Vol. 13, No. 2, 77-84, 2014

Building detection with multi-view colour infrared imagery
Charles Beumier, and Mahamadou Idrissa

Abstract
This paper presents an automatic building detection approach exploiting colour infrared (CIR) imagery. A Digital Surface Model (DSM) is first extracted by photogrammetry with a proprietary development including multiple views. Then a Digital Terrain Model (DTM) is derived from the DSM by selecting the lowest regions with slowly varying elevation. A normalised DSM, difference of the DSM and derived DTM highlights building candidates thanks to a simple threshold. In order to reduce false positives due to trees, a vegetation mask is obtained from the NDVI of the ortho-rectified CIR image. A specific procedure was designed to handle the problematic shadow areas where the NDVI criterion often misses vegetation.

The proposed building detection approach has been applied to the Vaihingen data set of the ISPRS benchmark and validated by the results of its evaluation procedure. We plan to integrate the new DTM extraction and shadow adapted vegetation mask, main contributions of this paper, to our project about change detection for database revision for the Belgian National Geographic Institute.

View Full Text (pdf file, 3.4 MB)                  Figure 2
(jpg file, 750 kB)
     Figure 3
(jpg file, 1 MB)
     Figure 4
(jpg file, 1.5 MB);
previous page
DOI: 10.12760/01-2014-2-05

History
Submitted: 28 Aug 2014
Revised: 05 Nov 2014
Accepted: 17 Nov 2014
Published: 25 Nov 2014
Responsible editor: Christoph A Hecker

Citation
Beumier, C & M Idrissa, 2014. Building detection with multi-view colour infrared imagery. EARSeL eProceedings, 13(2): 77-84
EARSeL-logo

EARSeL European Association of Remote Sensing Laboratories, Strasbourg, France

   
BIS-logo

BIS-Verlag
BIS Library and Information System, Carl von Ossietzky University of Oldenburg

   
Scopus-logo

Indexed in Scopus

   
DOAJ logo

DOAJ
Directory of Open Access Journals

   
SPERPA/RoMEO logo

SHERPA/RoMEO
Opening access to research

Creative Commons License

ISSN 1729-3782