Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Where to drive: free space detection with one fisheye camera

: Scheck, Tobias; Mallandur, Adarsh; Wiede, Christian; Hirtz, Gangolf


Osten, Wolfgang (Hrsg.); Nikolaev, Dmitry (Hrsg.); Zhou, Jianhong (Hrsg.) ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Twelfth International Conference on Machine Vision, ICMV 2019 : 16-18 November 2019, Amsterdam, the Netherlands
Bellingham, WA: SPIE, 2020 (Proceedings of SPIE 11433)
ISBN: 978-1-5106-3644-6
ISBN: 978-1-5106-3643-9
Paper 114332V, 10 S.
International Conference on Machine Vision (ICMV) <12, 2019, Amsterdam>
Fraunhofer IMS ()
free space detection; fisheye camera; convolutional neural network (CNN); synthetic data creation; Deep Learning

The development in the field of autonomous driving goes hand in hand with ever new developments in the field of image processing and machine learning methods. In order to fully exploit the advantages of deep learning, it is necessary to have sufficient labeled training data available. This is especially not the case for omnidirectional fisheye cameras. As a solution, we propose in this paper to use synthetic training data based on Unity3D. A five-pass algorithm is used to create a virtual fisheye camera. This synthetic training data is evaluated for the application of free space detection for different deep learning network architectures. The results indicate that synthetic fisheye images can be used in deep learning context.