Schlagwort: ‘Kalibrierung’

Camera calibration in SHAREWORK – part 2

February 9th, 2021 | by

In october last jear we already showed how to calibrate a camera network. With the calibration target at that time, a calibration accuracy in the sub-pixel range could already be generated. However, at the high distances of about 8 meters and at a resolution of “only” 4MP, this is still several millimeters of deviation in the real world. For our final tests, we reached into the bag of tricks again and got ourselves a larger calibration target. Now, however, the maneuverability is no longer so simple. How such a calibration process looks like with a target of more than 3 square meters, you can see in the video.

Watch this video on YouTube.
Der an dieser Stelle eingebundene Inhalt führt Sie auf Seiten, die von der von Google betriebenen Seite YouTube - YouTube, LLC, 901 Cherry Ave., San Bruno, CA 94066, USA - zur Verfügung gestellt werden. Mit dem Aufruf des Inhalts kann YouTube Ihre IP-Adresse und die Sprache des Systems, sowie verschiedene browserspezifische Angaben ermitteln. Wenn Sie in Ihrem YouTube-Account eingeloggt sind, ermöglichen Sie YouTube, Ihr Surfverhalten direkt Ihrem persönlichen Profil zuzuordnen. Dies können Sie verhindern, indem Sie sich aus Ihrem YouTube-Account ausloggen. YouTube verwendet Cookies und Tracking-Tools. Die Datenverarbeitungsvorgänge sowie die Zwecke der Verarbeitung können direkt bei YouTube erfragt und eingesehen werden.


Nils Mandischer

Stefan-Octavian Bezrucav

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