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
MSc Defense by Nora Nieskens
MsC Defense by Nora Nieskens On Friday, September 08, 2023 at 11 a.m. Nora Nieskens will present her Msc Thesis “Estuaries in transition: Earth observation-based analysis of the turbidity dynamics in selected North Sea estuaries” in room 00.B.09 in John-Skilton-Str....
Detection of slope deformation at the Tröllaskagi peninsula, N-Iceland, using Sentinel-1 DInSAR time series
MSc defense (MA2) by Ása Dögg Adalsteinsdóttir On Monday, September 18, 2023 Ása Dögg Adalsteinsdóttir will present her Msc Thesis at 14:00 Detection of slope deformation at the Tröllaskagi peninsula, N-Iceland, using Sentinel-1 DInSAR time series Thema: MSC...
MSc defense by Vanessa Rittlinger
On Tuesday, October 24, 2023 at 10:00 a.m. Vanessa Rittllinger will present her master thesis on “Detection of landslides in space and time using optical remote sensing data – A case study in South Tyrol” in the conference room 01.B.03 in John-Skilton-Str. 4a/1st...
MSc defense and Inno-Lab presentations
On Tuesday 20th of December at 12am we will have various presentations MSc defense by Kevin Yomi on "Evaluation wildfire activity in conflict-affected areas using earth observation and panel regression models: a case study of Borno State, Nigera, from 2003-2020" In...
EAGLEs visit DLR EOC
After a long break due to covid we resumed the EAGLE visit of DLR EOC. Many EAGLEs from the current generation and quite some of the past (covid) generations joined this event and listened to many talks by DLR researchers. Some of the presenters were even former...
Social event in the boulder gym
Last week we spend a few hours in the boulder hall to enjoy a day without courses, do some climbing and have plenty of time to chat. Many EAGLEs from the current and old generations joint us as well as many lecturer. Beside the social event we also collected Lidar...
MSc defense Caroline Busse
On Tuesday 22nd of November at 1pm we will have the MSc thesis defense by Caroline on "Change Detection using Sentinel-1 and Sentinel-2 Time Series: A Comparison of Models for the Detection of Forest Disturbances." from the abstract: "Forests provide essential...
internship, innoLab and MSc idea presentations
On Tuesday 22nd of November at 12am we will have the following presentations: Dilara Kim: „Automated glacier snowline mapping from multi-sensor satellite observation“, InnoLab, EURAC Research, Supervisor: Dr. Martina Barandun Walid Ghariani: „PM2.5 Prediction Using...
New EAGLE Earth Observation professors
We are very happy to welcome two new professors within the EAGLE M.Sc. program! Prof. Dr. Hannes Taubenböck and Prof. Dr. Tobias Ullmann will strengthen the urban remote sensing and radar earth observation within the EAGLE program. Various new courses are already...
MSc defense by Larissa Gorzawski
On Wednesday 5th of October at 2pm Larissa will present her M.Sc. thesis "Deep transfer learning on street-level imagery for classification of seismic building types in Lima, Peru". From the abstract: "Comprehensive exposure models for seismic risk assessment require...