Ask Your Question

maestroo's profile - activity

2016-04-02 20:36:52 -0600 commented question Watershed not working like expected
2016-03-27 09:21:44 -0600 received badge  Enthusiast
2016-03-24 12:21:24 -0600 received badge  Student (source)
2016-03-24 10:58:31 -0600 commented question Watershed not working like expected

I'm using Matlab MEX functions that interface OpenCV 3.0.1 APIs

2016-03-24 10:30:55 -0600 received badge  Editor (source)
2016-03-24 10:28:29 -0600 asked a question Watershed not working like expected


I'm using Matlab to use OpenCV functions, I succesfully used the watershed function from Matlab, but OpenCV variant is not working.

I'm using following int8 depth image: image description

because openCV using RGB image format, I replicated these values in a MxNx3-matrix. As marker I have an int32 matrix where I pointed every local minimum (5 in total), image description

By using following function

resultOpenCV= cv.watershed(rgbImage,marker);

The segmented matrix looks like this: image description

In Matlab using following function (even without markers)

resultMatlab= watershed(rgbImage(:,:,1));

This is the correct result: image description

Where am I wrong?

Thank you

2016-03-22 12:41:04 -0600 asked a question How to calibrate a 3D camera?

Hey I’m using a 3D camera (ToF camera). On the internet I didn’t find a clear way to calibrate this camera.

I receive a luminance image and a depth image (radius distance). This is what I have in mind for calibration method:

Put a checkerboard pattern on a table. Now use this pattern to determine the intrinsic and extrinsic parameters: extrinsic: I can use this pattern to create a new base where the checkerboard is the new (x,y)-plane (z=0). intrinsic: the x, y, (z?) values of the squares should be correct now.

Which functions do I need to use to achieve this? Or what is the conventional way to calibrate a ToF-camera?

Thank you.