Object-oriented image analysis

Lecturer

Michael Wurm

ECTS

5 ECTS

 

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

Coding examples and individual work will be covered

Software

Various software programs will be used, but mainly OpenSource software such as R.

Techniques

Different techniques will be introduced and practically applied.
w

Content

The content of scientific with regard to the audience will be discussed.

General Course News and Updates

MSc defense by Frederic Schwarzenbacher

MSc defense by Frederic Schwarzenbacher

Frederic Schwarzenbacher will defend his M.Sc. thesis on Monday 6th at 3pm. The title is "Habitat suitability modeling for Desert Locust in the Awash River basin: Estimation of the breeding probability based on remote sensing, climatology and environment data" and...

read more
MSc defense by Belen Villacis

MSc defense by Belen Villacis

Belen will defend her M.Sc. thesis “Spatio-temporal patterns of urban expansion among main biomes in Ecuador using LULC data from 1990-2018” on Wednesday 8th of September, 2pm. From the abstract: "Over the past decades, the world has experienced an accelerated...

read more
MSc defense by Ronja Lappe

MSc defense by Ronja Lappe

Ronja Lappe handed in her M.Sc. thesis "Assessing 30 years of coastline dynamics in Vietnam using the Landsat archive"from the abstract: "Almost half of the world’s human population lives in coastal regions, with 40 % less than ten meters above sea level. Due to...

read more
MSc defense by Martin Koenig

MSc defense by Martin Koenig

Martin König handed in his thesis with the title “Examining post-fire vegetation recovery with Landsat time series analysis in Olympic National Park (USA)”. Martin used remote sensing and ground collected data to make sense of vegetation recovery patterns for larger...

read more
thesis idea presentations

thesis idea presentations

On Monday 26th of July at 2pm we will have two MSc thesis idea presentations:   Jakob Wachter (thesis idea):"Derivation of Snow cover in mountain regions from Webcam and Sentinel Imagery (thesis idea)" - supervisors Dr. Tobias Ullmann and Dr. Mattia Rossi, EURAC...

read more
MSc Defense by Sandro Groth

MSc Defense by Sandro Groth

Sandro Groth will present his M.Sc. thesis "Using street-level imagery and multi-task deep learning for multi-hazard risk related building characterization" on June 28th at 9am. From his abstract: "Accurate building characterization is a key component of multi-hazard...

read more
MSc defense by Henrik Fisser

MSc defense by Henrik Fisser

Henrik Fisser will present his M.Sc. thesis on Thursday 17th of June at 9am about “Sentinel-2-based moving truck detection for spatiotemporal road cargo emission and density approximation”. More details from his abstract: "In many countries freight is mainly...

read more