Abstract
When we introduced the volumetric algorithm for single-tree delineation at the 3D GeoInfo 07, it was already a powerful algorithm with a high detection rate and the capability to generate trees for forestry units with only minimal user interaction. For the first test-area of 82 km2 this was acceptable, but as the test-areas grew, it showed that even the little user interaction does make the process laborious and strenuous. For currently envisaged test-areas of more than 1,000 km2, it is essential to further limit the required user interaction. In this paper we will show how to reduce the computational complexity of the volumetric algorithm and how to automatically calculate the free parameter that had to be set interactively in the earlier implementation. We will use the so called Receiver Operator Characteristic (ROC), an approach that is being used to model and imitate the human decision process when it comes to making a parameter decision in statistical processes. It turns out that this method, which is commonly used in other fields of scientific decision making, is also valuable for many other geo-information processes.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Buecken A, Rossmann J (2007) Using 3D-laser scanners and image-recognition for volume-based single-tree-delineation and -parameterization for 3D-GIS-applications. In: van Oesterom, Zlatanova, Penninga, Fendel (eds) Advances in 3D geoinformation systems, lecture notes in geoinformation and cartography LNG&C, Springer, Delft
Diedershagen O, Koch B, Weinacker H, Schütt C (2003) Combining LIDAR- and GIS data for the extraction of forest inventory parameters. In: Proceedings scand laser 2003
Erikson M (2003) Structure-preserving segmentation of individual tree crowns by brownian motion. In: Proceedings SCIA 2003, pp 283–289
Fawcett T (2003) ROC graphs: notes and practical considerations for data mining researchers. HP http://www.hpl.hp.com/techreports/2003/HPL-2003-4.pdf. Accessed 10 January 2012
Garcia R, Suárez J, Patenaude G (2007) Delineation of individual tree crowns for LiDAR tree and stand parameter estimation in Scottish woodlands. In: Fabrikant, Wachowski (eds) The European information society—leading the way with geo-information lecture notes in geoinformation and cartography, Springer, Berlin
Gougeon FA (1998) Automatic individual tree crown delineation using a valley-following algorithm and a rule-based system. In: Proceeding of international forum on automated interpretation of high spatial resolution digital imagery for forestry. 11–23
Gougeon FA (2010) Forest remote sensing in canada and the individual tree crown (ITC) approach to forest inventories. J Fac Agric Shinshu Univ 46:85–92
Hyyppä J, Inkinen M (1999) Detecting and estimating attributes for single trees using laser scanner. Photogram J Finland 2:27–42
Obuchowski N (2005) Fundamentals of clinical research for radiologists, ROC analysis. Am J Roentgenol 184:364–372
Persson Å, Holmgren J, Söderman U (2002) Detecting and measuring individual trees using an airborne laser scanner. Photogramm Eng Remote Sens 68:925–932
Popescu S, Wynne R (2004) Seeing the trees in the forest: using lidar and multispectral data fusion with local filtering and variable window size for estimation tree height. Photogramm Eng Remote Sens 70:589–604
Rossmann J, Krahwinkler PM (2009) Tree species classification and forest stand delineation based on remote sensing data – large scale monitoring of biodiversity in the forest. In: Proceedings of the ISRsE33
Rossmann J, Schluse M, Buecken A, Hoppen M (2009) Advances in forestry geo-information systems enabling new approaches in the bioenergy sector. In: Proceedings of the bioenergy 2009 conference
Acknowledgments
The project “Virtual Forest” is co-financed by the European Union and North-Rhine-Westphalia—European Regional Development Fund (EFRE)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Buecken, A., Rossmann, J. (2013). From the Volumetric Algorithm for Single-Tree Delineation Towards a Fully-Automated Process for the Generation of “Virtual Forests”. In: Pouliot, J., Daniel, S., Hubert, F., Zamyadi, A. (eds) Progress and New Trends in 3D Geoinformation Sciences. Lecture Notes in Geoinformation and Cartography. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29793-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-29793-9_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29792-2
Online ISBN: 978-3-642-29793-9
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)