Filtering of multichannel video sequences distorted by noise, based on the fuzzy-set theory

A new approach based on the fuzzy-set theory is proposed, which allows detection of object motion from frame to frame of video sequences and filtering of images distorted by additive noise. New fuzzy rules and membership functions introduced in the study make it possible to perform efficient filtering of video sequences using the correlation between channels and in video sequence neighboring frames. Simulation of the proposed and known algorithms of video sequence processing shows the advantage of the new filtering scheme in terms of conventional PSNR, MAE, NCD, SSIM criteria and visual comparison of filtered video sequences.