Filtern
Dokumenttyp
- Konferenzveröffentlichung (21) (entfernen)
Sprache
- Englisch (21) (entfernen)
Schlagworte
- 360° Panorama (1)
- Alternative Geschäftsmodelle (1)
- Artificial Intelligence (1)
- Assisted living technologies (1)
- Assistive robotics (1)
- Augmented Reality (1)
- Autonomous Agents (1)
- Continuous Queries (1)
- Crowdfunding (1)
- Datalog (1)
- Deductive Databases (1)
- Erweiterte Realität <Informatik> (1)
- Human-Robot Interaction (1)
- Human-centered computing (1)
- Incremental Evaluation (1)
- Journalismus (1)
- Kalman filter (1)
- Machine Learning (1)
- Mixed Reality (1)
- Multi-Agent System (1)
- NeRF (1)
- People with disabilities (1)
- Rescue Robotics (1)
- Robot assistive drinking (1)
- Robot assistive eating (1)
- Robotik (1)
- Small UAVs (1)
- Smart Grid (1)
- Tetraplegie (1)
- Update Propagation (1)
- Visual Monocular SLAM (1)
- Zustandsmaschine (1)
- human-centered design (1)
- hybrid sensor system (1)
- participatory design (1)
- risk management (1)
- sensor fusion (1)
- state machine (1)
- user acceptance (1)
Institut
- Informatik und Kommunikation (21) (entfernen)
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.