|
|
Souhrnná výzkumná zpráva Aalto 1903
Hanuš, Jan ; Fabiánek, Tomáš ; Fajmon, Lukáš
Within the airborne hyperspectral campaign for a Finnish university Aalto University were scanned two locations - Hyytiälä (FI) - Järvselja (EST). The scanned processed data is used for other scientific purposes.\nAbstrakt: V rámci letecké hyperspektrální kampaňe pro Finskou univerzitu Aalto-yliopisto byly nasnímány dvě lokality - Hyytiälä (FI) - Järvselja (EST). Předaná zpracovaná data jsou používány pro další vědecké účely.
|
|
| |
|
| |
|
|
Letecká hyperspektrální kampaň HYPOS
Hanuš, Jan ; Homolová, Lucie ; Janoutová, Růžena
ESA projekt HYPOS (Hyperspectral analysis and heterogeneous surface modelling) řešili pracovníci CzechGlobe společně se třemi francouzskými partnery (Magellium, CESBIO, IRSTEA) v letech 2016 až 2018. Úkolem projektu bylo vytvoření algoritmů pro odhad parametrů vegetace z hyperspektrálních dat a definování nejvhodnějších spektrálních pásem pro odhad parametrů z multispektrálních dat.
|
|
|
Hyperspectral image segmentation for estimation of biomass at reclaimed heaps
Pikl, Miroslav ; Zemek, František
This paper presents the preliminary results from a study that aims at estimation of above ground biomass and soil carbon content at reclaimed mining heaps in the Sokolov region. Two image segmentation methods are presented. We applied maximal likelihood (ML) and neural network (NN) classifi ers on airborne hyperspectral data. Th e objective of this part of the study was to prepare a land cover classifi cation of the region. Th e main focus was paid to discrimination of six classes with prevailing forest species cover. Th e classifi cation accuracy of the training sites was 93.75 % for NN and 79.12 % for ML respectively. But ML outperformed NN in overall classifi cation accuracy with 61.54 % compared to 40.9 % of NN. Th e more accurate results of the ML classifi er are probably infl uenced by properties of the training samples. Th e larger size of the training samples derived for ML enabled better representation of class histograms. Th e lower overall NN accuracy could result from high spatial resolution of HS data.
|
host ::
RSS.