Skip to content

Atmospheric Turbulence Mitigation using Complex Wavelet-based Fusion

Research output: Contribution to journalArticle

Original languageEnglish
Pages2398-2408
JournalIEEE Transactions on Image Processing
Journal publication dateJun 2013
Journal issue6
Volume22
Early online date26/02/13
DOIs
StatePublished

Abstract

Restoring a scene distorted by atmospheric turbulence is a challenging problem in video surveillance. The effect, caused by random, spatially varying, perturbations, makes a model-based solution difficult and in most cases, impractical.
In this paper, we propose a novel method for mitigating the effects of atmospheric distortion on observed images, particularly airborne turbulence which can severely degrade a region of interest (ROI). In order to extract accurate detail about objects behind the distorting layer, a simple and efficient frame selection method is proposed to select informative ROIs only from goodquality frames. The ROIs in each frame are then registered to further reduce offsets and distortions. We solve the spacevarying distortion problem using region-level fusion based on the Dual Tree Complex Wavelet Transform (DT-CWT). Finally, haze removal is applied. We further propose a learning-based metric specifically for image quality assessment in the presence of atmospheric distortion. This is capable of estimating quality in both full- and no-reference scenarios. The proposed method is shown to clearly outperform existing methods, providing enhanced situational awareness in a range of surveillance scenarios.

Documents

  • Finalised jrnl

    Rights statement: (c) 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

    Author final version (often known as postprint) , 30 MB, PDF-document

    9/06/14

DOI

View research connections

Related faculties, schools or groups