Camera calibration in SHAREWORK

October 9th, 2020 | by

In the EU project SHAREWORK we develop a framework for industry that allows human-robot collaboration even with heavy industrial robots. We are developing camera-based methods for localizing objects in the workspace and deriving process states from them, which in turn can be further used in task planning algorithms.

For the camera network, we set up and calibrated four Stereolabs ZED stereo cameras in our hall. Random, checkerboard, Aruco, as well as ChAruco patterns were used for the calibration. In the end, we have managed to calibrate the cameras to sub-pixel accuracy. In the video, you can see some data from our calibration sets. Currently the data is being processed and we hope to show more in a few weeks.

Watch this video on YouTube:

The content embedded at this point leads you to pages provided by the Google-operated site YouTube – YouTube, LLC, 901 Cherry Ave, San Bruno, CA 94066, USA. By calling up the content, YouTube can determine your IP address and the language of the system, as well as various browser-specific details. If you are logged into your YouTube account, you enable YouTube to assign your surfing behavior directly to your personal profile. You can prevent this by logging out of your YouTube account. YouTube uses cookies and tracking tools. The data processing operations as well as the purposes of the processing can be requested and viewed directly at YouTube.


Project page:


Contact person:

Stefan Bezrucav

Nils Mandischer


Comments are closed.