
        }

        if( !isVerticalStereo )
            for( j = 0; j < canvas.rows; j += 16 )
                line(canvas, Point(0, j), Point(canvas.cols, j), Scalar(0, 255, 0), 1, 8);
        else
            for( j = 0; j < canvas.cols; j += 16 )
                line(canvas, Point(j, 0), Point(j, canvas.rows), Scalar(0, 255, 0), 1, 8);
        imshow("rectified", canvas);
        char c = (char)waitKey();
        if( c == 27 || c == 'q' || c == 'Q' )
            break;
    }
}
KDvoid CornerSubPix ( KDint nIdx )
{
	string	sMsg;
	KDchar	szStr [ 256 ];

	Mat		tSrc;
	Mat		tDst;
	Mat		tGray;
	KDint	nThresh;
	RNG		tRng ( 12345 );

	nThresh = 205;

	// Load source image and convert it to gray
	tSrc = imread ( "/res/image/apple.png" );
	cvtColor ( tSrc, tGray, CV_BGR2GRAY );

	//
	// Apply Shi-Tomasi corner detector
	//
	// Parameters for Shi-Tomasi algorithm
	vector<Point2f>		aCorners;

	KDdouble	dQualityLevel		= 0.01;
	KDdouble	dMinDistance		= 10;
	KDint		nMaxCorners			= 4;
	KDint		nBlockSize			= 3;
	bool		bUseHarrisDetector	= false;
	KDdouble	dK					= 0.04;

	// Copy the source image
	tDst = tSrc.clone ( );

	// Apply corner detection
	goodFeaturesToTrack ( tGray, aCorners, nMaxCorners, dQualityLevel, dMinDistance, Mat ( ), nBlockSize, bUseHarrisDetector, dK ); 

	// Draw corners detected
	kdSprintfKHR ( szStr, "** Number of corners detected: %d\n", aCorners.size ( ) );
	sMsg = szStr;

	KDint		nR = 4;
	for ( KDuint i = 0; i < aCorners.size ( ); i++ )
	{
		circle ( tDst, aCorners [ i ], nR, Scalar ( tRng.uniform ( 0, 255 ), tRng.uniform ( 0, 255 ), tRng.uniform ( 0, 255 ) ), -1, 8, 0 );
	}

	// Set the neeed parameters to find the refined corners
	Size		tWinSize  = Size ( 5, 5 );
	Size		tZeroZone = Size ( -1, -1 );

	TermCriteria  tCriteria = TermCriteria ( CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 40, 0.001 );

	// Calculate the refined corner locations
	cornerSubPix ( tGray, aCorners, tWinSize, tZeroZone, tCriteria );

	// Write them down
	for ( KDuint i = 0; i < aCorners.size ( ); i++ )
	{
		kdSprintfKHR ( szStr, " -- Refined Corner [%d] ( %.3f, %.3f )\n", i, aCorners [ i ].x, aCorners [ i ].y );
		sMsg += szStr;
	}	

	g_pController->setFrame ( 1, tSrc );
	g_pController->setFrame ( 2, tDst );
	g_pController->setMessage ( sMsg.c_str ( ) );
}
Пример #3
0
/**
 * Find a list of candidate marker from a given scene
 *
 * @param current frame, in grayscale 8UC1 format
 * @return a list of marker candidates
 **/
vector<Marker> MarkerDetector::findMarkerCandidates( Mat& frame ) {
    vector<Marker> candidates;
    
    /* Do some thresholding, in fact you should tune the parameters here a bit */
    Mat thresholded;
    threshold( frame, thresholded, 50.0, 255.0, CV_THRESH_BINARY );
    
    /* Find contours */
    vector<vector<Point>> contours;
    findContours( thresholded.clone(), contours, CV_RETR_LIST, CV_CHAIN_APPROX_NONE );
    
    for( vector<Point> contour: contours ) {
        /* Approximate polygons out of these contours */
        vector<Point> approxed;
        approxPolyDP( contour, approxed, contour.size() * 0.05, true );
        
        /* Make sure it passes our first candidate check */
        if( !checkPoints( approxed ) )
            continue;
        
        /* Do some perspective transformation on the candidate marker to a predetermined square */
        Marker marker;
        marker.matrix = Mat( markerHeight, markerWidth, CV_8UC1 );
        std::copy( approxed.begin(), approxed.end(), back_inserter( marker.poly ) );
        
        /* Apply sub pixel search */
        cornerSubPix( thresholded, marker.poly, Size(5, 5), Size(-1, -1), TermCriteria(CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 40, 0.001) );
        
        /* Projection target */
        const static vector<Point2f> target_corners = {
            Point2f( -0.5f, -0.5f ),
            Point2f( +5.5f, -0.5f ),
            Point2f( +5.5f, +5.5f ),
            Point2f( -0.5f, +5.5f ),
        };
        
        /* Apply perspective transformation, to project our 3D marker to a predefined 2D coords */
        Mat projection = getPerspectiveTransform( marker.poly, target_corners );
        warpPerspective( thresholded, marker.matrix, projection, marker.matrix.size() );
        
        /* Ignore those region that's fully black, or not surrounded by black bars */
        if( sum(marker.matrix) == Scalar(0) ||
           countNonZero( marker.matrix.row(0)) != 0 ||
           countNonZero( marker.matrix.row(markerHeight - 1)) != 0 ||
           countNonZero( marker.matrix.col(0)) != 0 ||
           countNonZero( marker.matrix.col(markerWidth - 1)) != 0 ) {
            continue;
        }
        
        
        /* Find the rotation that has the smallest hex value */
        pair<unsigned int, unsigned int> minimum = { numeric_limits<unsigned int>::max(), 0 };
        vector<unsigned int> codes(markerHeight);
        unsigned int power = 1 << (markerWidth - 3);
        
        /* Rotate the marker 4 times, store the hex code upon each rotation */
        for( int rotation = 0; rotation < 4; rotation++ ) {
            stringstream ss;
            codes[rotation] = 0;
            
            for( int i = 1; i < markerHeight - 1; i++ ) {
                unsigned int code = 0;
                for ( int j = 1; j < markerWidth - 1; j++ ){
                    int value = static_cast<int>(marker.matrix.at<uchar>(i, j));
                    if( value == 0 )
                        code = code + ( power >> j );
                }
                
                ss << hex << code;
            }
            ss >> codes[rotation];
            
            if( minimum.first > codes[rotation] ) {
                minimum.first  = codes[rotation];
                minimum.second = rotation;
            }
            
            flip( marker.matrix, marker.matrix, 1 );
            marker.matrix = marker.matrix.t();
        }
        
        
        rotate( marker.poly.begin(), marker.poly.begin() + ((minimum.second + 2) % 4), marker.poly.end() );
        for( int i = 0; i < minimum.second; i++ ) {
            flip( marker.matrix, marker.matrix, 1 );
            marker.matrix = marker.matrix.t();
        }
        
        marker.code = minimum.first;
        
        candidates.push_back( marker );
    }
    
    return candidates;
}
Пример #4
0
AppTemplate::AppTemplate(const Mat* frame_set, const Rect iniWin,int ID)
	:ID(ID)//bgr,hsv,lab
{	
	//get roi out of frame set
	Rect body_win=scaleWin(iniWin,1/TRACKING_TO_BODYSIZE_RATIO);
	Rect roi_win(body_win.x-body_win.width,body_win.y-body_win.width,3*body_win.width,2*body_win.width+body_win.height);
	body_win= body_win&Rect(0,0,frame_set[0].cols,frame_set[0].rows);
	roi_win=roi_win&Rect(0,0,frame_set[0].cols,frame_set[0].rows);
	Mat roi_set[]={Mat(frame_set[0],roi_win),Mat(frame_set[1],roi_win),Mat(frame_set[2],roi_win)};

