Publications / 2018 Proceedings of the 35th ISARC, Berlin, Germany

Crane Safety System with Monocular and Controlled Zoom Cameras

Axel Vierling, Tanittha Sutjaritvorakul and Karsten Berns
Pages 882-888 (2018 Proceedings of the 35th ISARC, Berlin, Germany, ISBN 978-3-00-060855-1, ISSN 2413-5844)
Abstract:

In this paper, we propose an approach and workflow in order to detect humans in the environment around a crane with Monocular Images. The considered area is split up into a zone around the crane truck and one around the load. The load will be monitored with an optical zoom camera where we can control the zoom. We discretize the zoom levels and a Convolutional Neural Network for each zoom level is trained. Afterwards a Meta Convolutional Neural Network is trained in order to select the next zoom level. Since there are no public datasets available for this kind of task we propose to generate the needed data with a photorealistic simulation.

Keywords: Crane, Safety, Human Detection, Deep Learning, Simulation