AGNES -
Lehre und Prüfung online
Studierende in Vorlesung
Anmelden

Deep Learning for Landcover Classification - Detailseite

  • Funktionen:
  • Online Belegung noch nicht möglich oder bereits abgeschlossen
Grunddaten
Veranstaltungsart Seminar Veranstaltungsnummer 3313098
Semester WiSe 2020/21 SWS 2
Rhythmus Moodle-Link  
Veranstaltungsstatus Freigegeben für Vorlesungsverzeichnis  Freigegeben  Sprache deutsch
Belegungsfristen - Eine Belegung ist online erforderlich Zentrale Nachfrist    02.11.2020 - 05.11.2020   
Zentrale Frist    01.07.2020 - 28.10.2020   
Veranstaltungsformat Digital

Termine

Gruppe 1
Tag Zeit Rhythmus Dauer Raum Raum-
plan
Lehrperson Status Bemerkung fällt aus am Max. Teilnehmer
Fr. 09:00 bis 11:00 Block Johann von Neumann-Haus - 3.113 Rudower Chaussee 25 (RUD25) - (Unterrichtsraum) Ghamisi findet statt   06.11.2020: First Session 16
Gruppe 1:
Zur Zeit keine Belegung möglich


Zugeordnete Person
Zugeordnete Person Zuständigkeit
Ghamisi, Pedram
Studiengänge
Abschluss Studiengang LP Semester
Master of Education (ISG)  Informatik 1. Fach ( Vertiefung: mit LA-Option; POVersion: 2018 )   -  
Master of Education (BS)  Informatik 2. Fach ( Vertiefung: mit LA-Option; POVersion: 2015 )   -  
Master of Education (GYM)  Informatik 2. Fach ( Vertiefung: mit LA-Option; POVersion: 2015 )   -  
Master of Education (ISG)  Informatik 2. Fach ( Vertiefung: mit LA-Option; POVersion: 2018 )   -  
Master of Science  Informatik Hauptfach ( Vertiefung: kein LA; POVersion: 2015 )   -  
Zuordnung zu Einrichtungen
Einrichtung
Mathematisch-Naturwissenschaftliche Fakultät, Institut für Informatik
Inhalt
Kommentar

The number of data produced by sensing devices has increased exponentially in the last few decades, creating the “Big Data” phenomenon, and leading to the creation of the new field of “data science”, including the popularization of “deep learning” algorithms to deal with such data. In the field of remote sensing, the number of platforms for producing remotely sensed data has similarly increased, with an ever-growing number of satellites in orbit and planned for launch, and new platforms for proximate sensing such as unmanned aerial vehicles (UAVs). Fortunately, the increase in the number and heterogeneity of data sources (presenting both challenge and opportunity) has been paralleled by increases in computing power, by efforts to make data more open, and by advances in methods for landcover classification and data fusion. Deep learning has been used intensively in the remote sensing community for landcover classification using both single and multisensory data.

In this seminar, groups of students will each present an approach in lecture and elaboration by emphasizing the use of deep learning for landcover classification from the perspectives of single and multisensorytechniques. Students also apply a number of deep learning-based classifiers on real satellite images. For this purpose, we will distribute a proper amount of codes among the students for benchmarking and evaluation.

Bemerkung

The seminar takes place essentially as a block seminar at the end of the semester. Before that, however, introductory appointments and individual topic meetings must be attended. Teams of two students may be formed for the topics.

The approx. dates:

1) Early December - 10-minute presentations per group
2) Early February - block seminar
3) Late February (27.02.2021) - Submission of the seminar paper
 
The seminar will be given in English.

Strukturbaum

Die Veranstaltung wurde 1 mal im Vorlesungsverzeichnis WiSe 2020/21 gefunden:

Humboldt-Universität zu Berlin | Unter den Linden 6 | D-10099 Berlin