	
	Rect iniWin_roi=iniWin-Point(roi_win.x,roi_win.y);

	//scores for each channel
	list<ChannelScore> channel_score;
	
	Mat mask_roi(roi_set[0].rows,roi_set[0].cols,CV_8UC1,Scalar(0));
	rectangle(mask_roi,iniWin_roi,Scalar(255),-1);
	Mat inv_mask_roi(roi_set[0].rows,roi_set[0].cols,CV_8UC1,Scalar(255));
	rectangle(inv_mask_roi,body_win-Point(roi_win.x,roi_win.y),Scalar(0),-1);

	//calculate score for each channel
	Mat temp_hist;
	Mat temp_bp;
	int hist_size[]={BIN_NUMBER};
	for (int i=0;i<9;i++)
	{
		float range1[]={0,255};
		if (i==3)
		{
			range1[1]=179;
		}
		const float* hist_range[]={range1};
		
		calcHist(roi_set,3,&i,inv_mask_roi,temp_hist,1,hist_size,hist_range);
		normalize(temp_hist,temp_hist,255,0.0,NORM_L1);//scale to 255 for display

		calcBackProject(roi_set,3,&i,temp_hist,temp_bp,hist_range);
		int c[]={0};
		int hs[]={BIN_NUMBER};
		float hr[]={0,255};
		const float* hrr[]={hr};
		Mat hist_fore;
		Mat hist_back;
		calcHist(&temp_bp,1,c,mask_roi,hist_fore,1,hs,hrr);
		calcHist(&temp_bp,1,c,inv_mask_roi,hist_back,1,hs,hrr);
		normalize(hist_fore,hist_fore,1.0,0.0,NORM_L1);
		normalize(hist_back,hist_back,1.0,0.0,NORM_L1);
		//deal with gray image to get rid of #IND
		double score=getVR(hist_back,hist_fore);
		score=score==score ? score:0;
		channel_score.push_back(ChannelScore(i,score));
	}

	//choose the 2 highest scored channels
	channel_score.sort(compareChannel);
	channels[0]=channel_score.back().idx;
	channel_score.pop_back();
	channels[1]=channel_score.back().idx;
	
	//using 2 best channel to calculate histogram
	for (int i=0;i<2;++i)
	{
		_hRang[i][0]=0;
		if (channels[i]==3)
			_hRang[i][1]=179;	
		else
			_hRang[i][1]=255;	
		hRange[i]=_hRang[i];
	}
	calcHist(roi_set,3,channels,inv_mask_roi,temp_hist,2,hSize,hRange);
	normalize(temp_hist,temp_hist,255,0,NORM_L1);
	Mat final_mask;//mask for sampling
	calcBackProject(roi_set,3,channels,temp_hist,final_mask,hRange);
	threshold(final_mask,final_mask,5,255,CV_THRESH_BINARY_INV);
	          
	final_mask=min(final_mask,mask_roi);

	//choose the best two feature space for foreground****************
	Mat hist_fore,hist_back;
	channel_score.clear();
	double sum_score=0;
	for (int i=0;i<9;i++)
	{
		float range1[]={0,255};
		if (i==3)
		{
			range1[1]=179;
		}
		const float* hist_range[]={range1};
		Mat temp_hist_neg;
		calcHist(roi_set,3,&i,final_mask,temp_hist,1,hist_size,hist_range);
		normalize(temp_hist,temp_hist,255,0,NORM_L1);
		calcHist(roi_set,3,&i,inv_mask_roi,temp_hist_neg,1,hist_size,hist_range);
		normalize(temp_hist_neg,temp_hist_neg,255,0,NORM_L1);
		log(temp_hist,temp_hist);		
		log(temp_hist_neg,temp_hist_neg);
		temp_hist=temp_hist-temp_hist_neg;
		threshold(temp_hist,temp_hist,0,255,CV_THRESH_TOZERO);
		normalize(temp_hist,temp_hist,255,0.0,NORM_L1);//scale to 255 for display

		calcBackProject(roi_set,3,&i,temp_hist,temp_bp,hist_range);
		int c[]={0};
		int hs[]={BIN_NUMBER};
		float hr[]={0,255};
		const float* hrr[]={hr};
		calcHist(&temp_bp,1,c,final_mask,hist_fore,1,hs,hrr);
		calcHist(&temp_bp,1,c,inv_mask_roi,hist_back,1,hs,hrr);
		normalize(hist_fore,hist_fore,1.0,0.0,NORM_L1);
		normalize(hist_back,hist_back,1.0,0.0,NORM_L1);
		double score=getVR(hist_back,hist_fore);
		score=score==score ? score:0;
		channel_score.push_back(ChannelScore(i,score));
		sum_score+=exp(score);
	}


	channel_score.sort(compareChannel);
	channels[0]=channel_score.back().idx;
	channel_score.pop_back();
	channels[1]=channel_score.back().idx;

	for (int i=0;i<2;++i)
	{
		_hRang[i][0]=0;
		if (channels[i]==3)
			_hRang[i][1]=179;	
		else
			_hRang[i][1]=255;	
		hRange[i]=_hRang[i];
	}
	calcHist(roi_set,3,channels,final_mask,hist,2,hSize,hRange);///////////////////
	normalize(hist,hist,255,0,NORM_L1);

	//recover the shift_vector
	Mat backPro;
	calcBackProject(roi_set,3,channels,hist,backPro,hRange);
	iniWin_roi=iniWin-Point(roi_win.x,roi_win.y);
	Point2f origin_point_roi((float)(iniWin_roi.x+0.5*iniWin_roi.width),(float)(iniWin_roi.y+0.5*iniWin_roi.height));
	meanShift(backPro,iniWin_roi,TermCriteria( CV_TERMCRIT_EPS | CV_TERMCRIT_ITER, 10, 1 ));

	Point2f shift_point_roi((float)(iniWin_roi.x+0.5*iniWin_roi.width),(float)(iniWin_roi.y+0.5*iniWin_roi.height));
	shift_vector=(shift_point_roi-origin_point_roi)*(1/(float)iniWin.width);
}
Пример #5
0
Mat TableObjectDetector::clusterObjects(Mat P, int K, bool removeOutliers) {
    Mat L;
    int attempts = 5;
    P.convertTo(P, CV_32F);
    kmeans(P, K, L, TermCriteria(CV_TERMCRIT_ITER|CV_TERMCRIT_EPS, 10000, 0.0001), attempts, KMEANS_PP_CENTERS);

    // We remove outliers that are outside a number of standard deviations away
    // from the object centroid. We do this by just setting their cluster label
    // to -1
    
    if (removeOutliers) {
        float numStdDevs = 3;
        float maxDist = 0.1;

