An Evaluation of Pixel- and Object-Based Tree Species Classification in Mixed Deciduous Forests Using Pansharpened Very High Spatial Resolution Satellite Imagery

Quality tree species information gathering is the basis for making proper decisions in forest management. By applying new technologies and remote sensing methods, very high resolution (VHR) satellite imagery can give sufficient spatial detail to achieve accurate species-level classification. In this study, influence of pansharpening WorldView-3 (WV-3) on classification results three main (Quercus robur L., Carpinus betulus Alnus glutinosa (L.) Geartn.) has been evaluated. order increase accuracy, different algorithms (Bayes, RCS, LMVM) have conducted. The LMVM algorithm proved most effective technique. pixel- object-based were applied pansharpened imageries using a random (RF) algorithm. showed overall accuracy (OA) imagery: 92% 96% based approach, respectively. As expected, exceeded pixel-based approach (OA increased by 4%). fusion was analyzed as well. Overall improved images 7% approach). Also, regardless or approaches, use highly beneficial classifying complex, natural, mixed deciduous areas.