RVQ's profile - activity

Thank you for clarification!

Hi,

I have a simple question. I read about the cvtColor function in the docs. I would like to know how OpenCV converts a BGR image to greyscale image.

According to the docs it uses the following formular.

formular

Is it correct, that the Y stands for the alpha channel and all values in this channel will be replaced by 0.299?

Thanks in advance!

Thank you!

Thanks for the sources. Am I understanding you correct, that you say, that my Points are coplanar but it works anyway because of a closed form solution?

Hi,

A while ago I worked on pose estimation. I also asked a question about it to make it work. (old question)

Today I read the following about POSIT (solvePNP) in Learning OpenCV 1st Edition

POSIT (aka “Pose from Orthography and Scaling with Iteration”) is an algorithm originally proposed in 1992 for computing the pose (the position T and orientation R described by six parameters [DeMenthon92]) of a 3D object whose exact dimensions are known. To compute this pose, we must find on the image the corresponding locations of at least four non-coplanar points on the surface of that object.

This is my image

Example

For me this points appear to be coplanar, since they are all in the same plane? Could someone explain to me why it works anyway?

Thank you very much!

Hi,

I created a charuco board with the example application from the aruco module (create_board_charuco.cpp). I am suprised that the result is a board where all squares are black. In the las verion I used, I got a board with black and white squares. Why has it changed? Is it better or just a mistake?

My generated board: C:\fakepath\board.jpg

What I expected: C:\fakepath\charucoboard.jpg

Hi,

I am trying to do pose estimation. But I am clearly doing something wrong. Let's say I have a pattern consisting of 4 Markers (A,B,C,D). Each of these markers has an image coordinate and a pattern coordinate. The origin of the pattern is the center of the polygon.

The image coordinates (x/y) are the following. (In a 1280x960 image)

• Origin(616/814)

• A(561/664)

• B(702/838)

• C(637/982)

• D(520/755)

Pattern coordinates (x/y/z)

• Origin(0/0/0)

• A(-12/32/0)

• B(18/-5/0)

• C(12/-36/0)

• D(21/13/0)

Now it rotates by 90 degrees, but my coordinate system does not rotate with the pattern. I am wondering what is wrong? Is it because the Z coordinate is always 0?

• (x/y)
• Origin(632/784)

• A(718/812)

• B(567/938)

• C(441/909)

• D(632/784)

Pattern coordinates (x/y/z)

• Origin(0/0/0)

• A(32/12/0)

• B(-4/18/0)

• C(-35/11/0)

• D(11/19/0)

I am using solvePnP like this

 cv::solvePnP(patternPoints, imgPoints, cameraMatrix, distCoeffs, rvec, tvec);

Drawing the axis

//Method Call
pattern.drawAxis(image, camMatrix, distCoeffs, rvec, tvec,10);

//Implementation (taken from aruco.cpp)

void drawAxis(InputOutputArray _image, InputArray _cameraMatrix, InputArray _distCoeffs,
              InputArray _rvec, InputArray _tvec, float length) {

    CV_Assert(_image.getMat().total() != 0 &&
              (_image.getMat().channels() == 1 || _image.getMat().channels() == 3));
    CV_Assert(length > 0);

    // project axis points
    vector< Point3f > axisPoints;
    axisPoints.push_back(Point3f(0, 0, 0));
    axisPoints.push_back(Point3f(length, 0, 0));
    axisPoints.push_back(Point3f(0, length, 0));
    axisPoints.push_back(Point3f(0, 0, length));
    vector< Point2f > imagePoints;
    projectPoints(axisPoints, _rvec, _tvec, _cameraMatrix, _distCoeffs, imagePoints);

    // draw axis lines
    line(_image, imagePoints[0], imagePoints[1], Scalar(0, 0, 255), 3);
    line(_image, imagePoints[0], imagePoints[2], Scalar(0, 255, 0), 3);
    line(_image, imagePoints[0], imagePoints[3], Scalar(255, 0, 0), 3);
}

I know it's a late answer but maybe it's still helpfull.

You could try it with the object tracking algorithm provied by DLIB

Checkout this Blogpost http://blog.dlib.net/2015/02/dlib-181...

Thank you!

Hi,

I did the openCV Background Subtraction tutorial, which is described here.

First the complete source code is listed, in which createBackgroundSubtractorMOG is not used. But in the Explanation part it is described.

That's obviously an error, but it didn`t take me long to figure it out. Hower now I want to use createBackgroundSubtractorMOG instead of createBackgroundSubtractorMOG2, but it seems that this method has been complitly removed.

Does somybody know if this is true and if it is, why the method has been removed?

PS: I am using opencv 3.0.0

Thanks and Greets

RVQ

[Solved][Note]

I had some errors building opencv_contrib. However I just wanted to try BackgroundSubtractorMOG. So I just copied the .cpp and header files in my Project and builded it again, which worked fine.