A metaheuristic-based approach to optimizing color design for military camouflage using particle swarm optimization

Enhancing an existing military camouflage is an important component during the assessment of military camouflage. The current study proposed a new and practical approach to enhancing the undetectability of a military camouflage using particle swarm optimization (PSO). Eight different locations (20 x 50 pixels) in the one swamp background were selected to be the place of a human-shaped target. The PSO would generate newly proposed camouflage as an empirical parameter based on the lower and the upper bounds from selected four different colors in swamp background. The predictive algorithm was applied to adjust the optimum shift of %L*, %a*, and %b* from the original to the empirical parameter. Thirty participants were recruited to evaluate the original and newly proposed camouflages. Paired sample t test indicates that the newly proposed military camouflage had a significant lower camouflage similarity index value and a longer detection time. The PSO shows to be a method with good results; however, a comprehensive study using multiple backgrounds and patterns would be required to generalize the methodology to other background environments or camouflage patterns.