Size-constrained Region Merging (SCRM): An Automated Delineation Tool for Assisted Photointerpretation

摘要: The manual delineation of vegetation patches or forest stands is a costly and crucial stage in any land-cover mapping project inventory based upon photointerpretation. Recent computer techniques have eased the task interpreter; however, good deal craftsmanship still required delineation. In an effort to contribute automation this process, we introduce Size-Constrained Region Merging (SCRM), recently implemented software tool that provides interpreter with initial template tobe-mapped area may reduce digitization portion interpretation. essence, SCRM transforms ortho-rectified aerial satellite image (single multichannel) into polygon vector layer resembles work human interpreter, whom no priori knowledge scene, was given partitioning number homogeneous polygons all exceeding minimum size. We provide background information on foundations workflow, illustrate its application three different types images.