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
M.Sc. defense by Michael Wang
Michael Wang will present his thesis "Comparison of Surface Urban Heat Islands Using the World Settlement Footprint Imperviousness Layer" on Sept. 17th at 10am. From the abstract: "In the growing field of surface urban heat island (SUHI) analysis, impervious surface...
MSc. presentation by Fowad Ahmed
Fowad Ahmed will present his M.Sc. thesis "Agricultural landscape Configuration and Pattern Analysis with VHR Imagery in Bavaria" on Friday 11th at 11am. from the abstract: "Hedgerows and woody linear features are an integral part of the landscapes where they exist....
M.Sc. defense by Nina Gnann
Nina Gnann will present her M.Sc. thesis "Identification of anthropogenic debris assisted by unmanned aerial vehicles and deep learning” on September 8th 12pm. From the abstract: Due to anthropogenic actions, plastic and other debris are distributed in the environment...
MSc thesis presentations by Navid Chamani
Navid Chamani is defending his thesis "Investigation on the intra-annual variations of the relationship between Landsat 8-derived LST and spectral indices in west Africa" on September 25th 10am. from the abstract: "Monitoring the variations of the land surface...
MSc defense by Salim Soltani
Selected map of NSR and non_NSR cities from 1990-2019, NSR cities represent the cities located directly on the New Silk Road , and non_NSR cities represent cities located far from( at least 100 Km) the New Silk Road. Salim Soltani will defend his M.Sc. thesis...
New EAGLEs in 2020
we are finally through all 140 interviews of eligible EAGLE applications. We had again very good and highly suitable candiates and in total 25 applicants passed the interviews and are accepted to the EAGLE program. Our new EAGLEs are from various countries (15...
M.Sc. Defense by Felix Glasmann
Felix Glasman will defend his M.Sc. thesis "The FireBIRD Mission: Potential for the Detection of Gasflaring" on Thursday 30th of July at 11am. From his abstract: "The controversial but widespread process of gas flaring has received growing attention over the recent...
Internship presentations
On Thursday 30th at 10 am the following EAGLE students will present their internships or inno labs: Tobias Gutzmann: 'Aerial Image Analysis for WW2 Warfare Material Detection' at Luftbilddatenbank Henrik Fisser: 'Sentinel-2 Truck Detection - Sensing Trade from Space...
EAGLE student Henrik Fisser won ESA competition
Congratulations to Henrik Fisser, whose Sentinel-2 analysis on truck detection has been awarded the first prize for the European Data Cube COVID-19 contest! He uses the reflectance patterns of long moving vehicles in Sentinel-2 images. Please see the ESA webpage for...
MSc defense by Katrin Hasenbein
Katrin Hasenbein will defend her M.Sc. thesis on Thursday 12am on "The potential to enhance land use mapping by leveraging processing methods of time series data". from the abstract: "With the launch of the twin satellites of Sentinel-2 time series data with a high...