We are about to switch to a new forum software. Until then we have removed the registration on this forum.
Hi, I would like to find an object with a webcam and I would like to use the markers you can find in the three corners of a QRcode. There are libraries for QRcodes even with a find marker function but they only work if you have a fully readable QRcode. I would like to just slab the corner Markers on a playing card and then triangulate the position. I've found this: http://aishack.in/tutorials/scanning-qr-codes-2/ I don't really know how to translate this into Processing and I have a hard time with the syntax. I think it also uses many functions that aren't available in Processing.
Does perhaps someone know a tutorial that explains more the theory with pseudo code? I understand the concept of looking for Black and white pixels in the ratio of 1;1;3;1;1. How could I search for this pattern in the pixels array at different distances with some margin of error?
Answers
The term you are looking for is fiducials or fiducial markers.
Computer vision libraries often have built-in methods for dealing with fiducials. For Processing the two common libraries are OpenCV and BoofCV. If you search, you may find some tutorials and example code: