Original title:
Individual tree crowns delineation using local maxima approach and seeded region growing technique
Authors:
Novotný, Jan ; Hanuš, Jan ; Lukeš, Petr ; Kaplan, Věroslav Document type: Papers Conference/Event: GIS Ostrava 2011. Eight international symposium, Ostrava (CZ), 2011-01-24 / 2011-01-26
Year:
2011
Language:
eng Abstract:
Remote sensing applications in forestry can profit from a rapid development of optical sensors. Applied algorithms should be suited to the new properties of the data (very high resolution and wide spectral range). Segmentation of the image into objects is an important task in forestry applications of optical remote sensing. Segmentation of individual tree crowns involves two parts — detection and delineation phase. Local maxima approach and seeded region growing technique are presented as the key concepts. Furthermore improvements, namely histogram equalization and Voronoi diagram, are incorporated. Two datasets were processed and results of the segmentation are presented. Hyperspectral data with spatial resolution of 0.8m were found as a suitable for segmentation process with 84% and 78% accuracy of detection phase and 64% and 52% accuracy in delineation phase respectively. Finally discussion of recommended settings in the algorithm is presented.
Keywords:
individual tree crowns; local maxima detection; optical remote sensing; seeded region growing Project no.: CEZ:AV0Z60870520 (CEP), SP/2D1/70/08 (CEP) Funding provider: GA MŽP Host item entry: GIS Ostrava 2011. Eight international symposium. Ostrava, Czech Rrepbublic , January 2011, ISBN 978-80-248-2406-2
Institution: Global Change Research Institute AS ČR
(web)
Document availability information: Fulltext is available at the institute of the Academy of Sciences. Original record: http://hdl.handle.net/11104/0006456