3

does anyone have any experience with using large and complex images as markers (e.g. magazine layout, photo, text-layout) for a.r.?

i am not sure which way to go:

flash, papervision and flar would be nice for distribution but i suspect them to be too bad in terms of performance for a more complex marker than the usual 9x9 or 12x12 blocks. i had difficulties achieving both a good 3d performance and a smooth and solid 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 before if anyone has had experiences in this field and could give me a few hints or warnings. i know it has been done already so there is a way to do it smoothly.

thanks, anton

DasAntonym
  • 452
  • 3
  • 19
  • For the smooth part, I think you'd have to go for some mathematical tools - kalman filters or something. – Utkarsh Sinha Jan 24 '11 at 13:37
  • Google this→Natural Feature Extraction AR. You should find something useful. Better in C++/C cause no body implements that in Objective-C ;) – nacho4d Jan 25 '11 at 15:38
  • thanks for the help, i'll give it a try and see what will be the best option! – DasAntonym Feb 01 '11 at 12:21

2 Answers2

1

It sounds like you might want to start investigating natural feature tracking libraries. In general the tracking is smoother and more robust than with markers, and any feature-full natural image can be used as the marker. The downside is, I'm not aware of any non-proprietary solutions.

Metaio Unifeye works in a web-browser via flash if I recall correctly, something like that might be what you're looking for.

dabhaid
  • 3,849
  • 22
  • 30
  • metaio looks really nice and easy cause you don't need to do so much basics. sadly with this low requirement level comes a hefty price tag... sigh, we'll have to try and get them to sponsor the project. there's a demo, maybe i can check it out and give it a try. thanks! – DasAntonym Feb 01 '11 at 12:26
1

You should look at MOPED. MOPED is a real-time Object Recognition and Pose Estimation system. It recognizes objects from point-based features (e.g. SIFT, SURF) and their geometric relationships extracted from rigid 3D models of objects.
See this video for a demonstration.

Adi Shavit
  • 16,743
  • 5
  • 67
  • 137