Scholarly record
A LOCAL AREA TREE SPECIES CLASSIFICATION
Abstract
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.
Publication Impact Profile
Publication details
References5
Buecken A., Rossmann J., Forest Survey based on Remote Sensing Data, SGEM Vienna Green 2018, Austria, 2018
Fassnacht F.E., Latifi H., Sterenczak K, Mozelewska A., Lefsky M., Waser L.T., Straub C., Ghosh A., Review of studies on tree species classification from remotely sensed data, Remote Sensing of the Environment 186, Germany, 2016
Krahwinkler P., Rossmann J., Sondermann B., Support Vector Machine Based Decision Tree for very high Resolution multispectral Forest Mapping, Proceedings of the 2011 IEEE International Geoscience und Remote Sensing Symposium,Canada, 2011
Leberl F., Gruber M., Flying the New Large Format Digital Aerial Camera Ultracam, Photogrammetric Week '03, Germany, 2003
Stoffels J., Hill J., Sachtleber T., Mader S., Buddenbaum H., Stern O., Langshausen J., Dietz J., Ontrup G., Satellite-Based Derivation of High-Resolution Forest Information Layers for Operational Forest Management
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.
