2014-11-11 01:29:14 -0600 | received badge | ● Supporter (source) |
2014-11-11 01:29:04 -0600 | commented answer | Pose Estimation and Feature Detection Dear Saracchini, Thank you for your reply. I want to find the global pose of an object which has multiple uniquely identifiable markers attached to it at different angles/view points. As you stated, my idea is to pass the solvePnp algorithm the real world (3D) co-ordinates of the identifiable key points. As for the 2D points it would be the co-ordinates of the keypoints which have been positively matched by brute force. I want to know how can I extract the marker identity and 2D co-ordinates of the matched key points for further use in PnP algorithm. In actual I want to get an extremely stable sort of ARToolKit type functionality. Thanks for your patience and help. |
2014-11-09 11:53:52 -0600 | asked a question | Pose Estimation and Feature Detection Hi all, I am trying to make a fiducial (QR marker) based pose estimation program which would be able to track multiple markers. I have started by building upon the OpenCV documentation example. To do so I started by finding key points and descriptors using the SIFT algorithm. Then a used Brute Force matching to find good matches (used ratio test as well). Now I need to use solvePnpRansac to find the pose estimation. However, as per my understanding the pose estimation algorithm requires coordinates between the real world object and 2D scene. How can I get the coordinates of the keypoints which have been matched by the SIFT algorithm? Thanks. |
2014-08-23 12:43:51 -0600 | asked a question | P3P Pose Estimation Hello, I am relatively new to image processing so please bear with me. I am planning to use P3P Pose Estimation in a project that would require quite high (~100 Hz) update rate. For that I have been going through some papers which describe the P3P algorithm. It has been mentioned that P3P gives upto 4 solutions out of which one is used. A fourth point can be used to remove the ambiguity. What I want to know is that if we have a general idea about the pose of the object and the 3D points which we intend to correspondence are known to be fixed on a rigid object (e.g. a helmet) is is possible to constraint the P3P algorithm so that it gives a unique solution? Any further explanation of the P3P algorithm would be most welcome. Many thanks in advance. |