UAVs and Neural Networks for search and rescue missions
- In this paper, we present a method for detecting objects of interest, including cars, humans, and fire, in aerial images captured by unmanned aerial vehicles (UAVs) usually during vegetation fires. To achieve this, we use artificial neural networks and create a dataset for supervised learning. We accomplish the assisted labeling of the dataset through the implementation of an object detection pipeline that combines classic image processing techniques with pretrained neural networks. In addition, we develop a data augmentation pipeline to augment the dataset with utomatically labeled images. Finally, we evaluate the performance of different neural networks.
Volltext Dateien herunterladen
—In this paper, we present a method for detecting objects of interest, including cars, humans, and fire, in aerial images captured by unmanned aerial vehicles (UAVs) usually during vegetation fires. To achieve this, we use artificial neural networks and create a dataset for supervised learning. We accomplish the assisted labeling of the dataset through the imple- mentation of an object detection pipeline that combines classic image processing techniques with pretrained neural networks. In addition, we develop a data augmentation pipeline to augment the dataset with automatically labeled images. Finally, we evaluate the performance of different neural networks.
Weitere Dienste
| Verfasserangaben: | Hartmut Surmann, Artur Leinweber, Gerhard Senkowski, Julien Meine, Dominik Slomma |
|---|---|
| URN: | urn:nbn:de:hbz:1010-opus4-44617 |
| Dokumentart: | Konferenzveröffentlichung |
| Sprache: | Englisch |
| Datum der Veröffentlichung (online): | 09.10.2023 |
| Datum der Erstveröffentlichung: | 26.09.2023 |
| Veröffentlichende Institution: | Westfälische Hochschule Gelsenkirchen Bocholt Recklinghausen |
| Datum der Freischaltung: | 29.01.2024 |
| Seitenzahl: | 8 |
| Erste Seite: | 1 |
| Letzte Seite: | 8 |
| Fachbereiche / Institute: | Fachbereiche / Informatik und Kommunikation |
| DDC-Klassifikation: | Informatik, Informationswissenschaft, allgemeine Werke / Informatik, Wissen, Systeme / Datenverarbeitung; Informatik |
| Lizenz (Deutsch): |  Creative Commons - Namensnennung - Keine Bearbeitung |
