Click here to Skip to main content
15,885,899 members
Please Sign up or sign in to vote.
0.00/5 (No votes)
See more: , +
Hello,

I'am working on a markerless augmented reality engine for mobile devices and the algorithm as to track an observer/camera by solving for [ R | T] given a 3D model of scene and the observed feature point, where R = 3D rotation of observer/camera and T = 3D translation. The solver for this is perspective n - point (PnP) but I'am not using Opencv so I would like to implement my own which should be based on RANSAC. Can someone point me to useful resources?

Thanks.
Posted

1 solution

Okay solved this myself, if someone would love to read about pose estimation methods for augmented reality or other applications I think this thesis might be useful http://projekter.aau.dk/projekter/files/14427578/A_Comparison_of_2D-3D_Pose_Estimation_Methods.pdf[^]
 
Share this answer
 

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)



CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900