Developing a similarity index for static camouflaged target detection

摘要

Measurement of camouflage performance is of fundamental importance for military stealth applications. The goal of camouflage assessment algorithms is to automatically assess the effectiveness of camouflage in agreement with human detection responses. We propose a new method for computational evaluation of camouflage effectiveness. We evaluate the performance of the new method and other existing algorithms in a comparative setting which utilised an extensive human visual experiment. The results show that the new method is correlated with the human target searching results with higher correlations than the existing algorithms.