004 Datenverarbeitung; Informatik
Refine
Has Fulltext
- yes (6)
Is part of the Bibliography
- yes (6)
Document Type
- Journal article (5)
- Report (1)
Language
- English (6)
Keywords
- self-aware computing (2)
- Deep learning (1)
- Internet of Things (1)
- Performance Management (1)
- Quality-of-Service (1)
- Resource and Performance Management (1)
- Ressourcenmanagement (1)
- Software Engineering (1)
- Software Performance Engineering (1)
- Software Performance Modeling (1)
- anomaly detection (1)
- anomaly prediction (1)
- ant-colony optimization (1)
- encryption (1)
- failure prediction (1)
- genetic algorithm (1)
- intelligent transportation systems (1)
- logistics (1)
- multirotors (1)
- multiscale encoder (1)
- performance prediction (1)
- quadcopters (1)
- real-world application (1)
- rich vehicle routing problem (1)
- secure group communication (1)
- self-adaptive systems (1)
- sentinel (1)
- surface model (1)
- survey (1)
- taxonomy (1)
- unmanned aerial vehicles (1)
Institute
- Institut für Informatik (6) (remove)
In recent history, normalized digital surface models (nDSMs) have been constantly gaining importance as a means to solve large-scale geographic problems. High-resolution surface models are precious, as they can provide detailed information for a specific area. However, measurements with a high resolution are time consuming and costly. Only a few approaches exist to create high-resolution nDSMs for extensive areas. This article explores approaches to extract high-resolution nDSMs from low-resolution Sentinel-2 data, allowing us to derive large-scale models. We thereby utilize the advantages of Sentinel 2 being open access, having global coverage, and providing steady updates through a high repetition rate. Several deep learning models are trained to overcome the gap in producing high-resolution surface maps from low-resolution input data. With U-Net as a base architecture, we extend the capabilities of our model by integrating tailored multiscale encoders with differently sized kernels in the convolution as well as conformed self-attention inside the skip connection gates. Using pixelwise regression, our U-Net base models can achieve a mean height error of approximately 2 m. Moreover, through our enhancements to the model architecture, we reduce the model error by more than 7%.