Ask Your Question
0

How to interpret camera.yml of object_recognition_transparent_object?

asked 2014-09-16 05:16:56 -0500

Hi all,

I want to use transparent_object to estimate the pose of my object. And the sample program needs camera.yml as input.

%YAML:1.0
camera:
   K: !!opencv-matrix
      rows: 3
      cols: 3
      dt: d
      data: [ 525., 0., 3.2050000000000000e+02, 0., 525.,
          2.4050000000000000e+02, 0., 0., 1. ]
   D: !!opencv-matrix
      rows: 5
      cols: 1
      dt: f
      data: [ 0., 0., 0., 0., 0. ]
   width: 640 
   height: 480 
   pose:
      rvec: !!opencv-matrix
         rows: 3
         cols: 1
         dt: d
         data: [ 0., 0., 0. ]
      tvec: !!opencv-matrix
         rows: 3
         cols: 1
         dt: d
         data: [ 0., 0., 0. ]

I've found that this file is for camera calibration, http://docs.opencv.org/trunk/doc/tuto... http://maztories.blogspot.tw/2013/07/...

I don't know the relationship between this file and PR2. If I want to use PR2's kinect to get image, do I need to adjust the content of this file? How do I adjust it?

Thanks in advance.

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted
0

answered 2015-06-28 21:33:57 -0500

OK, the K matrix is the intrinsic matrix. D is the distortion coefficients. And this is not related to PR2's tf. http://docs.opencv.org/doc/tutorials/...

If I want to modify this file, I can use camera_calibration to get results and use camera calibration parser to transform the format.

edit flag offensive delete link more

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

1 follower

Stats

Asked: 2014-09-16 05:16:56 -0500

Seen: 1,433 times

Last updated: Jun 28 '15