International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B3. Istanbul 2004
clustering technique. It presents an advantage in the sense that
there is no prior knowledge is needed for such learning
processes, i.e. data samples group themselves in terms of
similarity. We develop an interactive environment integrated a
SOM view, 2D and 3D views of the dataset, thus it facilities
detections of clusters associated with different spatial objects.
Despite the preliminary nature of the case study, it does
illustrate the powerfulness of unsupervised methods in general
and SOM in particular in extracting spatial objects from a laser-
scanning dataset. It is important to note that SOM training
process is much dependent on the parameter settings as reported
in table 1. This issue deserves further research, in particular in
terms of how the parameter settings have impact on the
extraction of spatial objects from a point cloud.
ACKNOWLEDGEMENTS
The author would like to thank Mikael Óstlund from the GIS
institute at the University of Gávle who provides the datasets
for the case study.
REFERENCES
Ackermanm, F. (1999). Airborne laser-scanning - present status
and future expectations. /SPRS Journal of Photogrammetry and
Remote Sensing, 54: 64-7.
Axelsson P. (1999), Processing of Laser Scanner Data —
Algorithms and applications, ISPRS Journal | of
Phtotogrammetry & Remote Sensing, 54, pp. 138 — 147.
Haala N. and Brenner C. (1999), Extraction of buildings and
trees in urban environments, /SPRS journal of photogrammetry
& remote sensing, 54, pp. 130 — 137.
Hojholt P. (1995). Generalization of build-up areas using
Kohonen-networks, Proceedings of Eurocarto XIII, 2-4
October, Ispra, Italy.
Jiang B. and Harrie L. (2003), Selection of streets from a
network using self-organizing maps, ICA Generalization
Workshop, Paris, 28 — 30 April 2003 (a revised version of this
paper is to appear in Transactions in GIS, Blackwell Publishers,
Vol. 8, No.3)
Jiang B. and Nakos B. (2003), Line simplification using self-
organizing maps, a working paper presented at /SPRS workshop
on spatial analysis and decision making, 3 — 5 December 2003,
Hong Kong.
Kohonen T. (2001), Self-Organizing Maps (third edition),
Springer, Berlin, Heidelberg, New York.
Kraus K. and Pfeifer N. (1998), Determination of terrain
models in wooded areas with airborne laser scanner data. /SPRS
Journal of Photogrammetry & Remote Sensing, 53:193-203.
Maas H. and Vosselman G. (1999), Two algorithms for
extacting building models from raw laser altimetry data, /SPRS
journal of photogrammetry and remote sensing, 54, pp. 153 —
163.
McIntosh K. and Krupnik A. (2002), Integration of laser-
derived DSMs and matched image edges for generating an
accurate surface model. /SPRS Journal of Photogrammetry &
Remote Sensing, 53(3):167-176.
Oja E. and Kaski S. (editors. 1999), Kohonen Maps, Elsevier.
Openshaw S., Blake M. and Wymer C. (1995), Using
Neurocomputing Methods to Classify Britain's Residential
Areas, (html paper), available at
http://www.geog.leeds.ac.uk/papers/95-1/ (accessed on
2002-11-15).
Openshaw, S. (1994), Neuroclassification of spatial data, in
Hewitson, B. C. and Crane, R. G. (eds) Neural Nets:
Applications in Geography, Dordrecht: Kluwer Academic
Publishers, 53-70.
Petzold B., Reiss P., and Stossel W. (1999), Laser-scanning -
surveying and mapping agencies are using a new technique for
the derivation of digital terrain models. ISPRS Journal of
Photogrammetry & Remote Sensing, 54(2-3):95-104.
Sithole G. and Vosselman G. (2003) Report: ISPRS
Comparison of Filters, Department of Geodesy, Faculty of
Civil Engineering and Geosciences, Delft University of
Technology, available at
http://Www.geo.tudelft.nl/frs/isprs/filtertest/Report05082003.pd
f (accessed on 2003-11-12)
Tao C. V, Hu Y. 2001: “A review of post-processing
algorithms for airborne LIDAR Data”. Proceedings ASPRS
conference April 23-27, 2001. St. Louis Missouri. CD-ROM, 14
pages.
Tobler W. R. (1970), A Computer Movie Simulating Urban
Growth in Detroit Region, Economic Geography, 46, pp. 234-
240.
Ultsch A. and Siemon H. P. (1990), Kohonen's self organizing
feature maps for exploratory data analysis, In Proc. INNC '90,
int. neural network conf, page 305-308, Dordrecht,
Netherlands, Kluwer.
Vesanto J. (1999), SOM-based data visualization methods,
Intelligent data analysis, Elsevier Science, Volume 3(2), pp.
111-126.
Vesanto J., Himberg J., Alhoniemi E. and Parhankangas J.
(2000), SOM toolbox for Matlab 5, Report A57, Helsinki
University of Technology, Libella Oy, Espoo.
Vosselman, G., 2000. Slope based filtering of laser altimetry
data, International Archives of Photogrammetry and Remote
Sensing, Volume XXXIII, Amsterdam, pp. 935-942.
TR
KEY W
ABSTR
A meth
capturec
is utilize
trunk. P
calculate
Special
analysec
measure
The met
has beer
tree cro
Utilising
obtained
top. Wit
method
The dev
in chars
and Ink
2001, Ni
the qual
digital t
hitting tl
angular
model ii
Pfeifer (
the acci
conditio
2000; A
with acc
Inkinen
tree-wise
retrieved
inventor
angular |
al. (2002
growth :
factors €
digital t
(2002). I
data anc
behaviot