HOME
Full Articles List
Search by Author
Title: A LOCAL AREA TREE SPECIES CLASSIFICATION
BibTex 
Open this article in the author's DB |
|
A LOCAL AREA TREE SPECIES CLASSIFICATION
|
|
|
|
|
|
|
|
||
|
|
|
|
|
|
1314-2704
|
|
|
|
||
|
|
English
|
|
|
|
18
|
|
|
|
1.5
|
|
|
|
|
|
|
|
||
|
|
Many automated processes in the forestry sector require a tree species classification to locate individual trees or to distribute data to several species. There is already a huge number of classification approaches, which can be found in the literature. But still there is no global tree species classification available. The difficulty of a global classification is based on the variance in the appearance of the same species in several locations. This is mainly due to two problems: First internal disturbance - trees and their spectral properties vary based on the age of the tree, the altitude, the nutrient and water supply and other factors. Second external disturbance - the spectral properties are based on the sensor, the time of day and thereby the solar altitude and position, the weather and other external properties. Radiometric alignment limits the external disturbance and can especially cope with the sensor properties. But it cannot compensate the different time of day for the individual photos of an aerial flight campaign and therewith the different light exposure of the tree. An alternative is satellite imagery as satellites cover large areas with one scene, but at the price of clouds and ? in comparison to aerial photos ? a reduced resolution. For example the popular Sentinel 2 satellite provides a 10m resolution in the visible spectral bands and 20m in the infrared bands. According to the Nyquist-Shannon sampling theorem this allows to detect structures of 40m by 40m ? in the optimal case without any noise or other disturbance. In reality this allows one reading per forestry unit, by far not enough to differ between individual trees and to distribute data to several species. Other satellites offer a finer resolution, but this data is cost-intensive.
|
|
|
|
conference
|
|
|
|
||
|
|
||
|
|
18th International Multidisciplinary Scientific GeoConference SGEM2018
|
|
|
|
18th International Multidisciplinary Scientific GeoConference SGEM2018, 3 ? 6 December, 2018
|
|
|
|
Proceedings Paper
|
|
|
|
STEF92 Technology
|
|
|
|
International Multidisciplinary Scientific GeoConference-SGEM
|
|
|
|
Bulgarian Acad Sci; Acad Sci Czech Republ; Latvian Acad Sci; Polish Acad Sci; Russian Acad Sci; Serbian Acad Sci & Arts; Slovak Acad Sci; Natl Acad Sci Ukraine; Natl Acad Sci Armenia; Sci Council Japan; World Acad Sci; European Acad Sci, Arts & Letters; Ac
|
|
|
|
535-542
|
|
|
|
3 ? 6 December, 2018
|
|
|
|
website
|
|
|
|
cdrom
|
|
|
|
2112
|
|
|
|
Forestry; Timber Volume; Remote Sensing
|
|
Download PDF