Towards Better Land Cover Classification Using Geo-Tagged Photographs

Hirotaka Oba Masaharu Hirota Richard Chbeir 1 Hiroshi Ishikawa 2 Shohei Yokoyama 3
1 LIUPPA - Laboratoire Informatique de l'Université de Pau et des Pays de l'Adour
2 Graduate School of Engineering [Tokyo]
3 University of Shizuoka
Abstract : A land cover map that represents the land surface of the earth is based primarily on analysis of remotely sensed images. However, the rate of concordance of existing land cover maps is not high. This lack of concordance results from a difference in classification methods and observation conditions of remotely sensed images. Also, conducting field surveys around the world is unrealistic. Therefore, we use ground level photographs from photo-sharing sites instead of field surveys. We propose a method to classify areas into land cover types using image features, geo-tags, titles and tags. Additionally, we create the land cover map using classified photographs. We evaluate the method using ground truth created manually. Results show that the accuracy of the proposed method is about 70 percent in New York. \textcopyright 2014 IEEE.
Type de document :
Communication dans un congrès
2014 IEEE International Symposium on Multimedia, ISM 2014, Taichung, Taiwan, December 10-12, 2014, 2014, Unknown, Unknown Region. IEEE, pp.320-327, 2014, 〈10.1109/ISM.2014.78〉
Liste complète des métadonnées
https://hal-univ-pau.archives-ouvertes.fr/hal-01912905
Contributeur : Gaelle Chancerel <>
Soumis le : lundi 5 novembre 2018 - 17:32:51
Dernière modification le : mercredi 19 décembre 2018 - 11:38:36

Identifiants

Collections

LIUPPA

Citation

Hirotaka Oba, Masaharu Hirota, Richard Chbeir, Hiroshi Ishikawa, Shohei Yokoyama. Towards Better Land Cover Classification Using Geo-Tagged Photographs. 2014 IEEE International Symposium on Multimedia, ISM 2014, Taichung, Taiwan, December 10-12, 2014, 2014, Unknown, Unknown Region. IEEE, pp.320-327, 2014, 〈10.1109/ISM.2014.78〉. 〈hal-01912905〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

8

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD