Characterizing and Counting Roofless Buildings in Very High Resolution Optical Images

Author

Gueguen, Lionel ; Pesaresi, Martino ; Gerhardinger, Andrea ; Soille, Pierre

Author_Institution

Inst. for the Protection & Security of the Citizen, Joint Res. Center of the Eur. Comm., Ispra, Italy

Volume

9

Issue

1

fYear

2012

Firstpage

114

Lastpage

118

Abstract

Roofless buildings are encountered in case of conflicts and disasters as well as construction sites. A methodology for characterizing and counting roofless buildings in very high resolution optical images is presented. Using morphological transform to extract specific image components, the proposed method spatially aggregates them in a fuzzy logic framework. The result is a map of roofless building membership. This membership map is then used with partial ground truth to estimate the total number of roofless buildings. Finally, the methods are validated with a WorldView panchromatic image, where the membership map and the counting estimate show good accuracies.

Keywords

disasters; feature extraction; fuzzy set theory; geophysical image processing; image resolution; object detection; terrain mapping; transforms; WorldView panchromatic image; building characterization; conflicts; construction site; disasters; fuzzy logic framework; image component extraction; morphological transform; roofless building counting; roofless building membership mapping; spatial aggregation; very high resolution optical image; Buildings; Image resolution; Optical imaging; Optical sensors; Pixel; Remote sensing; Satellites; Counting; crisis; detection; roofless buildings; very high resolution (VHR) image;

fLanguage

English

Journal_Title

Geoscience and Remote Sensing Letters, IEEE

Publisher

ieee

ISSN

1545-598X

Type

jour

DOI

10.1109/LGRS.2011.2161750

Filename

5975197