FLIR Image Denoising with Morphological Filters on Complete Lattice

Abstract

In this paper, we propose a robust approach to denoise in forward looking infrared (FLIR) imagery taken from an airborne moving platform. We use morphological filters to reduce noise and clutter and better preserve important details. Based on target intensity and shape information, motion criteria, the proposed algorithm uses morphological filters by reconstruction to estimate background of image, and proposes adaptive nonlinear wavelet using the lifting scheme to remove Gaussian white noise. The experiments performed on FLIR image sequences, show the robustness of the proposed approach.