Using Synthetic Images to Evaluate and Improve Object Detection Neural Networks Performance on Aerial Image Datasets

Konen, Kai and Hecking, Tobias (2022) Using Synthetic Images to Evaluate and Improve Object Detection Neural Networks Performance on Aerial Image Datasets. International Journal of Semantic Computing, 16 (3), pp. 339-356. World Scientific Publishing Co. doi: 10.1142/S1793351X22420016. ISSN 1793-351X.

PDF - Only accessible within DLR - Preprint version (submitted draft)
13MB

Official URL: https://doi.org/10.1142/S1793351X22420016

Item URL in elib:

https://elib.dlr.de/186808/

Document Type:

Article

Title:

Using Synthetic Images to Evaluate and Improve Object Detection Neural Networks Performance on Aerial Image Datasets

Authors:

Authors	Institution or Email of Authors	Author's ORCID iD	ORCID Put Code
Konen, Kai	Kai.Konen (at) dlr.de	https://orcid.org/0000-0001-7957-4477	144889240
Hecking, Tobias	Tobias.Hecking (at) dlr.de	https://orcid.org/0000-0003-0833-7989	144889243

Date:

8 May 2022

Journal or Publication Title:

International Journal of Semantic Computing

Refereed publication:

Yes

Open Access:

Gold Open Access:

In SCOPUS:

Yes

In ISI Web of Science:

Yes

Volume:

DOI:

10.1142/S1793351X22420016

Page Range:

pp. 339-356

Publisher:

World Scientific Publishing Co

ISSN:

1793-351X

Status:

Published

Keywords:

UAV, Object Detection, Neural Networks, Aerial Images, Synthetic Images, Simulation

HGF - Research field:

Aeronautics, Space and Transport

HGF - Program:

Aeronautics

HGF - Program Themes:

Components and Systems

DLR - Research area:

Aeronautics

DLR - Program:

L CS - Components and Systems

DLR - Research theme (Project):

L - Unmanned Aerial Systems

Location:

Köln-Porz

Institutes and Institutions:

Institute of Software Technology > Intelligent and Distributed Systems
Institute of Software Technology

Deposited By:

Konen, Kai

Deposited On:

11 Aug 2022 10:50

Last Modified:

07 Nov 2025 11:24

Repository Staff Only: item control page