Improved classification of satellite imagery using spatial feature maps extracted from social media

Show simple item record

dc.identifier.uri http://dx.doi.org/10.15488/4071
dc.identifier.uri https://www.repo.uni-hannover.de/handle/123456789/4105
dc.contributor.author Leichter, Artem
dc.contributor.author Wittich, Dennis
dc.contributor.author Rottensteiner, Franz
dc.contributor.author Werner, Martin
dc.contributor.author Sester, Monika
dc.date.accessioned 2018-11-30T10:09:38Z
dc.date.available 2018-11-30T10:09:38Z
dc.date.issued 2018
dc.identifier.citation Leichter, A.; Wittich, D.; Rottensteiner, F.; Werner, M.; Sester, M.: Improved classification of satellite imagery using spatial feature maps extracted from social media. In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives 42 (2018), Nr. 4, S. 403-410. DOI: https://doi.org/10.5194/isprs-archives-XLII-4-335-2018
dc.description.abstract In this work, we consider the exploitation of social media data in the context of Remote Sensing and Spatial Information Sciences. To this end, we explore a way of augmenting and integrating information represented by geo-located feature vectors into a system for the classification of satellite images. For that purpose, we present a quite general data fusion framework based on Convolutional Neural Network (CNN) and an initial examination of our approach on features from geo-located social media postings on the Twitter and Sentinel images. For this examination, we selected six simple Twitter features derived from the metadata, which we believe could contain information for the spatial context. We present initial experiments using geotagged Twitter data from Washington DC and Sentinel images showing this area. The goal of classification is to determine local climate zones (LCZ). First, we test whether our selected feature maps are not correlated with the LCZ classification at the geo-tag position. We apply a simple boost tree classifier on this data. The result turns out not to be a mere random classifier. Therefore, this data can be correlated with LCZ. To show the improvement by our method, we compare classification with and without the Twitter feature maps. In our experiments, we apply a standard pixel-based CNN classification of the Sentinel data and use it as a baseline model. After that, we expand the input augmenting additional Twitter feature maps within the CNN and assess the contribution of these additional features to the overall F1-score of the classification, which we determine from spatial cross-validation. eng
dc.language.iso eng
dc.publisher London : International Society for Photogrammetry and Remote Sensing
dc.relation.ispartof ISPRS TC IV Mid-Term Symposium on 3D Spatial Information Science - The Engine of Change, 1–5 October 2018, Delft, The Netherlands
dc.relation.ispartofseries International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives 42 (2018), Nr. 4
dc.rights CC BY 4.0
dc.rights.uri https://creativecommons.org/licenses/by/4.0/
dc.subject Classification eng
dc.subject Data fusion eng
dc.subject Deep learning eng
dc.subject Satellite images eng
dc.subject Social media mining eng
dc.subject Data fusion eng
dc.subject Deep learning eng
dc.subject Image classification eng
dc.subject Image enhancement eng
dc.subject Image fusion eng
dc.subject Neural networks eng
dc.subject Remote sensing eng
dc.subject Satellite imagery eng
dc.subject Social networking (online) eng
dc.subject Trees (mathematics) eng
dc.subject Convolutional Neural Networks (CNN) eng
dc.subject Integrating information eng
dc.subject Satellite images eng
dc.subject Social media datum eng
dc.subject Social media minings eng
dc.subject Spatial cross validations eng
dc.subject Spatial features eng
dc.subject Spatial information science eng
dc.subject Classification (of information) eng
dc.subject.ddc 550 | Geowissenschaften ger
dc.title Improved classification of satellite imagery using spatial feature maps extracted from social media
dc.type article
dc.type Text
dc.relation.issn 1682-1750
dc.relation.doi https://doi.org/10.5194/isprs-archives-XLII-4-335-2018
dc.bibliographicCitation.issue 4
dc.bibliographicCitation.volume 42
dc.bibliographicCitation.firstPage 403
dc.bibliographicCitation.lastPage 410
dc.description.version publishedVersion
tib.accessRights frei zug�nglich


Files in this item

This item appears in the following Collection(s):

Show simple item record

 

Search the repository


Browse

My Account

Usage Statistics