0
$\begingroup$

Rosanswers logo

Hi all,

Does anyone know a working package for retrieving pose (3D position) of an object from an image or bag file? I used Objects of Daily Use Finder (ODUfinder) and tod_training + tod_detecting pair. They work quite good but I can't retrieve the pose of the objects in the images or the input from a camera.

The two packages can recognize the objects existing in database, tod_detect also gives an estimation of the POSE but JUST VISUALLY. So somehow it computes the pose as it can give it visually but I don't know how I can get it numerically.

Thank you for your help,

Best regards..


Originally posted by dlmypr on ROS Answers with karma: 236 on 2011-02-28

Post score: 0

$\endgroup$

2 Answers 2

0
$\begingroup$

Rosanswers logo

Maybe the "posest" package will help you. I have not used it yet but seem like it does what you want


Originally posted by jrcapriles with karma: 370 on 2011-03-10

This answer was NOT ACCEPTED on the original site

Post score: 1


Original comments

Comment by dlmypr on 2011-03-11:
thanks for the reply I will search it by the way I found the answer maybe I should post it.

$\endgroup$
0
$\begingroup$

Rosanswers logo

If you are running the recognizer node from tod_detecting and are seeing text output like

"Object name = " << object.objectName << ", imageId = " << object.imgIdx

then that is generated from line 167 of recognizer.cpp.

Each of the ObjectInfo objects referenced there have rvec and tvec members (see this) which presumably store the pose of the object. You could modify that loop to print out or otherwise output the pose as well as the name.


Originally posted by dlmypr with karma: 236 on 2011-03-11

This answer was ACCEPTED on the original site

Post score: 2

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.