! objects
' feature
ures the
k-means
'esult of
bility of
pendent
tion are
lermore,
textural
ads to a
lamaged
ecreases
etection
e main
ty and
building
t cannot
ition of
sible to
thereby
inges in
ubset of
od. Red
ntact
oftware
ata sets
id data
graphic
teler &
| among
the Open Source geographic information systems and provides
an access to over 500 modules for manipulation with 2d and 3d
raster and vector data. Its functionality can be expanded by the
creation of new modules using different programming
languages (Python, C, C++, MATLAB).
The algorithms for calculation of Detected Part of Contour
(DPC) and textural features are written in Python
(www.python.org). The algorithm for the Canny edge detection
is implemented using Python Image Library and OpenCV
Python Library. The programs are integrated as GRASS GIS
modules.
The Open Source machine learning system Orange (Boulicaut,
2004) is used for data analysis, classification and visualization.
6. CONCLUSION
In this paper, we presented a change detection methodology for
buildings that is based on the combined analysis of two
different data types — remotely sensed image and vector
information. The integrated analysis enables the investigation of
both, the building contour integrity and the area inside the
contour. In our study, we developed a new feature DPC for
assessment of the building contour integrity. Calculation of
textural features is based on the Haralick features which have
been adapted to the GIS requirements. Consequently, our
research contributes to the integration of remote sensing and
GIS technologies.
Despite of the promising result of the building condition
classification, future studies of different cases may require the
use of more sophisticated classification techniques than the
employed clustering approach. In the future, investigations will
focus on solving the identified classification problems that can
reveal new features and improve further experimental results.
REFERENCES
Boulicaut, J.-F., 2004. Orange: from experimental machine
learning to interactive data mining. PKDD, LNAI(3202), pp.
537-539.
Centeno, S., Jorge, 2000. Integration of satellite imagery and
GIS for land-use classification purposes. International Archives
of Photogrammetry and Remote Sensing, XXXIII(B7).
Chesnel, A.-L., Binet, R.,Wald L., 2007. Damage assessment on
buildings using very high resolution multitemporal images and
GIS. 5-th International Workshop on Remote Sensing for
Disaster Management Applications.
Delac, K., Grgic, M., Kos, T., 2006. Sub-image homomorphic
filtering technique for improving facial identification under
difficult illumination conditions. International Conference on
Systems, Signals and Image Processing. Budapest, Hungary,
Sept. 21-23.
Ehlers, M., Edwards, G., Y. Bedard, 1989. Integration of remote
sensing with geographic information systems: a necessary
evolution. Photogrammetric engineering and remote sensing,
55(11), pp. 1619-1627.
Gonzalez, R.C., Woods, R.E, 2002. Digital Image Processing.
Prentice Hall, New Jersey, p.793.
Haralick, R.M., Shanmugam, K., Its'hak, D., 1973. Textural
features for image classification. IEEE Trans. on Systems, Man
and Cybernetics, SMC-3(6), pp. 610-621.
Lo, C.P., Shipman, R.L., 1990. A GIS approach to land-use
change dynamics detection. Photogrammetric engineering and
remote sensing, 56(11), pp. 1483-1491.
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
Li, D., 2009. Remotely sensed images and GIS data fusion for
automatic change detection. International Journal of Image and
Data Fusion, 1(1), pp. 99-108.
Mattikalli, N.M., 1995. Integration of remotely-sensed raster
data with vector-based geographical information system for
land-use change detection. International Journal of Remote
Sensing, 16(15), pp. 2813-2828.
Neteler, M., Mitasova, H., 2004. Open Source GIS: A GRASS
GIS Approach. Second Edition. Kluwer | Academic
Publishers/Springer, Boston, p. 419.
Samadzadegan, F., Rastiveisi H., 2008. Automatic detection and
classification of damaged buildings, using high resolution
satellite imagery and vector data. The International Archives of
the Photogrammetry, Remote Sensing and Spatial Information
Sciences, XXXVII(B8), pp. 415-420.
Sofina, N., Ehlers, M., Michel, U., 2011. Object-based detection
of destroyed buildings based on remotely sensed data and GIS.
Earth Resources and Environmental Remote Sensing/GIS
Applications II. Proc. of SPIE 8181.
Weng, Q., 2002. Land use change analysis in the Zhujiang Delta
of China using satellite remote sensing, GIS and stochastic
modeling. Journal of Environmental Management, 64, pp. 273-
284.
http://grass.osgeo.org/
www.python.org/
www.pythonware.com/
http://opencv.willowgarage.com/documentation/python/index.ht
ml
ACKNOWLEDGEMENTS
This work uses Open Source software components such as
GRASS GIS, Python programming language and Orange data
mining software. The authors would like to thank the
development teams for providing and supporting the software.
The authors are also grateful to Digital Globe for providing the
image data, which made our investigation possible. Special
thanks go to the referees for their careful review and valuable
comments that helped to improve the paper.
