In: Wagner W., Székely, B. (eds.): ISPRS ТС VII Symposium - 100 Years ISPRS, Vienna, Austria, July 5-7, 2010, IAPRS, Vol. XXXVIII, Part 7B 
below the defined minimum segment area of 2 m 2 . Confusion 
with buildings (mainly the edges) is the major task of separating 
vegetation in urban areas. Using the cadastral building layer 
3.4% of the total vegetation segment area intersects with 
buildings and 7.7%, if the building polygons are buffered with 
2 m, indicating that predominantly building edges are wrongly 
classified. Note that also buildings overtopped by vegetation are 
also counted as error. On segment basis 4.8% of segments (402 
of 8413) are intersecting with buildings with more than 50% of 
their area. Looking at the buffered buildings, 14.0% (1182) of 
the segments confuse with building areas. 
Figure 9. (a) Vegetation segments and (b) derived generalized 
vegetation GIS layer 
The final result is the generalized vegetation mask (Fig. 9), 
generated by using the segments falling within one of the 
vegetation classes. Generalization was performed by removing 
small isolated vegetation areas (<20 m 2 ) and holes within 
vegetation (<20 m 2 ). Additionally the vegetation layer 
boundary is smoothed using Snakes (a=1.0). 
5. CONCLUSIONS 
This paper presented a novel workflow of GIS-based urban 
vegetation mapping using high density full-waveform LiDAR 
data. The combination of image-based object analysis and point 
cloud-based segment feature derivation and classification shows 
promising results for automated, operational applications, such 
as urban mapping, map updating, 3D visualization and urban 
tree inventory, when combined with single tree and stem 
detection algorithms. Future work will concentrate on including 
radiometric calibration, automated classification (e.g. statistical 
decision trees) and point cloud based single tree detection. 
ACKNOWLEDGMENTS 
We would like to thank the MA41-Stadtvermessung, City of 
Vienna, for their support and providing the airborne LiDAR 
data and reference datasets. 
REFERENCES 
Blaschke, T., 2010. Object based image analysis for remote 
sensing. ISPRS Journal of Photogrammetry and Remote 
Sensing, 65, pp. 2-16. 
GRASS Development Team, 2010. Geographic Resources 
Analysis Support System (GRASS) Software, Version 6.4.0. 
Open Source Geospatial Foundation, http://grass.osgeo.org 
Hirschmugl, M., Ofner, M., Raggam, J., Schardt, M., 2007. 
Single tree detection in very high resolution remote sensing 
data. Remote Sensing of Environment, 110, pp. 533-544. 
Hofle, B., Hollaus, M., Lehner, H., Pfeifer, N., Wagner, W., 
2008. Area-based parameterization of forest structure using 
full-waveform airborne laser scanning data. In: Proc. Silvilaser 
2008, Edinburgh, Scotland, pp. 227-235. 
Hofle, B., Miicke, W., Dutter, M., Rutzinger, M. , Dominger 
P., 2009. Detection of building regions using airborne LiDAR - 
A new combination of raster and point cloud based GIS 
methods. In: Proc. of the GIForum, Salzburg, pp. 66-75. 
Hyyppa, J., et al., 2001, HIGH-SCAN: The first European-wide 
attempt to derive single-tree information from laserscanner 
data. The Photogrammetric Journal of Finland, 17, pp. 58-68. 
Iovan, C., Boldo, D., Cord, M, 2007. Automatic extraction of 
urban vegetation structures from high resolution imagery and 
digital elevation model. In: Urban Remote Sensing Joint Event, 
URBAN2007 - URS 2007, Paris, pp. 1-5. 
Liang, X., J. Hyyppa, J., Matikainen, L., 2007. Deciduous- 
coniferous tree classification using difference between first and 
last pulse laser signatures. In: IAPRS, Vol. 36, Part 3/W52, pp. 
253-257. 
Mallet, C., Bretar, F., Soergel, U., 2008. Analysis of Full- 
waveform LiDAR Data for Classification of Urban Areas. 
Photogrammetrie Fernerkundung Geoinformation, 5, pp. 337- 
349. 
Reitberger, J., Schnorr, C., Krzystek, P., Stilla, U., 2009. 3D 
segmentation of single trees exploiting full waveform LIDAR 
data. ISPRS Journal of Photogrammetry and Remote Sensing, 
64, pp. 561-574. 
Rutzinger, M., Hofle, B., Pfeifer, N., 2007. Detection of high 
urban vegetation with airborne laser scanning data. In: 
Proceedings Forestsat 2007. Montpellier, France, pp. 1-5. 
Rutzinger, M., Hofle, B., Hollaus, M., Pfeifer, N., 2008. Object- 
Based Point Cloud Analysis of Full-Waveform Airborne Laser 
Scanning Data for Urban Vegetation Classification. Sensors, 
8(8), pp. 4505-4528. 
Rutzinger, M., Pratihast, A.K., Oude Elberink, S., Vosselman, 
G., 2010. Detection and Modeling of 3D Trees from Mobile 
Laser Scanning Data. In: Proc. ISPRS TCV Mid-Term 
Symposium, Newcastle upon Tyne, 6p. 
Secord, J., Zakhor, A., 2007. Tree Detection in Urban Regions 
Using Aerial Lidar and Image Data. IEEE Geoscience and 
Remote Sensing Letters, 4(2), pp. 196-200. 
SCOP++, 2010. Institute of Photogrammetry and Remote 
Sensing, www.ipf.tuwien.ac.at/products/products.html, last 
accessed 31.05.2010. 
Vosselman, G., 2003. 3D reconstruction of roads and trees for 
city modelling. In. IAPRS, Vol. 34, Part 3/W13, 6p. 
Wagner, W., Hollaus, M., Briese, C., Ducic, V., 2008. 3D 
vegetation mapping using small-footprint full-waveform 
airborne laser scanners. International Journal of Remote 
Sensing, 29 (5), pp. 1433-1452.