        // Caluclate centroids
        vector<Mat> clusterData;
        Mat clusterCentroids(K, 3, CV_32F);
        for (int k=0; k<K; k++) {
            Mat D = Mat(0, 3, CV_64F);
            for (int i=0; i<L.rows; i++) {
                if (L.at<int>(i)==k) {
                    D.push_back(P.row(i));
                }
            }
            clusterData.push_back(D);
            reduce(D, clusterCentroids.row(k), 0, CV_REDUCE_AVG);
        }


        // Now calculate distances of each point, and the std. devs. of each
        // cluster
        Mat Dist = Mat::zeros(P.rows, 1, CV_32F);
        vector<Mat> centroidDistances;
        for (int k=0; k<K; k++) {
            centroidDistances.push_back(Mat(0, 1, CV_32F));
        }
        for (int i=0; i<L.rows; i++) {
            Mat centroid = clusterCentroids.row(L.at<int>(i));
            Mat pt = P.row(i);
            int k = L.at<int>(i);
            float d = std::sqrt(
                    std::pow(pt.at<float>(0) - centroid.at<float>(0), 2) + 
                    std::pow(pt.at<float>(1) - centroid.at<float>(1), 2) + 
                    std::pow(pt.at<float>(2) - centroid.at<float>(2), 2) );

            Dist.at<float>(i) = d;
            centroidDistances.at(k).push_back(d);
        }
        for (int k=0; k<K; k++) {
            Mat ignore;
            Mat std_dev;
            meanStdDev(centroidDistances.at(k), ignore, std_dev);
            float k_std = std_dev.at<Scalar>(0)(0);

            for (int i=0; i<P.rows; i++) {
                if (L.at<int>(i) == k) {
                    //if (Dist.at<float>(i) > numStdDevs*k_std) {
                    if (Dist.at<float>(i) > maxDist) {
                        L.at<int>(i) = -1;
                    }
                }
            }
        }

        // Now compute standard deviations for all clusters
        //Mat centroidStdDevs = Mat::zeros(K, 1);
        //for (int k=0; k<K; k++) {

        //}
    }
    
    return L;
}
Пример #6
0
/**
 * Run hierarchical k-means with a distance threshold of 0.15 meters
 */
Mat TableObjectDetector::clusterObjectsHierarchical(cv::Mat P, int max_clusters) {
    Mat L = Mat::zeros	(P.rows, 1, CV_32S);
    double dthresh = 0.15;
    int currentClusterNum = 0;
    int num_iter = 30;
    std::stack<Cluster*> c_stack;
    
    // Initialize with a single cluster containing all datapoints
    Cluster* C = new Cluster();
    Mat D = Mat(P.rows, 4, CV_64F);
    P.copyTo(D.colRange(0, 3));
    // ID each point so we return them in the same order
    for (int i=0; i<D.rows; i++) {
        D.at<double>(i, 3) = i;
    }
    C->setData(D);
    c_stack.push(C);
        
    
    // Run hierarchical k-means
    for (int t=0; t<num_iter; t++) {
        if (currentClusterNum == max_clusters) {
            return L;
        }

        if (c_stack.empty()) {
            return L;
        }
        
        Cluster* C = (Cluster*)c_stack.top();
        c_stack.pop();
        Mat D = C->getData();
        // Calculate cluster centroid
        Mat Cmean; reduce(D, Cmean, 0, CV_REDUCE_AVG);
        // Calculate max distance
        double maxDist = 0;
        for (int i=0; i<D.rows; i++) {
            double dx = D.at<double>(i, 0) - Cmean.at<double>(0);
            double dy = D.at<double>(i, 1) - Cmean.at<double>(1);
            double dz = D.at<double>(i, 2) - Cmean.at<double>(2);
            double dist = sqrt(dx*dx + dy*dy + dz*dz);
            
            if (dist > maxDist) {
                maxDist = dist;
            }
        }
        
        // Check to see if this cluster satisfies the conditions
        if (maxDist < dthresh) {
            for (int i=0; i<D.rows; i++) {
                int idx = (int)D.at<double>(i, 3);
                L.at<int>(idx) = currentClusterNum;
            }
            currentClusterNum++;
        } else {

            Mat L_iter;
            int attempts = 5;
            Mat D32 = Mat(D.rows, 3, CV_64F);
            D.colRange(0, 3).copyTo(D32);
            D32.convertTo(D32, CV_32F);
            kmeans(D32, 2, L_iter, TermCriteria(CV_TERMCRIT_ITER|CV_TERMCRIT_EPS, 10000, 0.0001), attempts, KMEANS_PP_CENTERS);
            
            Mat D0 = Mat(0, 3, CV_64F);
            Mat D1 = Mat(0, 3, CV_64F);

            for (int i=0; i<L_iter.rows; i++) {
                if (L_iter.at<int>(i) == 0) {
                    D0.push_back(D.row(i));
                } else {
                    D1.push_back(D.row(i));
                }
            }
            
            Cluster* C0 = new Cluster();
            C0->setData(D0);
            Cluster* C1 = new Cluster();
            C1->setData(D1);
            
            c_stack.push(C0);
            c_stack.push(C1);

        }
        
    }
    
    return L;
}
Пример #7
0
 * \f$R_i, T_i\f$ are concatenated 1x3 vectors.
 * @param perViewErrors Output vector of average re-projection errors estimated for each pattern view.
 * @param flags flags Different flags  for the calibration process (see #calibrateCamera for details).
 * @param criteria Termination criteria for the iterative optimization algorithm.
 *
 * This function calibrates a camera using a set of corners of a  Charuco Board. The function
 * receives a list of detected corners and its identifiers from several views of the Board.
 * The function returns the final re-projection error.
 */
CV_EXPORTS_AS(calibrateCameraCharucoExtended) double calibrateCameraCharuco(
    InputArrayOfArrays charucoCorners, InputArrayOfArrays charucoIds, const Ptr<CharucoBoard> &board,
    Size imageSize, InputOutputArray cameraMatrix, InputOutputArray distCoeffs,
    OutputArrayOfArrays rvecs, OutputArrayOfArrays tvecs,
    OutputArray stdDeviationsIntrinsics, OutputArray stdDeviationsExtrinsics,
    OutputArray perViewErrors, int flags = 0,
    TermCriteria criteria = TermCriteria(TermCriteria::COUNT + TermCriteria::EPS, 30, DBL_EPSILON));

/** @brief It's the same function as #calibrateCameraCharuco but without calibration error estimation.
*/
CV_EXPORTS_W double calibrateCameraCharuco(
  InputArrayOfArrays charucoCorners, InputArrayOfArrays charucoIds, const Ptr<CharucoBoard> &board,
  Size imageSize, InputOutputArray cameraMatrix, InputOutputArray distCoeffs,
  OutputArrayOfArrays rvecs = noArray(), OutputArrayOfArrays tvecs = noArray(), int flags = 0,
  TermCriteria criteria = TermCriteria(TermCriteria::COUNT + TermCriteria::EPS, 30, DBL_EPSILON));



/**
 * @brief Detect ChArUco Diamond markers
 *
 * @param image input image necessary for corner subpixel.
Пример #8
0
///////////////////////////////////////////////////////
// Panel::CalibrateCamera() Description
///////////////////////////////////////////////////////
void Panel::CalibrateCamera(string sFilePath)
{
	help();

