Digital classification of tree species and spatial structure of forest stands from remotely sensed data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A_____%2F03%3A41100009" target="_blank" >RIV/62156489:_____/03:41100009 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Digital classification of tree species and spatial structure of forest stands from remotely sensed data

Popis výsledku v původním jazyce

Scanned multispectral aerial photographs were used to estimate tree and stand variables by means of standard and novel digital image processing methods. Individual tree crown detection and delineation were realized by the brightest pixel technique template matching, edge detection in gradient direction, pixel tracing and cost surface generation. Several algorithms were tested and implemented into a program -Kernel processor-. Automated classification of tree species was carried out in the Idrisi32 environment using traditional and soft classifiers. Bayclass soft classifier provided the most precise results. Described procedures enable to create special forests maps that support alternative or simplified forest management plans at protected territories.

Název v anglickém jazyce

Digital classification of tree species and spatial structure of forest stands from remotely sensed data

Popis výsledku anglicky

Scanned multispectral aerial photographs were used to estimate tree and stand variables by means of standard and novel digital image processing methods. Individual tree crown detection and delineation were realized by the brightest pixel technique template matching, edge detection in gradient direction, pixel tracing and cost surface generation. Several algorithms were tested and implemented into a program -Kernel processor-. Automated classification of tree species was carried out in the Idrisi32 environment using traditional and soft classifiers. Bayclass soft classifier provided the most precise results. Described procedures enable to create special forests maps that support alternative or simplified forest management plans at protected territories.

Druh

D - Stať ve sborníku

CEP obor

GK - Lesnictví

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2003

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 22nd EARSeL Symposium, Prague, Czech Republic, 4-6 June, 2002

ISBN

90-77017-71-2

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

439-446

Název nakladatele

Millpress Science Publishers, Rotterdam

Místo vydání

Rotterdam

Místo konání akce

Praha

Datum konání akce

4. 6. 2002

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—