All geek questions in one place

Augmented reality with large and complex markers

Does anyone have experience using large and complex images as markers (e.g. magazine layout, photo, text layout) for ar?

I'm not sure where to go:

flash, papervision and flar would be good for distribution, but I suspect they are too bad in terms of performance for a more complex marker than regular 9x9 or 12x12 blocks. I had difficulty achieving good 3D performance and smooth and reliable detection.

I can also do java or objective-c with opengl / opencv, and this is definitely also an option for this project.

I just would like to know earlier if someone has experience in this area and can give me some tips or warnings. I know that this has already been done, so there is a way to do it smoothly.

thanks anton

+3
source share
2 answers

It looks like you can start exploring the libraries for tracking natural functions. In general, tracking is smoother and more reliable than markers, and any full natural image can be used as a marker. The disadvantage is that I do not know any generic solutions.

Metaio Unifeye works in a web browser via flash, if I remember correctly, something like this might be what you are looking for.

+1
source

MOPED. MOPED - . (, SIFT, SURF) , 3D- .
.

+1

Source: https://habr.com/ru/post/1787340/

More articles:


All Articles