KIT | KIT-Bibliothek | Impressum | Datenschutz

Object Detection on Thermal Images for Unmanned Aerial Vehicles Using Domain Adaption Through Fine-Tuning

Rauch, Jonas; Doer, Christopher; Trommer, Gert F.

Abstract (englisch):

This work addresses state-of-the-art object detection methods using deep learning on thermal images for application on Unmanned Aerial Vehicles (UAVs). For this purpose, fine-tuning is performed using a custom dataset. Special focus is given to the generation of this dataset, as the annotations for the thermal images are automatically generated from simultaneously acquired visual images. The bounding boxes found on visual images using state-of-the-art object detection methods are applied as annotations to the thermal images. Furthermore, it is shown how the fine-tuned models can be executed in real-time on the drone's embedded PC, which is limited in its computing power, by using additional accelerator hardware.


Originalveröffentlichung
DOI: 10.23919/ICINS43216.2021.9470420
Scopus
Zitationen: 5
Zugehörige Institution(en) am KIT Institut für Regelungs- und Steuerungssysteme (IRS)
Publikationstyp Proceedingsbeitrag
Publikationsdatum 31.05.2021
Sprache Englisch
Identifikator ISBN: 978-5-91995-080-6
KITopen-ID: 1000136050
Erschienen in 28th Saint Petersburg International Conference on Integrated Navigation Systems (ICINS), 31st May 2021 - 2nd June 2021, Saint Petersburg, Russia
Veranstaltung 28th Saint Petersburg International Conference on Integrated Navigation Systems (ICINS 2021), Sankt Petersburg, Russland, 31.05.2021 – 02.06.2021
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Seiten Art.Nr. 9470842
Nachgewiesen in Dimensions
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page