	//! [file_read]
	Settings s;
	const string inputSettingsFile = sFilePath;
	FileStorage fs(inputSettingsFile, FileStorage::READ); // Read the settings
	if (!fs.isOpened())
	{
		cout << "Could not open the configuration file: \"" << inputSettingsFile << "\"" << endl;
//		return -1;
	}
	fs["Settings"] >> s;
	fs.release();                                         // close Settings file
	//! [file_read]

	//FileStorage fout("settings.yml", FileStorage::WRITE); // write config as YAML
	//fout << "Settings" << s;

	if (!s.goodInput)
	{
		cout << "Invalid input detected. Application stopping. " << endl;
//		return -1;
	}

	vector<vector<Point2f> > imagePoints;
	Mat cameraMatrix, distCoeffs;
	Size imageSize;
	int mode = s.inputType == Settings::IMAGE_LIST ? CAPTURING : DETECTION;
	clock_t prevTimestamp = 0;
	const Scalar RED(0, 0, 255), GREEN(0, 255, 0);
	const char ESC_KEY = 27;
	int counter = 1;

	//! [get_input]
	for (;;)
	{
		Mat view;
		bool blinkOutput = false;

		view = s.nextImage();

		//-----  If no more image, or got enough, then stop calibration and show result -------------
		if (mode == CAPTURING && imagePoints.size() >= (size_t)s.nrFrames)
		{
			if (runCalibrationAndSave(s, imageSize, cameraMatrix, distCoeffs, imagePoints))
				mode = CALIBRATED;
			else
				mode = DETECTION;
		}
		if (view.empty())          // If there are no more images stop the loop
		{
			// if calibration threshold was not reached yet, calibrate now
			if (mode != CALIBRATED && !imagePoints.empty())
				runCalibrationAndSave(s, imageSize, cameraMatrix, distCoeffs, imagePoints);
			break;
		}
		//! [get_input]

		imageSize = view.size();  // Format input image.
		if (s.flipVertical)    flip(view, view, 0);

		//! [find_pattern]
		vector<Point2f> pointBuf;

		bool found;
		switch (s.calibrationPattern) // Find feature points on the input format
		{
		case Settings::CHESSBOARD:
			found = findChessboardCorners(view, s.boardSize, pointBuf,
				CALIB_CB_ADAPTIVE_THRESH | CALIB_CB_FAST_CHECK | CALIB_CB_NORMALIZE_IMAGE);
			break;
		case Settings::CIRCLES_GRID:
			found = findCirclesGrid(view, s.boardSize, pointBuf);
			break;
		case Settings::ASYMMETRIC_CIRCLES_GRID:
			found = findCirclesGrid(view, s.boardSize, pointBuf, CALIB_CB_ASYMMETRIC_GRID);
			break;
		default:
			found = false;
			break;
		}
		//! [find_pattern]
		//! [pattern_found]
		if (found)                // If done with success,
		{
			// improve the found corners' coordinate accuracy for chessboard
			if (s.calibrationPattern == Settings::CHESSBOARD)
			{
				Mat viewGray;
				cvtColor(view, viewGray, COLOR_BGR2GRAY);
				cornerSubPix(viewGray, pointBuf, Size(11, 11),
					Size(-1, -1), TermCriteria(TermCriteria::EPS + TermCriteria::COUNT, 30, 0.1));
			}

			if (mode == CAPTURING &&  // For camera only take new samples after delay time
				(!s.inputCapture.isOpened() || clock() - prevTimestamp > s.delay*1e-3*CLOCKS_PER_SEC))
			{
				imagePoints.push_back(pointBuf);
				prevTimestamp = clock();
				blinkOutput = s.inputCapture.isOpened();
			}

			// Draw the corners.
			drawChessboardCorners(view, s.boardSize, Mat(pointBuf), found);
		}
		//! [pattern_found]
		//----------------------------- Output Text ------------------------------------------------
		//! [output_text]
		string msg = (mode == CAPTURING) ? "100/100" :
			mode == CALIBRATED ? "Calibrated" : "Press 'g' to start";
		int baseLine = 0;
		Size textSize = getTextSize(msg, 1, 1, 1, &baseLine);
		Point textOrigin(view.cols - 2 * textSize.width - 10, view.rows - 2 * baseLine - 10);

		if (mode == CAPTURING)
		{
			if (s.showUndistorsed)
				msg = format("%d/%d Undist", (int)imagePoints.size(), s.nrFrames);
			else
				msg = format("%d/%d", (int)imagePoints.size(), s.nrFrames);
		}

		putText(view, msg, textOrigin, 1, 1, mode == CALIBRATED ? GREEN : RED);

		if (blinkOutput)
			bitwise_not(view, view);
		//! [output_text]
		//------------------------- Video capture  output  undistorted ------------------------------
		//! [output_undistorted]
		if (mode == CALIBRATED && s.showUndistorsed)
		{
			Mat temp = view.clone();
			undistort(temp, view, cameraMatrix, distCoeffs);
		}
		//! [output_undistorted]
		//------------------------------ Show image and check for input commands -------------------
		//! [await_input]
		
		namedWindow("Image View" + to_string(counter), WINDOW_NORMAL);
		resizeWindow("Image View" + to_string(counter), 640, 480);
		imshow("Image View" + to_string(counter), view);
		char key = (char)waitKey(s.inputCapture.isOpened() ? 50 : s.delay);

		cout << "Image " << to_string(counter) << " Completed" << endl;
		counter++;

		if (key == ESC_KEY)
			break;

		if (key == 'u' && mode == CALIBRATED)
			s.showUndistorsed = !s.showUndistorsed;

		if (s.inputCapture.isOpened() && key == 'g')
		{
			mode = CAPTURING;
			imagePoints.clear();
		}
		//! [await_input]
	}

	// -----------------------Show the undistorted image for the image list ------------------------
	//! [show_results]
	if (s.inputType == Settings::IMAGE_LIST && s.showUndistorsed)
	{
		Mat view, rview, map1, map2;
		initUndistortRectifyMap(cameraMatrix, distCoeffs, Mat(),
			getOptimalNewCameraMatrix(cameraMatrix, distCoeffs, imageSize, 1, imageSize, 0),
			imageSize, CV_16SC2, map1, map2);

		m_mainMap1 = map1;
		m_mainMap2 = map2;

		for (size_t i = 0; i < s.imageList.size(); i++)
		{
			view = imread(s.imageList[i], 1);
			if (view.empty())
				continue;
			remap(view, rview, map1, map2, INTER_LINEAR);
			imshow("Image View", rview);
			char c = (char)waitKey();
			if (c == ESC_KEY || c == 'q' || c == 'Q')
				break;
		}
	}
	//! [show_results]

//	return 0;

}
Пример #9
0
 EMImpl()
 {
     nclusters = DEFAULT_NCLUSTERS;
     covMatType=EM::COV_MAT_DIAGONAL;
     termCrit = TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, EM::DEFAULT_MAX_ITERS, 1e-6);
 }
Пример #10
0
int main(int argc, char** argv)
{
    ofstream f1;
    f1.open("result.txt");
    size_t i,j;
    Point2f cp;
    cv::initModule_nonfree();
    vector<Point2f> MP1,MP2;
    vector<int> trainIdxs, queryIdxs;

