High-resolution aerial imagery plays a critical role in urban planning, energy mapping, and land-use classification. However, many datasets remain limited to lower resolutions due to acquisition costs or legacy data sources. Super-resolution (SR) techniques offer a means to enhance 25 cm aerial imagery to 8 cm, making it more suitable for object-level analysis. This thesis investigates the capability of a modified SRGAN architecture to enhance the visual and structural fidelity of aerial images, thereby improving the representation of urban features such as rooftops, dormers, and solar panels. The architecture incorporates an EdgeMaskBlock to improve edge awareness and preserve sharp contours in reconstructed imagery. To address the challenges of spatial complexity and temporal misalignment, a two-phase training strategy is implemented. First, the model is trained on synthetically downsampled HR-LR pairs to establish a robust initialization. This is followed by fine-tuning on real-world 25 cm inputs mis- aligned with their 8 cm HR counterparts, enabling the model to generalize under realistic and variable acquisition conditions. Evaluation is conducted across both training iterations using standard image quality metrics (PSNR, SSIM, LPIPS), along with downstream segmentation benchmarks. For Iteration 2, the gen- eralization capability of the model is assessed across new cities and seasonal conditions. Two segmen- tation pipelines are used: the Segment Anything Model (SAM) and the operational semantic segmen- tation system developed by Readar B.V., which detects buildings, dormers, and PV panels using both RGB and DSM data. Metrics such as precision, recall, and F1-score demonstrate that super-resolved outputs significantly outperform bicubic upsampling, particularly for fine-scale rooftop objects. The results show that the proposed SRGAN model improves perceptual quality while enabling effective domain transfer across seasons. These enhancements contribute to more reliable segmentation outputs, reinforcing the potential of GAN-based super-resolution as a practical tool in geospatial workflows that require fine-grained object recognition. ... Read more

This study explores the effectiveness of Virtual Reality (VR) compared to the use of 2D interfaces in interpreting point cloud data, focusing on user perception, interaction and relative measurement accuracy. Visualizing point clouds is often challenging due to the limitations in translating three-dimensional data into two-dimensional screens. VR offers a potential solution to enhance depth perception and deepen user understanding. The research utilizes Omnibase, a platform developed by Geodelta, that integrates various spatial data types, including point clouds, for applications such as municipal boundary measurements.

The study involved participants that are either familiar or unfamiliar with point clouds, to evaluate VR versus Omnibase. Quantitative measurements and qualitative feedback were collected on either platform. Results indicate that while VR provides better depth perception and a more immersive experience, it presents a steeper learning curve, especially for inexperienced users, additionally, it comes with physical side effects. The measurements in Omnibase showed higher consistency, though not necessarily greater accuracy, due to depth misinterpretations.

In addition to the study, the VR testing environment was developed using Potree. ... Read more