The course places particular emphasis on the applications of remote sensing in the terrestrial environment. The various techniques for detecting and monitoring land cover changes are a central theme. The objective of this course is twofold: first, to comprehend the theoretical concepts, and second, to apply that knowledge in practical settings by utilizing open-source and open-data software.
Upon completing this course, students will be able to:
– Understand the practical applications and value of remote sensing
– Use remote sensing software and the R statistical language.
– Make good decisions when selecting, processing, and producing information from digital images.
-Review of basic concepts and techniques of remote sensing.
-Classification of satellite images using advanced machine learning techniques (e.g., random forest).
-Accuracy estimation.
-Land cover change analysis techniques (cross-classification and time-series analysis)
-Image segmentation and object classification techniques (OBIA).
-Techniques for enhancing the spatial resolution of multispectral images (e.g., image reconstruction using higher spatial resolution images,
PanSharpening and image fusion.
-Image processing in cloud environments (e.g., Google Earth Engine).
-Various applications in the terrestrial environment, such as urban sprawl and green distribution.
Project based assignments 1-3 (100%)
Resit: 100% written examination
Pedion Areos, 383 34, Volos
+30 24210 74452-55
+30 24210 74380
g-prd@prd.uth.gr