yamanneameh's profile - activity

Hallo,

I calculated H-S Histograms of 100 images for the same object which located in different environment conditions, I need now one average histogram of these 100 histograms!

vector<matnd> histImages; let's assume that we have histImages[i] ; i=0 to 99 number of histograms

Thank you in advance

    // hue varies from 0 to 179, see cvtColor
    float hranges[] = { 0, 180 };
    // saturation varies from 0 (black-gray-white) to
    // 255 (pure spectrum color)
    float sranges[] = { 0, 256 };
    const float* ranges[] = { hranges, sranges };
    MatND hist;
    // we compute the histogram from the 0-th and 1-st channels
    int channels[] = {0, 1};

    calcHist( &hsv, 1, channels, Mat(), // do not use mask
             hist, 2, histSize, ranges,
             true, // the histogram is uniform
             false );
    double maxVal=0;
    minMaxLoc(hist, 0, &maxVal, 0, 0);

    int scale = 10;
    Mat histImg = Mat::zeros(sbins*scale, hbins*10, CV_8UC3);

    for( int h = 0; h < hbins; h++ )
        for( int s = 0; s < sbins; s++ )
        {
            float binVal = hist.at<float>(h, s);
            int intensity = cvRound(binVal*255/maxVal);
            rectangle( histImg, Point(h*scale, s*scale),
                        Point( (h+1)*scale - 1, (s+1)*scale - 1),
                        Scalar::all(intensity),
                        CV_FILLED );
        }

This not work because if you have in first file 20 images and in the second 10 images at the end you will get FilesVector[30] (with 30 images) but what I need is FilesVector[ vict(20) , vict(10)] so finally when I call FilesVector[0] this mean that I call the images in the first file

Hello,

I am looping through multiple files to read images inside each one, I got the files paths and number of images in each file:

//here is part of the code:

vector <Mat>& Images;

for( size_t i = 0; i < ImagesCounts.size(); i++ )
    {
       Mat img = imread( filename, 1 ); //
       Images.push_back( img );
}

I read by this code the images of the first file so: Images[0]= img1 , Images[1]=img2 .....

I am now in the second loop (which has different filename and ImageCounts)

and I need to save first vector of Images in a global vector.. this mean:

FilesVector(vect[1],vect[2]......vect[N]); N is number of files

where: vect[1] should include the images of the first file vect[2] should include the images of the second file

So how I can define the global vector and push the images I have in the first loop to vect[1].. ?

I tried this code before going to the second loop but didn't work!

vector<vector<Mat>> FilesVector;
FilesVector[0]=Images;

Hallo,

after calibration and undistortion I have this image and I need to remove the black borders(crop the image)only depending on the camera parameters which I have in the output XML file so how I can define the region of interest?

  <Camera_Matrix type_id="opencv-matrix">
  <rows>3</rows>
  <cols>3</cols>
  <dt>d</dt>
  <data>
    1.3117098501208040e+003 0. 6.9550000000000000e+002 0.
    1.3117098501208040e+003 520. 0. 0. 1.</data></Camera_Matrix>
<Distortion_Coefficients type_id="opencv-matrix">
  <rows>5</rows>
  <cols>1</cols>
  <dt>d</dt>
  <data>
    -2.1400301530776253e-001 4.6169624608789456e-002 0. 0.
    1.8396036701643875e-001</data></Distortion_Coefficients>
<Avg_Reprojection_Error>3.6924789370054928e-001</Avg_Reprojection_Error>
<Per_View_Reprojection_Errors type_id="opencv-matrix">
  <rows>16</rows>
  <cols>1</cols>
  <dt>f</dt>
  <data>
    3.56106251e-001 3.05902541e-001 3.21639299e-001 3.97623330e-001
    4.79688823e-001 3.31597805e-001 2.92068005e-001 3.66955608e-001
    3.19793940e-001 6.19786203e-001 4.36506212e-001 3.26359451e-001
    3.68108034e-001 2.78367579e-001 2.72553772e-001 2.62321293e-001</data></Per_View_Reprojection_Errors>
<!-- a set of 6-tuples (rotation vector + translation vector) for each view -->
<Extrinsic_Parameters type_id="opencv-matrix">
  <rows>16</rows>
  <cols>6</cols>
  <dt>d</dt>
  <data>
    8.2524798674623173e-002 1.1957588136538763e-002
    -5.2492873372617030e-002 -8.7280621973657318e+001
    -3.9451553914075618e+001 5.7852359123958058e+002
    -2.0676032091414645e-001 -6.0286278602077602e-002 ...
    <Image_points type_id="opencv-matrix">
  <rows>16</rows>
  <cols>54</cols>
  <dt>"2f"</dt>
  <data>
    4.99537811e+002 4.31490295e+002 5.57311035e+002 4.28100739e+002
    6.15545166e+002 4.24772125e+002 6.74481750e+002 4.21481506e+002
    7.33297974e+002 4.18324432e+002 7.91958740e+002 4.15214600e+002
    8.51019897e+002 4.12198181e+002 9.09479858e+002 4.09300568e+002
    9.67362793e+002 4.06486938e+002 5.02951508e+002 4.89633362e+002
...

