Discrete range clustering using Monte Carlo methods

Passive sensing algorithms using electrooptic sensors produce reliable range at sparse locations. Both for automatic guidance and as a display for aiding the pilot, these discrete ranges need to group into sets which correspond to objects in the nearby environment. The focus is on using Monte Carlo methods for clustering range points into meaningful groups. One of the aims is to explore whether simulated annealing methods offer significant advantage over the basic Monte Carlo method for this class of problems. The authors compare three different approaches and present results of application of these algorithms to a helicopter flight sequence.<>