Article ID Journal Published Year Pages File Type
385895 Expert Systems with Applications 2011 12 Pages PDF
Abstract

Inspired from various colors of ants in organized insect communities, we propose a novel ant system with a “subtractive” color mixing model of three primary colors for jointly estimating the number of tracks to be initiated and their individual tracks in the multi-sensor multi-target system. Firstly, each ant is assumed to deposit only one type of colored pheromones all the time, namely, cyan, magenta, or yellow, and ant’s decision depends on the colored pheromone similarity comparison with candidates to be visited. Then a mixture optimization function on a three-dimensional parameter space is proposed to exploit best solutions by the following ants, which results in a group of nearly cyan, magenta, or yellow tracks of interest. Finally, a new track initiation evaluation metric, i.e., Optimal Sub-Pattern Assignment (OSPA) distance, is introduced for the unknown number of tracks. Simulation results indicate favorable performance both in clutter-free and cluttered environment.

Research highlights► A novel ant system, which is based on a subtractive color mixing model of three primary colors, is proposed to initiate tracks of interest. ► A three-dimensional parameter space is proposed to exploit the best solutions. ► The OSPA metric is introduced to evaluate the performance of results obtained by our algorithm.

Related Topics
Physical Sciences and Engineering Computer Science Artificial Intelligence
Authors
, , , ,