Thank you for this explaination

Hello,

I have the camera calibration Parameters as followings, and it works well for undistortion function, how I can Transfer these parametrs if I changed the angle of camera axes 90 degree to the left or the right?!

uint w= 1040, h= 1392; double disto[5]= { -0.205410121, 0.091357057, 0.000740608, 0.000895488, 0.053117702, };

cv::Mat cameraMatrix;
cv::Mat distCoeffs;
cv::Mat cameraIdeal;
cv::Mat ROTATION(3,3,CV_64F);


ocv_setcam(cameraMatrix, 1286.635225995, 1287.007162383, 520, 730.910560759);
ocv_setcam(cameraIdeal,  1288,           1288,           520,           762);       
vect2ocv(distCoeffs, disto,5);

assert(ROTATION.isContinuous());  
double * R= ((double*) ROTATION.data);

R[0]= 1.0; // col=0 auf row=0
R[1]= 0.0;
R[2]= 0.0;  

R[3]=  0.0;  
R[4]=  1.0; 
R[5]=  0.0;  

R[6]=  0.0;
R[7]=  0.0;  
R[8]=  1.0;

Hello,

I need to know if you got your coordinate system and translate the output of ReprojectImageTo3D function as I am working in the same topic, I have like this result

X coordinate values always between 350 - 450 Y coordinate values always between -80 to -30 z coordinates values always between 230 - 280 and sometimes 10000 when so far

Thank you for your help

Hello,

the result of 3d reprojection using StereoSGBM algorithm is the X,Y,Z coordinates of each pixel in the depth image.

public void Computer3DPointsFromStereoPair(Image<Gray, Byte> left, Image<Gray, Byte> right, out Image<Gray, short> disparityMap, out MCvPoint3D32f[] points)

    {
           points = PointCollection.ReprojectImageTo3D(disparityMap, Q);
    }

by taking the first element of this result:

points[0] = { X= 414.580017 Y= -85.03029 Z= 10000.0 }

I'm confused here!! to which pixel this point refers to ? and why it is not like this X=0,Y=0,Z=10000.0!

Hello,

the result of 3d reprojection function is a matrix that has X,Y,Z of each pixel.

let's take the first element of this matrix points[0] which has: X= 414.580017 Y= -85.03029 Z= 10000.0

what is the unit here and where I can find this pixel in the image ? and why it is not like this X=0,Y=0,Z=10000.0!

points = PointCollection.ReprojectImageTo3D(disparityMap, Q);

Hello,

I can connect to robot Axis cameras, but I can not set Capture class to get frames from these Camera devices ? or is there any other method to do that!

 this.Video_Source1 = new AxAXISMEDIACONTROLLib.AxAxisMediaControl();
 this.Video_Source2 = new AxAXISMEDIACONTROLLib.AxAxisMediaControl();


 Video_Source1.MediaURL = CompleteURL("192.168.0.57:8083", "mjpeg");
 Video_Source1.Play();


 Video_Source2.MediaURL = CompleteURL("192.168.0.58:8082", "mjpeg");
 Video_Source2.Play();

  _Capture1 = new Capture(here is the problem);
  _Capture2 = new Capture(here is the problem);

   _Capture1.ImageGrabbed += ProcessFrame;
   _Capture1.Start();

    }

    private void ProcessFrame(object sender, EventArgs arg)
    {
      Image<Bgr, Byte> frame_S1 = _Capture1.RetrieveBgrFrame();
      Image<Bgr, Byte> frame_S2 = _Capture2.RetrieveBgrFrame();
        .
        .
        .
    }

Hello,

I can connect to robot Axis cameras but how I can set Capture class to get frames from these Camera devices ? or is there any other method to do that!

Video_Source1.MediaURL = CompleteUR ("192.168.0.57:8083", "mjpeg"); Video_Source1.Play();

Video_Source2.MediaURL = CompleteURL("192.168.0.58:8082", "mjpeg"); Video_Source2.Play();

_Capture1 = new Capture(here is the problem); _Capture2 = new Capture(here is the problem);

_Capture1.ImageGrabbed += ProcessFrame; _Capture1.Start();}

private void ProcessFrame(object sender, EventArgs arg) {

Image<bgr> frame_S1 = _Capture1.RetrieveBgrFrame(); Image<bgr> frame_S2 = _Capture2.RetrieveBgrFrame(); . . . }