SFM-Forest-Benchmark project: The benchmarking of image-based point cloud for forest inventory Principal Investigators Martin Mokroš 1 , Markus Hollaus 2 and Yunsheng Wang 3 Co-investigators Peter Surový 1 , Livia Piermattei 2 , Xinlian Liang 3 , Milan Koreň 4 , Julián Tomaštík 4 and Lin Cao 5 1 Czech University of Life Sciences Prague, Czech Republic; 2 TU Wien, Austria; 3 Finnish Geospatial Research Institute, Finland; 4 Technical University in Zvolen, Slovakia; 5Nanjing Forestry University, China Participants Gábor Brolly 1 , Carlos Cabo 2,3,4 , Bartłomiej Kraszewski 5 , Grzegorz Krok 5 , Martin Krůček 6 , Nizar Polat 7 , Atticus Stovall 8 , Di Wang 9 , Jinhu Wang 10 1 University of Sopron, Hungary; 2 Swansea University, United Kingdom; 3 University of Oviedo, Spain; 4 CETEMAS Research Institute, Spain; 5 Forest Research Institute, Poland; 6 The Silva Tarouca Research Institute for Landscape and Ornamental Gardening, Czech Republic; 7 Harran University, Turkey; 8 NASA Goddard Space Flight Center, USA; 9 Aalto University, Finland; 10 Chinese Academy of Sciences, China
15
Embed
SFM-Forest-Benchmark project: The benchmarking of image ...SFM-Forest-Benchmark project: The benchmarking of image-based point cloud for forest inventory Principal Investigators Martin
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
SFM-Forest-Benchmark project: The benchmarking of image-based point cloud for forest inventory
Principal Investigators
Martin Mokroš1, Markus Hollaus2 and Yunsheng Wang3
Co-investigators
Peter Surový1, Livia Piermattei2, Xinlian Liang3, Milan Koreň4, Julián Tomaštík4 and Lin Cao5
1Czech University of Life Sciences Prague, Czech Republic; 2TU Wien, Austria; 3Finnish Geospatial Research Institute, Finland; 4Technical University in Zvolen, Slovakia; 5Nanjing Forestry University, China
Participants
Gábor Brolly1, Carlos Cabo 2,3,4, Bartłomiej Kraszewski5, Grzegorz Krok5, Martin Krůček6, Nizar Polat7, Atticus Stovall8, Di Wang9, Jinhu Wang10
1University of Sopron, Hungary; 2Swansea University, United Kingdom; 3University of Oviedo, Spain; 4CETEMAS Research Institute, Spain; 5Forest Research Institute, Poland; 6The Silva Tarouca Research Institute for Landscape and Ornamental Gardening, Czech Republic; 7Harran University, Turkey; 8NASA Goddard Space Flight Center, USA; 9Aalto University, Finland; 10Chinese Academy of
Sciences, China
International Benchmarking of terrestrial Image-based Point Clouds for Forestry
ISPRS Scientific Initiatives 2019
Project hypothesis
• Is it possible to use image-based point clouds for individual tree mapping and modelling in various type of forest stands ?
• Is it possible to achieve similar accuracy from image-based point clouds as from TLS point clouds regarding DBH estimation within the research plots?
• Will applied algorithms for DBH and tree positions estimation show different performance on image- and TLS-based point clouds?
• What is influencing the accuracy of the tree mapping and modelling in algorithms?
Study site Shape
Size (m)
Diameter /
square length
Tree species
Stem
Density
[stems/ha]
Austria 1 Circular 40 Picea abies 533
Austria 2 Circular 40 Fagus sylvatica 390
China 1 Circular 30 Taxodium distichum 410
China 2 Circular 30 Liriodendron chinensis 609
Czechia 1 Square 50 Fagus sylvatica 280
Czechia 2 Square 50 Picea abies 272
Finland 1 Square 32 Pinus sylvestris 479
Finland 2 Square 32 Pinus sylvestris, Betula sp. 869
Slovakia 1 Circular 20 Abies alba 875
Slovakia 2 Circular 15 Quercus petraea 651
DATASETS
SfM TLS
Institution Responsible person
The Silva Tarouca Research Institute for
Landscape and Ornamental GardeningMartin Krůček
Aalto University Di Wang
Chinese Academy of Sciences Jinhu Wang
Czech University of Life Sciences Prague Karel Kuželka
Finnish Geospatial Research Institute Xinlian Liang
Forest Research Institute Grzegorz Krok
Forest Research Institute Bartłomiej Kraszewski
Harran University Nizar Polat
NASA Goddard Space Flight Center Atticus Stovall
Nanjing Forestry University Lin Cao
Nanjing Forestry University Lin Cao
Technical University of Vienna Markus Hollaus
Technical University in Zvolen Milan Koreň
University of Oviedo Carlos Cabo
University of Sopron Gábor Brolly
12,000+ individual results
RMSEBias
OmissionComission
CompletenessCorrectness
Preliminary conclusions
• It is possible to use image-based point clouds for individual tree mapping and modeling in various type of forest stands,
• it is possible to achieve similar accuracy from image-based point clouds as from TLS point clouds regarding DBH estimation within the research plots,
• applied algorithms for DBH estimation showed significant differencies