    //Read Video File
    VideoCapture cap("video1.avi");
    if( !cap.isOpened() )
    { cout << "Could not initialize capturing...\n"; return 0;}



    VideoWriter writer("ms_tracking.avi",CV_FOURCC('D','I','V','3'),
                 10,cvSize(640,480),1);

    cv::SURF mySURF;    mySURF.extended = 0;
    Ptr<DescriptorMatcher> descriptorMatcher = DescriptorMatcher::create( "FlannBased" );
    int mactherFilterType = getMatcherFilterType( "CrossCheckFilter" );

    Mat frame,img1,img2;
    cap >> frame;
    if( frame.empty() )
        return -1;
    img1 = frame.clone() ;
    Mat temp,temp1;

    if(img1.empty())
        cout << "Exiting as the input image is empty" << endl;


    const char* name = "Initiate_ROI";
    box = cvRect(-1,-1,0,0);
    cvNamedWindow( name,1);
    cvSetMouseCallback( name, my_mouse_callback2);

    // Main loop
    while( 1 )
    {
        img1.copyTo(temp);

        if( drawing_poly)
        {

            for ( i=0; i < polyPoints.size(); i++)
                circle(temp, polyPoints[i], 2, Scalar(0,255,0), -1,8);
        }
        cv::imshow(name,temp) ;
        char c = (char)waitKey(10);
        if( c == '\x1b' ) // esc
            break;
        if(poly_drawn)
            break;
    }

    //Read the polygon points from a text file

    FILE *f11;
    polyPoints.clear();
    IpolyPoints.clear();
    f11 = fopen("points.txt","r");
    Point a;
    for(int j=0;j<37;j++)
    {
        fscanf(f11,"%d",&(a.x));
        fscanf(f11,"%d",&(a.y));
        polyPoints.push_back(a);
        IpolyPoints.push_back(a);
    }
    fclose(f11);

    // Drawing Polygon
    Point pointArr[polyPoints.size()];
    for (i=0; i< polyPoints.size(); i++)
        pointArr[i] = polyPoints[i];
    const Point* pointsArray[1] = {pointArr};
    int nCurvePts[1] = { polyPoints.size() };
    polylines(temp, pointsArray, nCurvePts, 1, 1, Scalar(0,255,0), 1);

    cout << polyPoints.size() << endl;
    box= boundingRect(polyPoints);

   //boxOrg = Rect(box.x-15, box.y-15, box.width+30, box.height+30);
   boxOuter = Rect(box.x-30, box.y-30, box.width+60, box.height+60);
    //box =boxOrg; // storing the initial selected Box, as "box" variable changes in consecutive matching
    boxP=box;
    Mat img1ROI, labels1, clusters1, descriptors,roidescriptors, descriptors1,bdescriptors, bmdescriptors;
    vector<int> reprojections; // number of reprojections per KP, size same as KP(incresing)
    vector<Point2f> points,points1,points2, Mpoints1,Mpoints2,bpoints,npoints1,npoints2; //bmpoints,tpoints;
    vector<KeyPoint> roikeypoints, bkeypoints,keypoints,keypoints1, keypoints2;


    draw_box(temp, box ); //Show InnerBox  - This is used by the Mean-Shift Tracker
    draw_box(temp,boxOuter); //Show OuterBox - This is used for removing background points
    bpoints.clear();

    //calculating keypoints and descriptors of the selected polygon in image roi
    //==============================================================================================//
    for(i=0;i<polyPoints.size();i++)
    {
        // cout << polyPoints[i] << endl; //
        polyPoints[i].x = polyPoints[i].x -boxOuter.x;
        polyPoints[i].y = polyPoints[i].y- boxOuter.y;
    }

    img1ROI = img1(boxOuter);
    points1.clear();
    mySURF.detect(img1ROI, roikeypoints);
    KeyPoint::convert(roikeypoints, points);
    mySURF.compute(img1ROI, roikeypoints, roidescriptors);

    bdescriptors.release();bkeypoints.clear();
    bcategorizePoints( points, bpoints,polyPoints, roikeypoints, roidescriptors, bkeypoints, bdescriptors);
    shiftPoints(bpoints,boxOuter);
    for(i=0;i<bpoints.size();i++)
        circle(temp, bpoints[i], 2, Scalar(0,255,0),2);

  vector<KeyPoint> tpkeypoints;    Mat tpdescriptors;
    categorizePoints( points, points1,polyPoints, roikeypoints, roidescriptors, tpkeypoints, tpdescriptors);

    shiftPoints(points1, boxOuter);
    for(i=0;i<points1.size();i++)
        circle(temp, points1[i], 2, Scalar(0,0,255),2);
    //====================================================================================================//
    points1.clear();
    Mat img2ROI;

  //  tpkeypoints = keypoints1;    tpdescriptors = descriptors1;
    cv::imshow(name,temp) ;
    imwrite("a.jpg",temp);
    cout << "BD_SIZE \t" << bdescriptors.rows << "\t" << "FD_SIZE \t"  << tpdescriptors.rows << endl;


//    Mat newimg = img1ROI.clone();
//     KeyPoint::convert(tpkeypoints, points1);
//    for(size_t i=0;i<points1.size();i++)
//         circle(newimg, points1[i], 2, Scalar(255,0,255),2);

//     imshow( "newimg", newimg );
//    points1.clear();

    waitKey(0);
    cvDestroyWindow( name );


    int FG_mp, FG, BG_mp, BG, FG_BG, msI ; //Foreground matching points
    struct timeval t1, t2;

    for(int l=0;;l++)
    {
        gettimeofday(&t1, NULL);
        cv::kmeans(tpdescriptors, NOC, labels1, TermCriteria( CV_TERMCRIT_ITER + CV_TERMCRIT_EPS, 50, 1.0 ), 1,
                   KMEANS_RANDOM_CENTERS, clusters1);

        cap >> frame;
        img2 = frame.clone() ;
        temp1 =frame.clone() ;

        if(img2.empty() )
        {
            cout<< "Could not open image: " << endl ;
            break;}

        int flag=1;
        Mpoints1.clear();
        Mat descriptors2;

        msI=0;

        meanShift(img1, img2, descriptorMatcher, mactherFilterType, tpkeypoints, tpdescriptors,keypoints2,descriptors2,
                  clusters1, cp, flag, MP1,img2ROI,bkeypoints, bdescriptors, temp1,FG_mp, FG, BG_mp, BG, FG_BG,msI);



        //==========scaling=================
        float scale=1;

       // cout <<"MP1size \t" << MP1.size() <<endl;

        if(APPLY_SCALING)
        {
            vector<DMatch> filteredMatches;

            if(descriptors1.rows > 4 && descriptors2.rows > 4)
            {
                crossCheckMatching( descriptorMatcher, descriptors1, descriptors2, filteredMatches, 1 );

                trainIdxs.clear();    queryIdxs.clear();

                for( i = 0; i < filteredMatches.size(); i++ )
                {
                    queryIdxs.push_back(filteredMatches[i].queryIdx);
                    trainIdxs.push_back(filteredMatches[i].trainIdx);
                }

                points1.clear(); points2.clear();
                KeyPoint::convert(keypoints1, points1, queryIdxs);
                KeyPoint::convert(keypoints2, points2, trainIdxs);
                //  cout << "point2size" << points2.size() << endl;

