Institutional Repository of Vilnius University
Spatial-Temporal change detection in satellite imaging-monitoring /
Abstract
dc:descriptionIn this master thesis, satellite imagery and change detection analyzed and by using different deep learning techniques. The first experiment was a UNet-like semantic segmentation paired with vector autoregression for spatial-temporal change analysis, and the second experiment employs CLIP-based zero-shot classification to effectively detect changes without the need for extensive labeling. Additionally, caption based change classification done which these captions generated using Llama model. The work further investigates the use of the MiniCPM-V model for satellite image recognition across diverse dataset. Finally, an innovative pipeline that integrates fine-tuned Stable Diffusion and our trained CycleGAN models is introduced to unify heterogeneous datasets merging captions, RGB images, and multispectral Sentinel-2 datathereby generating synthetic multispectral imagery.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Komurcu, Kursat,
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- eng
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD238881035&prefLang=en_US