DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Synthetic Training Data for Semantic Segmentation of the Environment from UAV Perspective

Hinniger, Christoph and Rüter, Joachim (2023) Synthetic Training Data for Semantic Segmentation of the Environment from UAV Perspective. Aerospace, 10 (7). Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/aerospace10070604. ISSN 2226-4310.

[img] PDF - Published version

Official URL: https://www.mdpi.com/2226-4310/10/7/604


Autonomous unmanned aircraft need a good semantic understanding of their surroundings to plan safe routes or to find safe landing sites, for example, by means of a semantic segmentation of an image stream. Currently, Neural Networks often give state-of-the-art results on semantic segmentation tasks but need a huge amount of diverse training data to achieve these results. In aviation, this amount of data is hard to acquire but the usage of synthetic data from game engines could solve this problem. However, related work, e.g., in the automotive sector, shows a performance drop when applying these models to real images. In this work, the usage of synthetic training data for semantic segmentation of the environment from a UAV perspective is investigated. A real image dataset from a UAV perspective is stylistically replicated in a game engine and images are extracted to train a Neural Network. The evaluation is carried out on real images and shows that training on synthetic images alone is not sufficient but that when fine-tuning the model, they can reduce the amount of real data needed for training significantly. This research shows that synthetic images may be a promising direction to bring Neural Networks for environment perception into aerospace applications.

Item URL in elib:https://elib.dlr.de/195944/
Document Type:Article
Title:Synthetic Training Data for Semantic Segmentation of the Environment from UAV Perspective
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Rüter, JoachimUNSPECIFIEDhttps://orcid.org/0000-0002-5559-5481143182704
Date:30 June 2023
Journal or Publication Title:Aerospace
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In ISI Web of Science:Yes
Publisher:Multidisciplinary Digital Publishing Institute (MDPI)
Keywords:environment perception; semantic segmentation; synthetic data; game engine; sim-to-real gap; machine learning; unmanned aerial vehicle
HGF - Research field:other
HGF - Program:other
HGF - Program Themes:other
DLR - Research area:Digitalisation
DLR - Program:D IAS - Innovative Autonomous Systems
DLR - Research theme (Project):D - SKIAS
Location: Braunschweig
Institutes and Institutions:Institute of Flight Systems > Unmanned Aircraft
Institute of Flight Systems
Deposited By: Rüter, Joachim
Deposited On:28 Sep 2023 13:37
Last Modified:28 Sep 2023 13:37

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.