                //homography

                npoints1.clear();npoints2.clear();
                Mpoints1.clear();Mpoints2.clear();
                Mat H12, points1t;
                double ransacReprojThreshold = 10;
                if( ransacReprojThreshold >= 0  && points1.size() > 4)
                    H12 = findHomography( Mat(points1), Mat(points2), CV_RANSAC, ransacReprojThreshold );
              vector<char> matchesMask( filteredMatches.size(), 0 );// NONmatchesMask( filteredMatches.size(), 0 );
                if( !H12.empty() )
               {

                    perspectiveTransform(Mat(points1), points1t, H12);

                    double maxInlierDist = 10;//ransacReprojThreshold < 0 ? 3 : ransacReprojThreshold;

                    for(i = 0; i < points1.size(); i++ )
                    {
                        if( norm(points2[i] - points1t.at<Point2f>((int)i,0)) <= 5)// maxInlierDist ) // inlier
                        {
                            matchesMask[i] = 1;
                            npoints2.push_back(points2[i]);
                            npoints1.push_back(points1[i]);
                        }
                    }



                    for(i=0; i<npoints2.size();i++)
                    {
                        for(j=0;j<MP1.size();j++)
                        {
                            double dist = norm(npoints2[i]-MP1[j]);
                            // cout <<"dist \t" <<dist << endl;
                            //  waitKey(0);
                            if(dist < 0.1)
                            {
                                Mpoints2.push_back(npoints2[i]);
                                Mpoints1.push_back(npoints1[i]);
                                break;
                            }

                        }
                    }



                }
                Mat drawImg;
                drawMatches( img1ROI, keypoints1, img2ROI, keypoints2, filteredMatches, drawImg, CV_RGB(0, 255, 0), CV_RGB(0, 0, 255), matchesMask
             #if DRAW_RICH_KEYPOINTS_MODE
                             , DrawMatchesFlags::DRAW_RICH_KEYPOINTS
             #endif
                             );
                imshow( "correspondance", drawImg );
                cout << "npoints1.size \t" << Mpoints1.size() << "\t" << Mpoints2.size() << endl;
                if(Mpoints1.size() > 8)
                    weightScalingAspect(Mpoints1,Mpoints2,&scale);

            }

        }


        img1=img2;
        img1ROI = img2ROI;
        boxOrg =box;
        keypoints1 = keypoints2;
        descriptors1 =descriptors2;

        box.x += box.width/2;
        box.y += box.height/2;
        box.height = round(boxOrg.height *scale);
        box.width = round(( float(boxOrg.width)/float(boxOrg.height) ) * box.height);
        box.x -= box.width/2;
        box.y -= box.height/2;

        boundaryCheckRect(box);

        cout <<"SCALE \t" << scale << endl;

        gettimeofday(&t2, NULL);
       double diff = (float)((t2.tv_sec * 1000000 + t2.tv_usec) - (t1.tv_sec * 1000000 + t1.tv_usec));
       diff = diff/1000;
        cout <<"Time taken in mili sec \t" <<  diff<< endl;
       // cout << tpdescriptors.rows << endl;
        //cout <<"BD \t" << bdescriptors.rows << endl;
        f1 <<  l << "\t" << FG_mp << "\t"   << BG_mp  << "\t"   << FG   << "\t"<< msI << "\n";
        cout << "l \t" << l << "\t" <<" msI \t"<< msI << endl;
        imshow("img2",temp1);
        writer << temp1;
         waitKey(0);




       // boxOrg = eBox;

        char c = (char)waitKey(10);
        if( c == '\x1b' ) // esc
        {
            cout << "Exiting ..." << endl;
            break;
        }

    }
    trajectory.close();

    return 0;
}
Пример #11
0
//---------------------------------------------------------
Ptr<StatModel> COpenCV_ML_ANN::Get_Model(void)
{
	Ptr<ANN_MLP>	Model	= ANN_MLP::create();

	//-----------------------------------------------------
	Mat	layer_sizes(1, 2 + Parameters("ANN_LAYERS")->asInt(), CV_32SC1);

	layer_sizes.at<int>(0)	= Get_Feature_Count();	// The first layer needs the same size (number of neurons) as the number of columns in the training data

	for(int i=1; i<layer_sizes.cols-1; i++)
	{
		layer_sizes.at<int>(i)	= Parameters("ANN_NEURONS")->asInt();
	}

	layer_sizes.at<int>(layer_sizes.cols-1)	= Get_Class_Count();	// The last layer needs the same size (number of neurons) as the number of output columns

	Model->setLayerSizes(layer_sizes);

	//-----------------------------------------------------
	switch( Parameters("ANN_ACTIVATION")->asInt() )
	{
	case  0:	// Identity
		Model->setActivationFunction(ANN_MLP::IDENTITY);
		break;

	default:	// Sigmoid
		Model->setActivationFunction(ANN_MLP::SIGMOID_SYM, 
			Parameters("ANN_ACT_ALPHA")->asDouble(),
			Parameters("ANN_ACT_BETA" )->asDouble()
		);
		break;

	case  2:	// Gaussian
		Model->setActivationFunction(ANN_MLP::GAUSSIAN,
			Parameters("ANN_ACT_ALPHA")->asDouble(),
			Parameters("ANN_ACT_BETA" )->asDouble()
		);
		break;
	}

	//-----------------------------------------------------
	Model->setTermCriteria(TermCriteria(TermCriteria::MAX_ITER + TermCriteria::EPS,
		Parameters("ANN_MAXITER")->asInt   (),
		Parameters("ANN_EPSILON")->asDouble()
	));

	//-----------------------------------------------------
	switch( Parameters("ANN_PROPAGATION")->asInt() )
	{
	case  0:	// resilient propagation
		Model->setTrainMethod(ANN_MLP::RPROP);
		Model->setRpropDW0             (Parameters("ANN_RP_DW0"     )->asDouble());
		Model->setRpropDWPlus          (Parameters("ANN_RP_DW_PLUS" )->asDouble());
		Model->setRpropDWMinus         (Parameters("ANN_RP_DW_MINUS")->asDouble());
		Model->setRpropDWMin           (Parameters("ANN_RP_DW_MIN"  )->asDouble());
		Model->setRpropDWMax           (Parameters("ANN_RP_DW_MAX"  )->asDouble());
		break;

	default:
		Model->setTrainMethod(ANN_MLP::BACKPROP);
		Model->setBackpropMomentumScale(Parameters("ANN_BP_MOMENT"  )->asDouble());
		Model->setBackpropWeightScale  (Parameters("ANN_BP_DW"      )->asDouble());
		break;
	}

	//-----------------------------------------------------
	return( Model );
}
Пример #12
0
TEST_P(ML_ANN_METHOD, Test)
{
    int methodType = get<0>(GetParam());
    string methodName = get<1>(GetParam());
    int N = get<2>(GetParam());

    String folder = string(cvtest::TS::ptr()->get_data_path());
    String original_path = folder + "waveform.data";
    String dataname = folder + "waveform" + '_' + methodName;

    Ptr<TrainData> tdata2 = TrainData::loadFromCSV(original_path, 0);
    Mat samples = tdata2->getSamples()(Range(0, N), Range::all());
    Mat responses(N, 3, CV_32FC1, Scalar(0));
    for (int i = 0; i < N; i++)
        responses.at<float>(i, static_cast<int>(tdata2->getResponses().at<float>(i, 0))) = 1;
    Ptr<TrainData> tdata = TrainData::create(samples, ml::ROW_SAMPLE, responses);

