Abstract
We modified the structure similarity index, which is extensively used for image quality assessment, to be clutter metrics and call them target structure similarity measures (TSSIM). Two methods for calculating the TSSIM metrics were suggested. In this paper, via different mathematical formulas, the metrics are used to predict detection probabilities and detection times. The degrees of correlation between various clutter metrics and both the target detection probabilities and the mean detection times, which are obtained from the Search_2 dataset, are presented. Based on these data, comparisons between TSSIMs and three other typical clutter metrics are demonstrated. Experiment results show the TSSIMrms measure generates much better predictive capabilities for both the experimental detection probabilities and the mean detection times than other clutter measures being compared.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call