Using texture to tackle the problem of scale in land-cover classification

摘要: Object Based Image Analysis (OBIA) is a form of remote sensing which attempts to model the ability human visual system (HVS) interpret aerial imagery. We argue that in many its current implementations, OBIA not an accurate this system. Drawing from theories cognitive psychology, we propose new conceptual believe more accurately represents how HVS performs image interpretation. The first step generation segmentation where each area uniform properties represented correctly. goal work implement step. To achieve extract novel complementary set intensity and texture gradients offer increased discrimination strength over existing competing gradient sets. These are then fused using strategy accounts for spatial uncertainty boundary localization. Finally performed watershed algorithm. Results achieved very outperform popular Canny operator.