We know where you are going: tracking objects in terrain

Traditional tracking algorithms rely heavily on past observations of objects but do not account for local information. These approaches work well when the objects of interest are subatomic particles, aircraft, or projectiles. However, they fail to account for the movement of intelligent objects in terrain. In this paper, we present an algorithm for tracking remotely sensed objects moving over terrain using information provided by a geographic information system. The proposed model specifically accounts for the influence of the environment (rivers, roads, vegetation, elevation, etc.) on the propagation of the probability densities. We make a number of assumptions about the motion of targets, but do not assume knowledge of goal locations.