Reputation: 7304
I tried to understand the cornerSubPix
API in OpenCV for its idea behind and usefulness. I read the explanation in the link and can't understand how it works and how it is useful.
Can somebody explain me how it works and how it is useful at corner refinement? I checked my corner detection application for without cornerSubPix
and with cornerSubPix
. Not much difference in output image, but it takes time to process.
Thanks
Upvotes: 4
Views: 4455
Reputation: 6080
I can´t explain better how it works than the actual documentation but I can help you with the: "how it is useful at corner refinement" Part.
The corners you find are in Pixel Coordinates. This means a Pixel can be at Position (10,10) or (11,11) but not at Position (11.3,11.2)
Subpixel refinement allows edges at such positions and helps to find a better position.
Upvotes: 5