The general outdoors passive ranging scenario is one of the most challenging and important areas of research for an optical sensor system moving free in the three dimensional space. We describe here an integrated system of image processing and AI algorithms developed and demonstrated at the Systems and Research Center of Honeywell. This passive ranging system produces a dense range map of an outdoors scene, based only on the sensed imagery and the average speed of the aircraft. No additional knowledge is required about the terrain or the aircraft/sensor attitude changes.

Image segmentation can be treated as a pixel classification problem. This classification may be done by measuring a set of features at each point and defining a decision surface in the feature space. This method is commonly used in multispectral images, but there is no obvious choice for the feature set in the case of monochromatic images. Ihis paper makes use of a two-dimensional feature set consisting of gray level and edge value. Ihe structure of this feature space is analyzed, and several plausible decision surfaces are suggested. These are compared experimentally on a set of FLIR test images.