Inventory of Single Oak Trees Using Object-Based Method on WorldView-2 Satellite Images and Earth
Subject Areas : Journal of Radar and Optical Remote Sensing and GIS
yousef
taghi mollaei
1
(PhD student of forestry in Ilam university)
abdolali
karamshahi
2
(Associate Professor and Faculty Member of Forest Sciences Department in University of Ilam)
Seyyed Yousef
Erfanifard
3
(Associate Professor, Department of Natural Resources and Environment, College of Agriculture, Shiraz University, Shiraz, Iran)
Keywords: Classification, Canopy, Zagros forests, Separation of single trees, Haft-Barm of Shiraz, remote sensing,
Abstract :
Remote sensing provides data types and useful resources for forest mapping. Today, one of the mostcommonly used application in forestry is the identification of single tree and tree species compassionusing object-based analysis and classification of satellite or aerial images. Forest data, which is derivedfrom remote sensing methods, mainly focuses on the mass i.e. parts of the forest that are largelyhomogeneous, in particular, interconnected) and plot-level data. Haft-Barm Lake is the case study whichis located in Fars province, representing closed forest in which oak is the valuable species. HighResolution Satellite Imagery of WV-2 has been used in this study. In this study, A UAV equipped with acompact digital camera has been used calibrated and modified to record not only the visual but also thenear infrared reflection (NIR) of possibly infested oaks. The present study evaluated the estimation offorest parameters by focusing on single tree extraction using Object-Based method of classification with acomplex matrix evaluation and AUC method with the help of the 4th UAV phantom bird image in twodistinct regions. The object-based classification has the highest and best accuracy in estimating single-treeparameters. Object-Based classification method is a useful method to identify Oak tree Zagros Mountainsforest. This study confirms that using WV-2 data one can extract the parameters of single trees in theforest. An overall Kappa Index of Agreement (KIA) of 0.97 and 0.96 for each study site has beenachieved. It is also concluded that while UAV has the potential to provide flexible and feasible solutionsfor forest mapping, some issues related to image quality still need to be addressed in order to improve theclassification performance.