An Automated Delineation Tool for Assisted Interpretation of Digital Imagery

The manual delineation of vegetation patches or forest stands is a costly and critical stage in any landcover mapping project or forest inventory based upon photointerpretation. Recent computer techniques have eased the task of the interpreter; however a good deal of craftsmanship is still required in the delineation. In an effort to contribute to the automation of this process, we introduce Size-Constrained Region Merging (SCRM), a recently implemented software tool that provides the interpreter with an initial template of the to-be-mapped area that may reduce the manual digitization portion of the process. In essence, SCRM transforms an ortho-rectified aerial or satellite image (single or multi-channel), into a polygon vector layer that resembles the work of a human interpreter, whom without a priori knowledge of the scene, was given the task of partitioning the image into a number of homogeneous polygons all exceeding a minimum size (i.e., minimum mapping unit). We provide background information on SCRM foundations, workflow and usage, and illustrate its application on a Quickbird image acquired over a rural area.