Deutsch
 
Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
  Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben
Zeitschriftenartikel

Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images

Urheber*innen

Barz,  Björn

/persons/resource/kschroet

Schröter,  Kai
4.4 Hydrology, 4.0 Geosystems, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/mmuench

Münch,  Moritz
4.4 Hydrology, 4.0 Geosystems, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/yang

Yang,  B.
1.4 Remote Sensing, 1.0 Geodesy, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/unger

Unger,  A.
1.4 Remote Sensing, 1.0 Geodesy, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/dransch

Dransch,  D.
1.4 Remote Sensing, 1.0 Geodesy, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

Denzler,  Joachim

Externe Ressourcen
Es sind keine externen Ressourcen hinterlegt
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte in GFZpublic verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Barz, B., Schröter, K., Münch, M., Yang, B., Unger, A., Dransch, D., Denzler, J. (2018): Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images. - Archives of Data Science. Series A, 5, 1, A06.
https://doi.org/10.5445/KSP/1000087327/06


Zitierlink: https://gfzpublic.gfz-potsdam.de/pubman/item/item_5001225
Zusammenfassung
The analysis of natural disasters in a timely manner often suffers from limited sensor data. This limitation could be alleviated by leveraging information contained in images of the event posted on social media platforms, so-called “Volunteered Geographic Information (VGI)”. To save the analyst from manual inspection of all images posted online, we propose to use content-based image retrieval with the possibility of relevance feedback for retrieving only relevant images of the event. To evaluate this approach, we introduce a new dataset of 3,710 flood images, annotated by domain experts regarding their relevance with respect to three tasks (determining the flooded area, inundation depth, water pollution). We compare several image features and relevance feedback methods on that dataset, mixed with 97,085 distractor images, and are able to improve the precision among the top 100 results from 55% to 87% after 5 rounds of feedback.