Image segmentation algorithms for land categorization

Abstract

The focus of this chapter is on image segmentation algorithms for land categorization. Our image analysis goal will generally be to appropriately partition an image obtained from a remote sensing instrument on-board a high flying aircraft or a satellite circling the earth or other planet. An example of an earth remote sensing application might be to produce a labeled map that divides the image into areas covered by distinct earth surface covers such as water, snow, types of natural vegetation, types of rock formations, types of agricultural crops and types of other man created development. Alternatively, one can segment the land based on climate (e.g., temperature, precipitation) and elevation zones. However, most image segmentation approaches do not directly provide such meaningful labels to image partitions. Instead, most approaches produce image partitions with generic labels such as region 1, region 2, and so on, which need to be converted into meaningful labels by a post-segmentation analysis.