    ASSERT_FALSE(tdata.empty()) << "Could not find test data file : " << original_path;
    RNG& rng = theRNG();
    rng.state = 0;
    tdata->setTrainTestSplitRatio(0.8);

    Mat testSamples = tdata->getTestSamples();

#ifdef GENERATE_TESTDATA
    {
    Ptr<ml::ANN_MLP> xx = ml::ANN_MLP_ANNEAL::create();
    Mat_<int> layerSizesXX(1, 4);
    layerSizesXX(0, 0) = tdata->getNVars();
    layerSizesXX(0, 1) = 30;
    layerSizesXX(0, 2) = 30;
    layerSizesXX(0, 3) = tdata->getResponses().cols;
    xx->setLayerSizes(layerSizesXX);
    xx->setActivationFunction(ml::ANN_MLP::SIGMOID_SYM);
    xx->setTrainMethod(ml::ANN_MLP::RPROP);
    xx->setTermCriteria(TermCriteria(TermCriteria::COUNT, 1, 0.01));
    xx->train(tdata, ml::ANN_MLP::NO_OUTPUT_SCALE + ml::ANN_MLP::NO_INPUT_SCALE);
    FileStorage fs;
    fs.open(dataname + "_init_weight.yml.gz", FileStorage::WRITE + FileStorage::BASE64);
    xx->write(fs);
    fs.release();
    }
#endif
    {
        FileStorage fs;
        fs.open(dataname + "_init_weight.yml.gz", FileStorage::READ);
        Ptr<ml::ANN_MLP> x = ml::ANN_MLP_ANNEAL::create();
        x->read(fs.root());
        x->setTrainMethod(methodType);
        if (methodType == ml::ANN_MLP::ANNEAL)
        {
            x->setAnnealEnergyRNG(RNG(CV_BIG_INT(0xffffffff)));
            x->setAnnealInitialT(12);
            x->setAnnealFinalT(0.15);
            x->setAnnealCoolingRatio(0.96);
            x->setAnnealItePerStep(11);
        }
        x->setTermCriteria(TermCriteria(TermCriteria::COUNT, 100, 0.01));
        x->train(tdata, ml::ANN_MLP::NO_OUTPUT_SCALE + ml::ANN_MLP::NO_INPUT_SCALE + ml::ANN_MLP::UPDATE_WEIGHTS);
        ASSERT_TRUE(x->isTrained()) << "Could not train networks with  " << methodName;
        string filename = dataname + ".yml.gz";
        Mat r_gold;
#ifdef  GENERATE_TESTDATA
        x->save(filename);
        x->predict(testSamples, r_gold);
        {
            FileStorage fs_response(dataname + "_response.yml.gz", FileStorage::WRITE + FileStorage::BASE64);
            fs_response << "response" << r_gold;
        }
#else
        {
            FileStorage fs_response(dataname + "_response.yml.gz", FileStorage::READ);
            fs_response["response"] >> r_gold;
        }
#endif
        ASSERT_FALSE(r_gold.empty());
        Ptr<ml::ANN_MLP> y = Algorithm::load<ANN_MLP>(filename);
        ASSERT_TRUE(y != NULL) << "Could not load   " << filename;
        Mat rx, ry;
        for (int j = 0; j < 4; j++)
        {
            rx = x->getWeights(j);
            ry = y->getWeights(j);
            double n = cvtest::norm(rx, ry, NORM_INF);
            EXPECT_LT(n, FLT_EPSILON) << "Weights are not equal for layer: " << j;
        }
        x->predict(testSamples, rx);
        y->predict(testSamples, ry);
        double n = cvtest::norm(ry, rx, NORM_INF);
        EXPECT_LT(n, FLT_EPSILON) << "Predict are not equal to result of the saved model";
        n = cvtest::norm(r_gold, rx, NORM_INF);
        EXPECT_LT(n, FLT_EPSILON) << "Predict are not equal to 'gold' response";
    }
}
Пример #13
0
Файл: Calib.cpp Проект: ALX5/PJS
Calib::Calib()
{
    Size boardSize(6,5); // Chessboard' size in corners with both color (nb of squares -1)
    int widthSquare = 40; // Width of a square in mm
    int heightSquare = 27;
    vector <Mat> images;

    // Getting the four images of the chessboard
    string imageFileName = "../src/mire1.jpg";
    images.push_back(imread(imageFileName, 1));

    imageFileName = "../src/mire2.jpg";
    images.push_back(imread(imageFileName, 1));

    imageFileName = "../src/mire3.jpg";
    images.push_back(imread(imageFileName, 1));

    imageFileName = "../src/mire4.jpg";
    images.push_back(imread(imageFileName, 1));

    Size imageSize = images.at(0).size();

    // Find chessboard's corners in the scene for the 4 images
    vector<vector<Point2f> > cornersScene(1);
    vector<Mat> imagesGray;

    imagesGray.resize(4);

    for (int i=0; i<4; i++)
    {
        if(images.at(i).empty())
        {
            cerr << "Image not read correctly!" << endl;
            exit(-1);
        }

        bool patternFound = findChessboardCorners(images.at(i), boardSize, cornersScene[0]);
        if(!patternFound)
        {
            cerr << "Could not find chess board!" << endl;
            exit(-1);
        }

        // Improve corner's coordinate accuracy
        cvtColor(images.at(i), imagesGray.at(i), CV_RGB2GRAY);
        cornerSubPix(imagesGray.at(i), cornersScene[0], Size(3,2), Size(-1,-1), TermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 30, 0.1));

        // Drawing the corners
        drawChessboardCorners(images.at(i), boardSize, Mat(cornersScene[0]), patternFound );

        imshow("Corners find", images.at(i));

        int keyPressed;
        /*do
        {
            keyPressed = waitKey(0);
        } while (keyPressed != 27);*/
    }

    // Getting the chessboard's corners on the mire's image
    vector<vector<Point3f> > cornersMire(1);

    for( int y = 0; y < boardSize.height; y++ )
    {
        for( int x = 0; x < boardSize.width; x++ )
        {
            cornersMire[0].push_back(cv::Point3f(float(x*widthSquare),
                                                 float(y*heightSquare), 0));
        }
    }

    // Getting the camera's parameters

    Mat distortionCoefficients = Mat::zeros(8, 1, CV_64F);
    Mat cameraMatrix = Mat::eye(3, 3, CV_64F);

    calibrateCamera(cornersMire, cornersScene, imageSize, cameraMatrix,
                    distortionCoefficients, rotationVectors, translationVectors);


    //cout << "Camera matrix: " << cameraMatrix << endl;
    //cout << "Distortion _coefficients: " << distortionCoefficients << endl;
    cout << rotationVectors.at(0) << endl;
    cout << translationVectors.at(0) << endl;

