Mapping land cover and land use from object-based classification: an example from a complex agricultural landscape

摘要: From its inception, land-use and land-cover mapping have been major themes in remote-sensing research applications. Although frequently considered together, land use cover LULC are defined differently, with referring to the economic function of Earth’s surface natural or engineered biophysical cover. Land can be observed directly using remote sensing, but must inferred from type. In this study, we test whether object-based image analysis OBIA improve classification a complex agricultural landscape located along border between Poland Ukraine. We quantitatively compared results OBIA-based versus per-pixel classifications for both use, respectively. Our show that was not significantly improved when methods were used. overall accuracy modest, applied spectral spatial/geometric features objects, used independently. suggest anthropogenically altered landscapes where geometry arrangement spatial structure may convey information, techniques provide powerful tool improving classification.