Skip to the main content

Journal of the Forestry (Šumarski list), Vol. 138 No. 9-10, 2014.

Preliminary communication

TREE SPECIES CLASSIFICATION USING WORLDVIEW-2 SATELLITE IMAGES AND LASER SCANNING DATA IN A NATURAL URBAN FOREST

Andrej Verlič ; Dr. Tisa / Slovenian Forestry Institute, Ljubljana, Slovenia
Nataša Đurić ; Slovenian Centre of Excellence for Space Sciences and Technologies SPACE-SI, Ljubljana, Slovenia
Žiga Kokalj ; Slovenian Centre of Excellence for Space Sciences and Technologies SPACE-SI / Research Centre of the Slovenian Academy of Sciences and Arts, Ljubljana, Slovenia
Aleš Marsetič ; Slovenian Centre of Excellence for Space Sciences and Technologies SPACE-SI / Research Centre of the Slovenian Academy of Sciences and Arts, Ljubljana, Slovenia
Primož Simončič ; Slovenian Forestry Institute, Ljubljana, Slovenia
Krištof Oštir ; Slovenian Centre of Excellence for Space Sciences and Technologies SPACE-SI / Research Centre of the Slovenian Academy of Sciences and Arts, Ljubljana, Slovenia

Full text: english pdf 769 Kb

page 477-488

downloads: 1.303

cite

Abstract

A detailed tree species inventory is needed to sustainably manage a natural, mixed, heterogeneous urban forest. An object-based image analysis of a combination of high-resolution WorldView-2 multi-spectral satellite imagery and airborne laser scanning (LiDAR) data was tested for classification of individual tree crowns of five different tree species. The model training data were obtained from a systematic grid of plots in the forest. In total, 304 coniferous (Norway spruce and Scots pine) and 270 deciduous (European beech, Sessile and Pedunculate oak (combined), and Sweet chestnut) trees were identified in the field. The classification was performed by applying the support vector machine model. An accuracy assessment was performed by calculating a confusion matrix to evaluate the accuracy of the classification output by comparing the classification result to the independent test data. The overall accuracy of the classification was 58 %.

Keywords

green infrastructure; ground truth data; spectral signature; tree species mapping; tree species inventory; forest monitoring

Hrčak ID:

133541

URI

https://hrcak.srce.hr/133541

Publication date:

30.11.2014.

Article data in other languages: croatian

Visits: 3.074 *