Search published articles
Showing 2 results for Erfanifard
Volume 6, Issue 4 (Fall 2018)
Abstract
Aims: 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.
Materials & Methods: 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.
Conclusion: 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.
Volume 23, Issue 1 (1-2021)
Abstract
Spatially explicit estimates of aboveground biomass over large area are necessary for natural resources managers. This study examined aboveground biomass and carbon stock of the wild pistachio (Pistacia atlantica) based on individual tree crown detection and allometric development in the arid woodlands using high-resolution satellite images of GeoEye-1 in a reserved forest area of Wild Pistachio trees in the South Khorasan Province, East of Iran. Biomass of sampled trees was determined using field sampling and experimental tests. In addition, the biomass of stems was determined using volume and density. The allometric biomass and carbon stock equations of Wild Pistachio trees were developed based on crown area, diameter at breast height (1.3 m), and height of trees. The trees crowns were detected and delineated on the GeoEye-1 images, using local maxima filters, and region growing segmentation algorithms, respectively. In addition, a morphological watershed transformation method was applied to split the connected and overlapped tree crowns. Performing algorithms was assessed using the measured field crown of sample trees by precision, recall, and overall accuracy indices. The biomass and carbon stock of trees of the study area were estimated using delineated crown area and the developed allometric equations. The results showed that the equation that used crown area could explain more than 80% of the remarked variation in biomass and carbon stock. In addition, the crown detection method results showed that overall detection rate and the quality of crown boundaries were acceptable. In conclusion, the study confirmed that combining the allometric equations with crown information from high-resolution images could contribute to the explicit mapping of biomass and carbon stock of wild pistachio trees in the arid woodlands.
