CMRT09: Object Extraction for 3D City Models, Road Databases and Traffic Monitoring - Concepts, Algorithms, and Evaluation
For the purpose of the NDVI image, the Red and NIR channels
exhibit excessive tree pixels in the extremities due to tree lean
and the structure of the resulting NDVI image will therefore not
match the structure of the DSM. This requires further
investigation. The DSM quality can also be improved by
incorporating building foot prints if available.
LiDAR and aerial images should, ideally, not be captured
separately. Objects which exist in the images might not exist in
the LiDAR data and it is time consuming to identify and
separate those points, especially vehicles on roads or in parking
areas. In addition, if the time delay is significant, the vegetation
may change considerably.
Results from the automatic and semi-automatic stages of this
workflow are encouraging. Limitations identified above are the
subject of continuing research.
7. REFERENCES
Clode, S. and Rottensteiner, F. 2005. Classification of Trees
and Powerlines from Medium Resolution Airborne Laser
Scanner Data in Urban Environments. Proceedings of
Workshop on Digital Image Computing, Brisbane, Australia,
pp. 97-102.
Clode, S., Rottensteiner, F., Kootsookos, P. and Zelniker, E.,
2007. Detection and Vectorization of Roads from LiDAR Data.
Photogrammetric Engineering and Remote Sensing, 73(5), pp.
517-535.
Rottensteiner, F. Trinder, J. Clode, S. Kubik, K. Lovell, B.
2004. Using the DempsterShafer Method for the Fusion of
LiDAR Data and Multi-spectral Images for Building Detection.
Proceedings of the 17th International Conference on Pattern
Recognition, Vol. 2, pp. 339 - 342.
Fugro International. FL1-MAP 400 Specifications. [Online],
Available at: http:/Avww.flimap.com/site47.php (accessed: 26 th
June 2009).
Haitao, L. Haiyan, G., Yanshun, H. and Jinghui, H., 2007.
Fusion of High Resolution Aerial Imagery and LiDAR Data for
Object-Oriented Urban Land-Cover Classification Based on
SVM. ISPRS Workshop on Updating Geo-spatial Databases
with Imagery & The 5th ISPRS Workshop on DMGISs,
Urumchi, Xingjiang, China. [Online], Available at:
www.commission4.isprs.org/urumchi/papers/179-
184%20Haitao%20Li.pdf (accessed: 26 th June 2009).
Hatger, C., 2005. On the Use of Airborne Laser Scanning Dat
to Verify and Enrich Road Network Features , Proceedings of
ISPRS Technical Commission III Symposium , Enschede,
Netherlands.
Heipke, C., Mayr, H. , Wiedemann, C. and Jame, O., 1997.
Evaluation of Automatic Road Extraction. International
Archives of Photogrammetrv and Remote Sensing, XXXII
(3/2W3), 56.
Leica Geosystems Incorporation. [Online], Available at:
http://www.leica-geosystems.com/corporate/en/lgs_57627.htm
(accessed: 12 th October 2008).
Mayer, H., 2008. Object Extraction in Photogrammetric
Computer Vision. ISPRS Journal of Photogrammetry and
Remote Sensing, Volume 63, Issue 2, pp. 213-222.
Mayer, H., Hinz, S. and Stilla, U. 2008. Automated Extraction
of Roads, Buildings and Vegetation from Multi-source Data,
Advances in Photogrammetry, Remote Sensing and Spatial
Information Sciences: ISPRS Congress Book.
N. Haala and C. Brenner, 1999. Extraction of Buildings and
Trees in Urban Environments. ISPRS Journal of
Photogrammetty and Remote Sensing, Vol. 54, pp. 130—137.
Sithole, G and Vosselman, G., 2003. Comparison of Filtering
Algorithms. Proceedings of the ISPRS working group III/3
workshop on 3-D reconstruction from airborne laserscanner
and InSAR data, Dresden, Germany, 8-10 October .
58