0
$\begingroup$

I was looking for some commonly used approaches in computer vision to find the following calibration stickers and I was pretty surprised that I have not found any. I am not sure if I am just googling wrong terms or whether no one cares about this topic.

So I am wondering what is the common approach to find these pasterns ? Is it just by looking for geometrical objects of known properties combined with filtering of colors or by using some feature extractor such as SIFT (which I have not tried yet, but I think that the pattern is too simple for featrue extractor such as SIFT) or is there some more complex/robust approach?

Sorry for such a bad question, but I really did not find any discussions on that topic.

enter image description here

$\endgroup$
  • $\begingroup$ Try using hough transform for detecting circles and generalised hough transform for detecting triangles.I think as preprocessing step first detect the object based on colour of wall and object. $\endgroup$ – Vinith Jun 22 '18 at 14:24

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.