Pattern recognition and pose estimation

edit

Hi. I working for augmented reality application. For pattern recognition i use next pipe:

• orb feature detecting
• orb descriptor extracting
• feature matching with Bruteforce matcher
• pose estimation (SolvePNPRansac)

But it's pipeline works fine only for small distances and not "hard" angles.

Is there the better approach for pose estimation?

Is there additional capabilities for pattern recognition, when it flat?