Title:
Generating Simulated Infrared Sensor Images Using Deep Learning Neural Networks
Abstract:
This study presents a method for generating infrared images using deep learning techniques, specifically Generative Adversarial Networks (GANs), trained on data from real flight experiments. Implemented in Python, the approach leverages a U-Net adapted for gray-scale IR image generation. After training on a multi-core computer, the method achieved accurate infrared image generation, applicable in flight simulation and autonomous navigation.
Event:
Deutscher Luft- und Raumfahrtkongress 2025, Augsburg
Location, Year:
Deutsche Gesellschaft für Luft- und Raumfahrt - Lilienthal-Oberth e.V., Bonn, 2025
Format:
21,0 x 29,7 cm, 5 Pages
Descriptors:
EN: deep learning, sensor simulation, infrared simulation, GAN
Citation:
Peinecke, N. (2025): Generating Simulated Infrared Sensor Images Using Deep Learning Neural Networks. DGLR Published Conference Papers. Volume 4. (2026). ISSN: 2941-3451. Deutsche Gesellschaft für Luft- und Raumfahrt - Lilienthal-Oberth e.V.. (Text). https://doi.org/10.25967/650013. urn:nbn:de:101:1-2510241345293.131019629805.
Publishing Date:
24.10.2025