MAPPING HAZELNUT TREES FROM HIGH RESOLUTION DIGITAL ORTHOPHOTO MAPS: A QUANTITATIVE COMPARISON OF AN OBJECT AND A PIXEL BASED APPROACHES

Abstract

This study investigates the suitability of object and pixel-based approaches for extraction of hazelnut trees from high resolution digital orthophoto maps. For object-based approach, simple linear iterative clustering (SLIC) method was employed to segment image pixels into homogeneous regions. Features spanning spectral, spatial and textural domains were extracted from each segment then classification was performed by employing support vector machine (SVM) classifier. For pixel-based approach, the spectral reflectance information from all four bands were used as features and applied maximum likelihood (ML) classifier for classification of each pixel into hazelnut and other tree species classes. An area based approach was used to evaluate the performance of the proposed method. The experiments showed that overall classification accuracy for object-based method was superior to the pixel-based method. Using object-based approach the overall accuracy obtained was 86% while pixel-based approach scored 76%.