Object-Based Image Classification Process at Landscape Level Based on Spectral Index Extraction Using Sentinel 2 MSI Satellite Imagery

Authors : Esin Karamanlı, Ömer Faruk Uzun

Pages : 66-81

Doi:10.58816/duzceod.1675848

View : 101 | Download : 81

Publication Date : 2025-12-30

Article Type : Research Paper

Abstract :Land Cover-Land Use (LC/LU) classification provides data for effective management of environmental and ecological decisions at the landscape scale. In this process, Sentinel-2 Multi Spectral Imager (MSI) satellite images contribute to classification methods by facilitating information extraction with their high spectral resolution. While index-based methods mostly focus on the separation of single classes, landscapes require the separation of multiple classes. This study shows how different spectral indexes derived from Sentinel-2 MSI imagery can be used in large areas with the object-based image classification technique. The Silifke district of Mersin province was selected as a sample area. Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Built-up Area Extraction Index (BAEI), Built-up Area Index (BAI), Band Ratio (BR28, BR38), Normalized Built-up Area Index (NBAI), New Building Index (NBI), Urban Index (UI), Normalized Difference Soil Tillage Index (NDTI), Red Edge Based Normalized Difference Vegetation Index (NDVIre) and Normalized Difference Water Index (MNDWI) were used. While no significant results were obtained with BR28, BR38, NBAI, NBI and UI, 0.8815 kappa coefficient of 0.8815 and overall accuracy rate of %94.11 were obtained with other indexes.
Keywords : Nesne-tabanlı görüntü analizi, Spektral indisler, Sınıflandırma, En yakın komşu algoritması, Makine öğrenmesi

ORIGINAL ARTICLE URL