Automated Coloring of Panchromatic Orthoimagery

Simon Premoze
Computer Science Department
University of Utah
Salt Lake City, Utah


Realistic rendering of outdoor terrain requires both that the geometry of environment be modeled accurately and that appropriate texturing be laid down on top of that geometry. While digital elevation data is widely available for much of the world and many methods exist for converting this data to forms suitable for graphics systems, we have much less experience with patterning the resulting surface. We describe an approach for automatic coloring of panchromatic aerial orthoimagery. The method is able to remove shading and shadowing effects in the original image so that shading and shadowing appropriate to variable times of day and year can be added. The method we present is based on pattern recognition principles. It classifies regions in the original panchromatic orthoimage into classes that are subsequently colored with user selected color palette. The method requires very little user interaction and is robust. The user only needs to select a few training point for each class that are later used in the pattern recognition and classification step. We also present an alternative method that is even simpler and requires no user intervention.