Please use this identifier to cite or link to this item:https://hdl.handle.net/20.500.12259/83559
Type of publication: research article
Type of publication (PDB): Straipsnis kitose duomenų bazėse / Article in other databases (S4)
Field of Science: Miškotyra / Forestry (A004)
Author(s): Jonikavičius, Donatas;Mozgeris, Gintautas
Title: Forest change detection using medium resolution single acquisition time satelite images
Is part of: Forest and Sustainable Development [elektroninis išteklius] : Proceedings of the Biennial International, Brasov, 15-16 October 2010. Brasov: Transilvania University Press
Extent: p. 421-426
Date: 2011
Keywords: Forest inventory;Change detection;Satellite images;Erosion;Reconstruction
Abstract: Traditionally, numerous solutions are used for satellite image based forest change detection. Most of them are based on the use several satellite images from different dates of acquisition. This paper discusses the usability of single acquisition time medium resolution SPOT 4 HRVIR satellite image, some sample of field measured plots and information from previous stand-wise forest inventory to detect clear final felling related changes in test area in central Lithuania. Grids of stand volume per 1 ha were estimated using the non-parametric k-nearest neighbor estimator and subtracted from the grids representing the stand volume estimated a decade ago within the frames of conventional forest inventory. More than 90% overall change detection accuracy was achieved. The change commission errors were much reduced applying post-processing techniques to remove automatically produced false changes
Internet: https://hdl.handle.net/20.500.12259/83559
Affiliation(s): Vytauto Didžiojo universitetas
Žemės ūkio akademija
Appears in Collections:Universiteto mokslo publikacijos / University Research Publications

Files in This Item:
marc.xml5.55 kBXMLView/Open

MARC21 XML metadata

Show full item record
Export via OAI-PMH Interface in XML Formats
Export to Other Non-XML Formats


CORE Recommender

Page view(s)

27
checked on May 1, 2021

Download(s)

6
checked on May 1, 2021

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.