A Novel Transformation Watershed Image Segmentation Model in Digital Elevation Maps Processing

Abstract

Computer analysis of image objects starts with finding them-deciding which pixels belong to each object. Digital elevation maps or models (DEMs) are arrays of numbers representing the spatial distribution of terrain elevations. They can be seen as gray-scale images, whereby the value of a pixel represents an elevation rather than a luminance intensity (the brighter the gray-tone level of a pixel, the higher the elevation of the terrain point corresponding to this pixel). Useful applications of DEMs can be found in civil/rural engineering, geographic information systems (GIS), geomorphology, water resources management, photogrammetry, satellite imaging. A watershed is defined as a region of land that assists in draining water (usually rainwater) into a river or a creek. It is an area of high ground through which water flows into the river or creek. Simply defined, the watershed is a transformation in grayscale images. This technique aims to segment the image, typically when two regions-of-interest are close to each other, their edges touch. Thus far, we have discussed segmentation based on three principal concepts.