How to understand orientation of keypoints in Feature Matching?

Python
1

I was referring to these notes on Oriented FAST Rotated BRIEF, I have attached a url document of the part I didn’t understand where it states The direction of the vector from this corner point to centroid gives the orientation.

  1. How does the orientation of keypoints calculated? and How is vector drawn from particular corner inside the the circular patch towards centroid(center of the circle)? I got the part where it calculates the intensity weighted centroid which is basically (x,y) points located at the center of the patch. Calculation of centroid can be achieved through moments method of opencv

It would be really helpful if someone can explain this concept to me and I can continue my learning. Thanks

2

please, no images of text here (or anywhere else), thank you.

then: nice explanation here

3

Thanks for quick response. I don’t mind removing the images of text and won’t put any images of text from now on. I am just curious is it against this forum policy? just want to know and understand. So next I can be more aware before posting

4
  • can’t be indexed for search
  • ppl can’t quote (parts of) it
  • if it’s code, ppl can’t try it
  • not accessible from text readers
  • wasting storage/bandwidth