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
Inno lab and MSc idea presentation
On Friday 8th of April from 9am onwards we will have the following EAGLE presentations: "Assessment of open-source street-level imagery for building classification in Lima, Peru" by Larissa Gorzawski (Inno lab supervised by Hannes Taubenböck and Christian Geiß)...
MSc idea and inno lab presentations
On Friday 11th of March from 10am onwards the following students will introduce their MSc idea or report on their innovation laboratory: Kemeng Liu (MSc idea): "Mapping Spatial-Temporal Developments of Coastal Aquaculture" supervised by Tobias Ullmann Antonio...
MSc defense by Sofia Garcia
On Friday, March 11th at 9am Sofia will present her M.Sc. thesis "Estimating socioeconomic variables in Bolivia using satellite-based nighttime light images and electricity consumption data". From the abstract: "The lack of up-to-date data on socio-economic parameters...
MSc thesis defense by Nestor Gualsaqui
On March 8th at 10:30 Nestor will present his M.Sc. thesis "Pre-crop emergence weed mapping using high satellite imagery". From the abstract: "During the last decades, the growth of the world population has been increasing and weather fluctuations around the world...
MSc defense Nils Karges
Nils Karges will present his M.Sc. thesis "Exploring spatial relationships of soundscape variables in urban areas. " on 15th of February at 9:30. From the abstract: "This work describes the relationship between soundscape and the underlying landscape in an urban...
MSc defense Camilo Zamora
On Friday 11th of February at 9am Camilo Zamora will present his M.Sc. thesis "Deforestation dynamics in the Dry Chaco ecoregion: a three decades of change detection and fragmentation study analysis". From the abtract: "Tropical forests represent 52% of global forests...
MSc idea and interesting presentations
on Friday 18th of February at 9am we will have the following presentations: Jakob Rieser - Thesis Idea: "A Synergistic Use of Optical and SAR Remote Sensing Data for the Long-term Evolution of Biocrusts and their Activity across diverse Dryland Ecosystems"....
Internship, inno lab and MSc. idea
On Monday 17th of January at 9am we will have the following presentations: Luisa Pflumm (MSc. idea presentation): "Assess silver-backed chevrotaindistribution in Nui Chua NP (Vietnam).", supervisors: Insa Otte, Andreas Wilting (IZW) Christopher Chan (Msc. idea...
Our EAGLEs featured on the University page
Our EAGLEs Sofia, Annika, Antonio, Andreas and Nils are featured on the University webpage with their UrbanSens idea of combining mobile IoT sensors and Earth Observation data for urban climate monitoring. Their success winning the DLR Copernicus challenge rewarded...
MSc defense by Yomna Eid
Yomna will present her M.Sc. thesis "Assessment of ESA CCI+ and NASA MODIS-LST in Ecological Transects of Australia" on January 14th 2022 at 10am. From the abstract: "Identifying the best-performing MODIS LST products available for scientific analysis is instrumental...