Aim
In this course we will learn the alternative image analysis paradigm of object-based image classification. Image objects are areas in images which consist of pixels from the same land-cover class (e.g. buildings, water surfaces, vegetation) and allow the application of additional image classification methods in comparison to pure pixel-based methods and the integration of multi-modal date (e.g. vector data).
Content
In the course we will use satellite images and high resolution aerial images in combination with vector data and analyze various image classification methods (nearest neighbor -> random forests -> deep learning) to extract relevant information from the images.
We will use the software “eCognition”.
The course will be held on 3 days in Würzburg plus an introductory lecture which is being held online.
Session 1: getting to know to image objects and eConition software, basic classification methods
Session 2: advanced classification (Machine Learning)
Session 3: Deep Learning
Coding
Software
Techniques
Content
General Course News and Updates
Radiometric calibration, speckle reduction, geometric and terrain correction are essential preprocessing steps for SAR data. Within an innovation laboratory you will explore the different calibration and data preparation techniques for ground detected and single look...
Surface model creation from multi-source remote sensing data
Nowadays there are plenty of 3D data sources which offer the possibility to model and monitor structural attributes of the landscape via the derivation of terrain, surface and canopy models. The core idea of this research project within an innovation laboratory is to...