detect - What is the state-of-art algorithms for planar object recognition? -


i read sift, surf, fern, brift , evolution algorithms. not sure algorithms best. need help. of course know each algorithms have own advantages, here key classify:

  • which fastest in training/ recognize phases?
  • which consume fewest memory in runtime?
  • which can implement detect 3d object?

thank you, , sorry bad english. in case, want implement application on smartphone recognize known object.

your question bit complicated.

there no optimal methods cases methods suit specific cases.

if decide use local descriptors in method advise started using sift / surf popular descriptors not efficient (slow) , require lot of memory. after that, can try replace them binary descriptors (eg. brief, orb, brisk, freak) more efficient , require less storage.

but said before depends on want implement, , requirements of application.


Comments

Popular posts from this blog

python - mat is not a numerical tuple : openCV error -

c# - MSAA finds controls UI Automation doesn't -

wordpress - .htaccess: RewriteRule: bad flag delimiters -