CMRT09: Object Extraction for 3D City Models, Road Databases and Traffic Monitoring - Concepts, Algorithms, and Evaluation
76
After this process, the correctness has been improved to 94%
with remaining 7% omission error (Figure 12, R6). However, it
has not been applied on all 109 buildings of this test yet, due to
time restrictions, while it has shortcomings, as the travelling
salesman algorithm does not use any input data information for
forming closed polygons.
5.3 Final results
The rule-based system for the combination of methods can be
seen in Figure 12.
Figure 12. Combination of the methods. R: result from
combination, M: Method.
Table 3 gives a summary of the correctness and omission
percentages of the various detection methods.
Correctness
(%)
Omission
(%)
Correctness
(%)
Omission
(%)
Ml
83
7
R1
86
12
M2
84
9
R2
96
20
M3
85
8
R3
85
8
M4
84
17
R4
85
7
R5
91
7
R6
94
7
Table 3. Summary of the correctness and omission percentages.
6. CONCLUSIONS
In this paper, different methods for object detection (mainly
buildings) in Lidar data and aerial images have been presented.
In each method, the basic idea was to get first preliminary
results and improve them later using the results of the other
methods. The methods have been tested on a dataset located at
Zurich Airport, Switzerland, containing RGB and CIR, Lidar
DTM and DSM point clouds and regular grids and building
vector data for accuracy assessment. The results from each
method have been combined according to their error
characteristics. Edges have been used for further improvement
of the detected building outlines. Finally, the correctness of
detection has been 94% with remaining 7% omission error that
mostly comes from construction process on airport buildings.
Future work will focus on the improvement of use of edges,
using the Lidar DSM to eliminate lines which don’t belong to
buildings and 3D building roof modeling.
ACKNOWLEDGEMENTS
This work has been supported by the EU FP6 project Pegase.
We acknowledge data provided by Swisstopo and Unique
Company (Airport Zurich).
REFERENCES
Axelsson, P., 2001. Ground estimation of laser data using
adaptive TIN-models. Proc. of OEEPE workshop on
airborne laserscanning and interferometric SAR for
detailed digital elevation models, 1-3 March, Stockholm,
Sweden, pp. 185-208.
Brenner, C., 2000. Towards fully automatic generation of city
models. Int. Archives of Photogrammetry and Remote
Sensing, Vol 33, Part B3/1, pp.85-92.
Brovelli, M.A., Cannata, M., Longoni U.M., 2002. Managing
and processing Lidar data within GRASS. Proc. of the
GRASS Users Conf. 2002, Trento, Italy.
http://citeseer.ist.psu.edu/541369.html (accessed 02 July
2009).
Canny, J., 1986. A computational approach to edge detection.
IEEE Trans. Pattern Anal. Machine Intel!., 8(6), 679-698.
Deineko, V., Van Dal, R., Rote, G., 1992. The convex-hull-
and-line traveling salesman problem: A solvable case.
Information Processing Letters, 51 (3), 141-148.
http://citeseer.ist.psu.edu/old/286488.html (accessed 02
July 2009).
Durupt, M., Taillandier, F., 2006. Automatic building
reconstruction from a digital elevation model and
cadastral data : An operational approach. IAPRS , Vol. 36,
Part 3, pp. 142-147.
http://www.isprs.org/commission3/proceedings06/singlep
apers/0_ 14.pdf (accessed 02 July 2009).
Elberink, S.,0., Vosselman, G., 2006, 3D Modelling of
Topographic Objects by Fusing 2D Maps and LIDAR
Data, IAPRS* Vol. 36, Part 4, pp. 199-204.
http://intranet.itc.nl/papers/2006/conf/vosselman_3D.pdf
(accessed 02 July 2009).
Elmqvist, M., Jungrt, E., Lantz, F., Persson, A., Soderman, U.,
2001. Terrain modelling and analysis using laser scanner
data. IAPRS*, Vol. 34, Part 3/W4, pp. 219-227.
http://www.isprs.org/commission3/annapolis/pdf/Elmqvist
.pdf (accessed 02 July 2009).
Gandalf, 2009. http://gandalf-library.sourceforge.net/
(accessed 27 June 2009).
Gruen, A., Wang, X., 1998. CC-Modeler: A topology
generator for 3-D city models. 1SPRS Journal of
Photogrammetry & Remote Sensing 53(5), 286-295.
http://linkinghub.elsevier.com/retrieve/pii/S092427169800
0112 (accessed 02 July 2009).
Haala, N., and Brenner, C., 1999. Virtual city models from
Laser altimeter and 2D map data. Photogrammetric
Engineering & Remote Sensing 65 (7), 787-795.
http://www.ifp.unistuttgart.de/publications/1999/norbert_o
hio.pdf (accessed 02 July 2009).