Valuation of Object-Based and Decision Tree Classification Methods in Estimating the Quantitative Characteristics of Single Oak Trees on WorldView-2 and UAV Images

One of the most commonly used applications in forestry is the identification of single trees and tree species compassions using object-based image analysis (OBIA) and classification of satellite or aerial images. The aims of this study were the valuation of OBIA and decision tree (DT) classification methods in estimating the quantitative characteristics of single oak trees on WorldView-2 and unmanned aerial vehicle (UAV) images. In this experimental study Haft-Barm forest, Shiraz, Iran, was considered as the study area in order to examine the potential of Worldview-2 satellite imagery. The estimation of forest parameters was evaluated by focusing on single tree extraction using OBIA and DT methods of classification with a complex matrix evaluation and area under operating characteristic curve (AUC) method with the help of the 4th UAV phantom bird image in two distinct regions. Data were analyzed by paired t-test, multivariate regression analysis, using SPSS 25, Excel 2016, eCognation v. 8.7, ENVI, 5, PCI Geomatica 16, and Google Earth 7.3 Software.
Findings: The base object classification had the highest and best accuracy in estimating single-tree parameters. Basic object classification method was a very useful method for identifying Oak tree Zagros Mountains forest. With using WV-2 data, the parameters of single trees in the forest can extract. The accuracy of OBIA is 83%. While UAV has the potential to provide flexible and feasible solutions for forest mapping, some issues related to image quality still need to be addressed in order to improve the classification performance