}
OpticalFlow::OpticalFlow() {
    data.termcrit = TermCriteria(TermCriteria::COUNT | TermCriteria::EPS, 40, 0.03);
    data.subPixWinSize = Size(10, 10);
    data.winSize = Size(7, 7);
    data.blocked = false;
}
TrackerSamplerPF::TrackerSamplerPF(const Mat& chosenRect,const TrackerSamplerPF::Params &parameters):
    params( parameters ),_function(new TrackingFunctionPF(chosenRect)){
        className="PF";
        _solver=createPFSolver(_function,parameters.std,TermCriteria(TermCriteria::MAX_ITER,parameters.iterationNum,0.0),
        parameters.particlesNum,parameters.alpha);
}
Пример #16
0
    Mat temp2;
    Mat temp3;
    Mat temp4;
    Mat temp5;
};


enum { OPTFLOW_USE_INITIAL_FLOW=4, OPTFLOW_FARNEBACK_GAUSSIAN=256 };

//! computes sparse optical flow using multi-scale Lucas-Kanade algorithm
CV_EXPORTS_W void calcOpticalFlowPyrLK( InputArray prevImg, InputArray nextImg,
                           InputArray prevPts, CV_OUT InputOutputArray nextPts,
                           OutputArray status, OutputArray err,
                           Size winSize=Size(15,15), int maxLevel=3,
                           TermCriteria criteria=TermCriteria(
                            TermCriteria::COUNT+TermCriteria::EPS,
                            30, 0.01),
                           double derivLambda=0.5,
                           int flags=0 );

//! computes dense optical flow using Farneback algorithm
CV_EXPORTS_W void calcOpticalFlowFarneback( InputArray prev, InputArray next,
                           CV_OUT InputOutputArray flow, double pyr_scale, int levels, int winsize,
                           int iterations, int poly_n, double poly_sigma, int flags );

//! estimates the best-fit Euqcidean, similarity, affine or perspective transformation
// that maps one 2D point set to another or one image to another.
CV_EXPORTS_W Mat estimateRigidTransform( InputArray src, InputArray dst,
                                         bool fullAffine);
    
}
Пример #17
0
///////////////////////////////////////////////////////
// Panel::PixelsToLength() 
//  Description: Not currently used: Calculates the
// ratio of cm to pixels from one checkerboard image
///////////////////////////////////////////////////////
void Panel::PixelsToLength(string sImgPath)
{
	cout << "Pixels to Length" << endl << endl;
	m_pPanel->m_Image = imread(sImgPath);

	Point2f corner1;
	Point2f corner2;
	Point2f corner3;
	Point2f corner4;

	bool found = false;

	found = findChessboardCorners(m_pPanel->m_Image, Size(9, 6), m_pPanel->corners,
		CALIB_CB_ADAPTIVE_THRESH | CALIB_CB_FAST_CHECK | CALIB_CB_NORMALIZE_IMAGE);

	Mat imgGray;
	cvtColor(m_pPanel->m_Image, imgGray, COLOR_BGR2GRAY);
	cornerSubPix(imgGray, m_pPanel->corners, Size(11, 11), Size(-1, -1),
		TermCriteria(CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 30, 0.1));

	corner1.x = m_pPanel->corners[45].x;
	corner1.y = m_pPanel->corners[45].y;

	corner2.x = m_pPanel->corners[0].x;
	corner2.y = m_pPanel->corners[0].y;

	corner3.x = m_pPanel->corners[8].x;
	corner3.y = m_pPanel->corners[8].y;

	corner4.x = m_pPanel->corners[53].x;
	corner4.y = m_pPanel->corners[53].y;

	// Draw rectangle around checkerboard

	line(m_pPanel->m_Image, corner1, corner2, CV_RGB(0, 0, 255), 2);
	line(m_pPanel->m_Image, corner2, corner3, CV_RGB(0, 0, 255), 2);
	line(m_pPanel->m_Image, corner3, corner4, CV_RGB(0, 0, 255), 2);
	line(m_pPanel->m_Image, corner4, corner1, CV_RGB(0, 0, 255), 2);

	circle(m_pPanel->m_Image, corner1, 10, CV_RGB(0, 0, 255), 2);
	circle(m_pPanel->m_Image, corner2, 10, CV_RGB(0, 255, 0), 2);
	circle(m_pPanel->m_Image, corner3, 10, CV_RGB(255, 0, 0), 2);
	circle(m_pPanel->m_Image, corner4, 10, CV_RGB(100, 100, 100), 2);

	double pixel_length = 0;
	double pixel_width = 0;

	double pixel_width1 = norm(corner1 - corner2);
	double pixel_length1 = norm(corner2 - corner3);
	double pixel_width2 = norm(corner3 - corner4);
	double pixel_length2 = norm(corner4 - corner1);

	if (pixel_length1 >= pixel_length2)
		pixel_length = pixel_length1;
	else 
		pixel_length = pixel_length2;

	if (pixel_width1 >= pixel_width2)
		pixel_width = pixel_width1;
	else
		pixel_width = pixel_width2;


	double ratio = (m_pPanel->m_boardLength - 1.0) / (m_pPanel->m_boardWidth - 1.0);

	if (pixel_length >= (pixel_width * ratio)){
		m_pPanel->m_cmPerPixel = (m_pPanel->m_squareSize * (float)(m_pPanel->m_boardLength - 1)) / pixel_length;
	}
	else
		m_pPanel->m_cmPerPixel = (m_pPanel->m_squareSize * (float)(m_pPanel->m_boardWidth - 1)) / pixel_width;

	cout << "cm per pixel : " << m_pPanel->m_cmPerPixel << endl;

	// Perspective Transform
	//	double ratio = 8.0 / 5.0;
	//	double length = ratio * pixel_width;
	//
	//	vector<Point2f> panel_pts;
	//	vector<Point2f> rect_pts;
	//	panel_pts.push_back(corner1);
	//	panel_pts.push_back(corner2);
	//	panel_pts.push_back(corner3);
	//	panel_pts.push_back(corner4);
	//	rect_pts.push_back(Point2f(0, 0));
	//	rect_pts.push_back(Point2f((float)width, 0));
	//	rect_pts.push_back(Point2f((float)width, (float)length));
	//	rect_pts.push_back(Point2f(0, (float)length));
	//
	//	// Draw new rectangle
	//	line(m_pPanel->m_Image, rect_pts[0], rect_pts[1], CV_RGB(255, 0, 0), 2);
	//	line(m_pPanel->m_Image, rect_pts[1], rect_pts[2], CV_RGB(255, 0, 0), 2);
	//	line(m_pPanel->m_Image, rect_pts[2], rect_pts[3], CV_RGB(255, 0, 0), 2);
	//	line(m_pPanel->m_Image, rect_pts[3], rect_pts[0], CV_RGB(255, 0, 0), 2);
	//
	//	// Perspective Transorm
	//	Mat transmtx = getPerspectiveTransform(panel_pts, rect_pts);
	//	int offsetSize = 500;
	//	Mat transformed = Mat::zeros(m_pPanel->m_Image.cols + offsetSize, m_pPanel->m_Image.rows + offsetSize, CV_8UC3);
	//	warpPerspective(m_pPanel->m_Image, transformed, transmtx, transformed.size());
	//
	////	Mat subImg(transformed, Rect(corner1.x, corner1.y, width, length));
	//
	//	namedWindow("Original", WINDOW_NORMAL);
	//	imshow("Original", m_pPanel->m_Image);
	//	namedWindow("Warped", WINDOW_AUTOSIZE);
	//	imshow("Warped", transformed);
}