ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | Q&A
Ask Your Question

Kinect raw disparity offset

asked 2011-04-12 21:44:15 -0500

Roberto Battisti gravatar image

updated 2016-10-24 09:02:18 -0500

ngrennan gravatar image

Hello, I'm looking at the kinect calibration ( ). Can anyone tell me why the disparity offset, doff, is around 1090? How is this value obtained?



edit retag flag offensive close merge delete


Are you aware that using openni_kinect ( there is no need for calibration?
Felix Endres gravatar image Felix Endres  ( 2011-04-13 01:45:10 -0500 )edit

1 Answer

Sort by ยป oldest newest most voted

answered 2011-04-20 11:50:53 -0500

Patrick Mihelich gravatar image

As Felix said, OpenNI internally converts the raw disparity values to metric distances, so when using openni_kinect there's no longer any need to calibrate that conversion. If you're interested in how this was done, the code is in kinect_calibration, starting line 292.

Basically, the depth Z is related to a raw disparity reading r by Z = A / (B - r), where A and B are constants we are solving for. In calibration, we:

  1. Capture depth and IR images of a checkerboard with known size.
  2. Find the checkerboard corners in the IR image.
  3. Solve the PnP problem to get the 3d coordinates of each corner. (In the code, this is a by-product of calibrating the IR camera intrinsics.)
  4. Look up the corresponding raw disparity reading for each corner in the depth images.
  5. Given this set of (Z, r) observations, perform a least-squares fitting for A and B.
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


Asked: 2011-04-12 21:44:15 -0500

Seen: 1,173 times

Last updated: Apr 20 '11