direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

WS 19/20 - Machine Learning for Remote Sensing Data Analysis

Information
Typ
Seminar
Duration
one Semester
SWS/Credits Points (ECTS)
2 SWS/3 ECTS
Contact
sekr@rsim.tu-berlin.de
Language
English
Participants
16
Date
Fridays 10:00 - 12:00
Room
EN 719
(first lecture in HFT-TA 441)

Announcements

 The first lecture will be given on October,18th at 10 @ HFT-TA 441. 

Registration

Please register for the course in ISIS.

Learning Outcomes

Participants of this seminar will acquire knowledge on advanced methodologies for the analysis of remote sensing images acquired by the last generation Earth observation satellite systems. In particular, this seminar course will provide students on the one hand an in-depth theoretical and practical knowledge on remote sensing image analysis; and on the other hand a know-how in one or more domains of applications, such as land-cover maps generation, land-cover maps updating, biophysical parameter estimation, image search and retrieval, change detection. Moreover, the students will learn about the current developments in remote sensing and related data analysis methods, and how machine learning techniques can be employed to solve Earth observation questions.

Content

Remote sensing images are a rich information source for monitoring the Earth surface, e.g., for climate change analysis, urban area studies, forestry applications, risk and damage assessment, water quality assessment, crop monitoring. Due to the recent developments in both passive multispectral and hyperspectral sensors, and synthetic aperture radar active instruments, the role of this technology is becoming more and more important for understanding the dynamics of our planet. To efficiently process/analyze the data, remote sensing has evolved into a multidisciplinary field, where machine learning algorithms play an important role nowadays. In this seminar, students will review the current state of the art in the field of machine learning applied to remote sensing image analysis in the framework of different Earth observation applications. The general topics include but are not limited to:

  • feature selection and extraction;
  • supervised, unsupervised, semi-supervised classification and regression,
  • deep learning,
  • active learning,
  • structured learning,
  • transfer learning and domain adaptation with applications to remote sensing image analysis.

Description of Teaching and Learning Methods

At the beginning of the semester there will be overview lectures that will provide some background concepts on remote sensing, different types of remote sensing images and the general remote sensing image processing/analysis chain. In addition, a set of primary literature works will be provided. Then, the students will further investigate the topics assigned to them in the seminar. A few weeks after they will give a short presentation of approx. 10 minutes (based on their initial understandings on the considered topic) that will be open to all seminar participants. In the further course of the semester the students will give a final presentation of approx. 30 minutes. In addition to the talk the students will also prepare a technical report with 10-15 pages describing their topic.

Recommended literature

  • G. Camps-Valls, and L. Bruzzone, Kernel methods for Remote Sensing Data Analysis, Wiley & Sons 2009
  • L. Bruzzone, B. Demir, A Review of Modern Approaches to Classification of Remote Sensing Data, in Land Use and Land Cover Mapping Europe, Practices and Trends, Eds: I. Manakos, M. Braun, EARSeL Book Series, Springer Verlag, Chapter 9, 2014, pp. 127-143.
  • E. Alpaydin, Introduction to Machine Learning, MIT Press, Cambridge, Massachusetts, London, England, 2004.

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Head of Chair

Prof. Dr. Begüm Demir
Phone: +49 30 314 23771
Room E-N 627

Administration

Sara Tennstedt
Room E-N 628
Phone +49 30 314 21418

availability by phone
only during office hour

Thursday
10:00 - 12:00

Address

Technische Universität Berlin
Remote Sensing Image Analysis (RSiM) Group
sec. EN 5, 6th floor
Einsteinufer 17
D-10587 Berlin