Object-Based Classification of Izmir Metropolitan City by Using Sentinel-2 Images

• Published in: 2019 9th International Conference on Recent Advances in Space Technologies (RAST) pp. 407 - 412
• Main Authors: Ozlem Yilmaz, Elif, Varol, Beril, Hale Topaloglu, Raziye, Sertel, Elif
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-06-2019
• Subjects: LCLU maps; object based classification; Sentinel-2; Urban Atlas
• DOI: 10.1109/RAST.2019.8767781

This study aims to create Land Cover Land Use (LCLU)map of a part of the Izmir metropolitan city in Turkey, based on an enhanced Urban Atlas nomenclature and object based classification approach. Multi-temporal Sentinel-2 images from different seasons are used and rule-based object oriented classification techniques are applied on the images. Totally 20 LCLU classes are identified in the study area with different accuracy values. Thematic open source data were also integrated into classification to better identify some land use classes and to increase the total classification accuracy. Our results show that 10-m bands of Sentinel-2 images are capable to produce thematically detailed LCLU map with an overall accuracy of 86% and 0.852 Kappa values.